VOLUME 11, ISSUE 4, APRIL 2022

Abstract: IoT-based health monitoring systems lower frequent visits to hospitals and meetings between doctors and patients. However, patients suffering from chronic diseases require regular health observation by clinical staff. In this proposed work, I have taken advantage of the IoT technology to make patients' lives better for prior determination of disease and treatment. A smart vital monitoring system is being designed using Internet of Things (IoT) technology which can observe the pulse rate, oxygen level, blood pressure, and temperature of a patient. This framework is useful for country regions where close by clinics can be in contact with city medical clinics about their patient's health conditions. If any changes happen in a patient's health in view of standard qualities, the IoT framework will alarm the doctor or specialist accordingly. This patient's vital monitoring framework with the use of IoT assists medical specialists to gather patient's health information continuously. The accessibility of fast internet permits the framework to screen patients' vitals at regular intervals. This framework would also help in identifying and early treatment of COVID-19 patients. If the patient's heart rate or body temperature or body oxygen levels falls below standard values, then the IoT framework will alarm the doctor or specialist accordingly.

Keywords: Telehealth, Internet of Things (IoT), Remote Patient Monitoring, and E-Health

Abstract: An object of the study is the potential risk of hosting the server outside of the country. The goal of this article is to define the risks and opportunities associated with the rapid development of cloud technologies and their penetration into almost all technological areas. The modern-day economy is evolving under the influence of information and communication technology. People are witnessing huge success in every sphere of management and economy with the use of Cloud Computing, Big Data, and Cyberphysical Systems. Modern life and work are shaped by cloud computing. It has become a part of the daily lives of people. Companies of all sizes have now turned to cloud computing for their business needs. Currently, everyone is talking about the cloud solution as a way to save money and increase the efficiency of resources. However, nothing is perfect, and this is no exception for cloud computing. The use of this technology is undoubtedly beneficial, however, there are some risks and concerns that should not be overlooked. The purpose of this article is to raise awareness about the ongoing war between Ukraine and Russia, how it impacts cloud technology when hosted outside of the country. Furthermore, this article will also look at how this war affects the IT industry if organizations depend on their operations and get support from outside countries, including hardware, software, network infrastructure, data centers, mobile device management, cloud computing, cyber security etc. Although cloud computing is developing rapidly, both conceptually and practically, legal, contractual, economic, service quality, interoperability, security, and privacy issues continue to pose significant challenges. The discussion focuses on critical challenges in cloud computing: regulatory, security, and privacy issues. A brief presentation on the future trends of cloud computing deployment is also presented, together with some solutions to mitigate these challenges.

Keywords: Cloud Computing, Bigdata, Blockchain, Cyber Security, Russia & Ukraine Cyber War, IT Army, DDos.

Abstract: In this high-tech era, technology has made it possible that everyone can live a comfortable life. But somehow the blind humans want to depend upon others of their each day lifestyles which in the long run makes them much less assured in an strange environment. However in recent times the explosion of progressive generation provides many possibilities for them to stay expectantly without feeling as a burden. So, on this paper, we recommend a new concept of an shrewd taking walks stick tool that can be used for protection and navigation to manual them to attain their vacation spot region competently without going through any problems. This system is made with the sensor incorporating the networks that can be implemented within a walking stick, which can provide the group communication between them, in which the navigation information and networks can be provided. It performs some functions such as Real time tracking, Real time monitoring of user, Emergency alert to the guardian, ambulance or police, Obstacle Detection, Voice assistant. It consists of Arduino, Global Positioning System (GPS) along with sensors like Ultrasonic and other supportive sensors and an Android-based Application (APP). Keywords. Intelligent device, Arduino, Ultrasonic Sensor, GPS.

Abstract: Communication can be defined as a act of exchanging information, Emotions, Feelings among each other or group of people. But in case of Dumb & Deaf people it becomes difficult to communicate. In this paper, a real time System for Sign Language detection was built through the images captured by PC camera. The main aim of this project is to help Disabled people, Dumb & Deaf, Paralyzed people to communicate with ease. This model detects the sign irrespective of the standard Sign Language. The existing Digital Models are slow, they take very plenty amount of time just to print a Alphabet, and thinking of whole sentence is a lot of time. This model overcomes the problem of time as it detects it as whole word other than a single alphabet. This model is proposed using TensorFlow Algorithm was made using a set of images for particular sign in different skin tones, lightning, and background, etc. The system displays high accuracy of 80-90% for the sign detection.

Keywords: Sign Language, Gestures, Real Time, Labeling Software, TensorFlow Object detection module.

Abstract: A Farmer with an average income has to work a lot every day. They have to spend hours on the field and then in the market. Our motive is to provide solutions to farmers' day to day problems by allowing them to buy their equipment online and by also allowing them to sell their crops online. This in result will reduce their working hours and will give them more time to focus on their field work. This paper focuses on the different aspects of agriculture and the impact of technology on it.

Keywords: Farmer, Crops, Agriculture

Abstract: Social media apps are proving to be very effective in today’s generation and have a great impact on society. So, we came up with the idea of preparing an application like WhatsApp - one of the top social media apps. Web application is nowadays in the demand of the web development sector. We have tried to develop a message application like WhatsApp (like a clone which is a process of creating a website with similar architecture, features, and functions of a website / web application).

Keywords: Django, Python, SQLite, App-Cloning.

Abstract: The exponential growth of data generation is difficult to perceive. Every enterprise has a lot of data, some of which they don’t even accumulate due to difficulty of data extraction and selecting the most relevant data. Hence, appears the mistake of neglecting useful data amidst other unproductive data. This phenomenon does not depend on the company’s ability to compute and communicate, but rather on the ability to provide adequate information, to take good decisions and to compare results with the planned objectives. These can be done through adopting modern approaches to machine condition monitoring. Machine condition monitoring or condition-based monitoring is the process of monitoring machinery conditions while in operation. The data generated by machines provide with real insights into near real-time values of the machine parameters which are helpful for analysis. This paper shows how this methodology has developed, the main features and benefits of Data Extraction and Remote Machine Condition Monitoring. By taking measurements of pressure, temperature, and vibration, we are more likely to identify early malfunctions resulting in costly shutdowns. In turn, it will ensure the long-term and effective operation of entire machine systems.

Keywords: Condition Monitoring, Dashboards, Fault detection, Data extraction.

Abstract: The Most of the energy meters are designed to bill as per the units of energy consumed. These meters need to be manually read by people in order to provide monthly/quarterly bills. We here propose a prepaid energy billing meter. The system is designed to allow amount of energy to be used as long as the account has balance pending. It also allows the operator to recharge the user account using GSM. Index Terms: Smart Meter, Prepaid Energy Meter, Arduino, GSM.

Abstract: The objective of this project is designing a system for running hotel management business. The flexibility of the system should be kept in mind in order to make the system more user friendly. We need to learn about the proper working and all the procedures of the hotels by visiting different hotels and gaining experience of the industry. The quality of the system depends on the diversity in the sources. This system will be providing all the information related to the availability and the amenities provided by different hotels along with precise comparison.

Keywords: Hotel, FlexibleManagement, Bootstrap,Flask.

Abstract: Image viewers that are available online currently pose a challenge to the users regarding the usability. With further investigations it was found that the users also face the barrier of cost. Most of the available free version of image viewer a user has to satisfy its needs with just basic features as all the other significant features comes at a cost. Therefore our project tries to tackle all of these problems. friendly. Image Viewer Slideshow, provides basic features ranging from opening a photo, zooming in and out , sliding pictures to see the next picture to advanced features like taking a live picture, editing the clicked photo to sharing the photo and even deleting it. It is a simple android application which would help the users to access and use the app to edit images of various formats by giving them several options to choose from. This application will also have a highlight slideshow feature which will enable the user to view their images in one go. This app is made to be user friendly.

Keywords: features, user, image, photo, images, basic, picture, available, viewer

Abstract: Attendance management is important to every single organization, it can decide whether or not an organization such as educational institutions, public or private sectors will be successful in the future. Managing student attendance during lecture periods has become a difficult challenge. The ability to compute the attendance percentage becomes a major task as manual computation produces errors, and wastes a lot of time. For the stated reason, an efficient Web-based application for attendance management system is designed to track student’s activity in the class. This application takes attendance electronically and the records of the attendance are storing in a database. Student attendance management system deal with the maintenance of the student’s attendance details. It is generates the attendance of the student on basis of presence in class. It is maintaining daily basis of attendance, the staff will be provide with the separate username and password to make student attendance. The staff handling the particular subject to responsible to make the attendance for all stu- dents. Only if the student presents the particular date, the attendance will be calculated

Abstract: Competition is rapidly growing in businesses requiring entrepreneurs to create product excellence and to study the behaviour of consumers. One of the advantages that can be done by entrepreneurs is utilizing technologies under development. Technological developments enable employers in small, medium, and large companies to do business by using the Internet. Now the development of the Internet can be integrated with mobile devices such as mobile phones to make the flow of information more widely. Sole Traders and small-scale businesses running on WhatsApp, Instagram do not have a simple platform to run their businesses. These businesses need to spend a lot in setting up their inventory, accounting systems or make manual bookkeeping via excel or paper notebooks. Generic Inventory Software for online and offline business is a mobile-based application that serves as a one-stop-shop for sole traders, freelancers, sellers trading via Instagram, WhatsApp, etc., and small-scale businesses. The application of mobile-based inventory is to make users inventory, with a menu that is available in the form of product items. This application can make traders organize, process, and monitor the movement of inventory items more easily. It will also help improve performance and accommodate transaction inventory items in stores. Hence, it can provide optimal results in speed, precision, and accuracy in performing daily business.[1] Keyword: Mobile-based application, inventory, small-scale business, products, QR code, transaction.

Abstract: Smart Vision is an assistant for blind people which provides the outline of their environment. The smart vision aims to bring the attractive world as a narrative to the visually impaired. The narrative is generated by converting the scenes within their surrounding to text which describes the important objects in the scene. samples of text include 'Children playing within the garden', 'people walking', 'Book kept on the table'. The keywords and one line is played within the variety of audio. Smart vision aims to produce this missing experience for them. The system uses state of the art deep learning techniques from Microsoft Cognitive Services for image classification and tagging. The experience is powered by the python voice assistant.

Keywords: Smart Vision, Deep learning, Microsoft Cognitive Services, image classification, voice assistant, tagging.

Abstract: This project presents the overall design of Home Automation System (HAS) with low cost and wireless system. It specifically focuses on the development of an IOT based home automation system that is able to control various components via internet or be automatically programmed to operate from ambient conditions. In this project, we design the development of a firmware for smart control which can successfully be automated minimizing human interaction to preserve the integrity within whole electrical devices in the home. A smart home will take advantage of its environment and allow seamless control whether the user is present or away. With a home that has this advantage, you can know that your home is performing at its best in energy performance. Implementing this system will allow you to explore a variety of engineering tasks, including software programming, circuit board design, Wi-Fi, TCP/IP protocols, web server logic design, and other aspects. This automation system allows you to better understand the challenges of software and hardware development.

Abstract: The use of machine learning and specifically neural networks is a growing trend in software development, and has grown immensely in the last couple of years in the light of an increasing need to handle big data and large information flows. Machine learning has a broad area of application, such as human-computer interaction, predicting stock prices, real time translation, and self -driving vehicles. Large companies such as Microsoft and Google have already implemented machine learning in some of their commercial products such as their search engines, and their intelligent personal assistants Cortana and Google Assistant. The recognition and classification of the diversity of materials that exist in the environment around us are a key visual competence that computer vision systems focus on in recent years. Understanding the identification of materials in distinct images involves a deep process that has made usage of the recent progress in neural networks which has brought the potential to train architectures to extract features for this challenging task. This project uses state of-the-art Convolutional Neural Network (CNN) techniques and Support Vector Machine (SVM) classifiers in order to classify materials and analyze the results. Building on various widely used material databases collected, a selection of CNN architectures is evaluated to understand which is the best approach to extract features in order to achieve outstanding results for the task. The results gathered over four material datasets and nine CNNs outline that the best overall performance of a CNN using a linear SVM can achieve up to 92.5 % mean average precision, while applying a new relevant direction in computer vision, transfer learning. By limiting the amount of information extracted from the layer before the last fully connected layer, transfer learning aims at analyzing the contribution of shading information and reflectance to identify which main characteristics decide the material category the image belongs to. The results of the comparison emphasize the fact that the accuracy and performance of the system improves, especially in the datasets which consist of a large number of images.

Keywords: Image Classification, Convolutional Neural Network, recognition, TensorFlow, CIFAR-10, Support Vector Machine

Abstract: This paper focuses on predicting the rice harvest and investigating the factors affecting rice production in various regions of the Maharashtra region of India. The software aims to provide a rice harvest using a random forest algorithm and accurately predicting the yield. To demonstrate the effectiveness of harvest forecasting, an Indian government database will be used in 34 districts of the Maharashtra region, India [2]. Boundaries such as rainfall, temperature, humidity, and location are given as a contribution to the random forest model to define the annual variation of the regional rice crop in Maharashtra. The software will also use other IoT devices to retrieve real-time data from the field. This will give an accurate result to farmers and prevent major losses to farming. With the help of powerful services like Amazon Web Services(AWS), Java, and Flask it tends to work on low-end devices and remote regions.

Keywords: Amazon Web Services(AWS), Flask, REST API, Android Studio, MySQL, Java, Arduino Ide and Random Forest Regression.

Abstract: The current medical system focuses on specific, well-known diseases and is unable to accurately diagnose and predict disease based on early symptoms. These models use a variety of patient characteristics to balance the probability of an outcome over some time and to harness the power to improve decision-making and personal care. Discovering hidden patterns and collaborations from a medical website and the growing testing of a predictable disease model is essential. This paper aims to design a model which can easily diagnose various diseases relying on their symptoms. The model evaluates the user’s symptoms as input and returns the disease probability as an output[1].The disease probability is calculated by making use of the naive bayes classifier. Therefore this research paper will attempt to apply machine learning activities to health facilities in a particular program. The proposed web-based forecasting app uses the Naive Bayes Algorithm and Decision Tree, a machine learning method as a diagnostic separator based on real-life clinical information.

Keywords: Machine learning, Naive Bayes, Decision Tree, Disease Prediction.

Abstract: Sentimental analysis is the analysis of opinions and emotions from any type of message or text. Sentimental analysis of the data is very helpful to convey the emotion of the majority or particular individual. It is also called opinion mining. This technique is performed to find the sentiment of the individual for a given source of content. Online platforms like social media contain a high volume of data in the form of reviews, tweets, comments, blogs, etc. This paper analyzes the movie reviews using various methods such as KNN, Naive Bayes, LSTM, and Random Forest Classifier.

Keywords: Dataset, Sentiment Analysis, Reviews, K-Nearest Neighbor, Naive Bayes.

Abstract: In current technical market, new small level startup are going towards automatic hosting and paying a lot of money to multiple hosting companies. They don't have control over scaling up and down and quality of hosting. Now we are introducing a tool, which can help a startup to scale up their infrastructure as per different architectural setup. We are setting the startup setup over AWS cloud so that they can get the benefit of "pay as we go" model. Now startup company would have full control over infrastructure as well as bills.

Keywords: AWS Cloud Computing, Access key, Secrete key, AWS CLI, Authorization, Authentication, MFA

Abstract: The purpose of the hassle-free doctor Consultation system is to automate the prevailing Manual system by the help of computerized equipment’s and full-fledged computer software, full-filling their requirements, so their variable data/information space are often stored for extended period with easy accessing and manipulation of the identical. Thus, it'll help organization in better utilization of resources. The organization can maintain computerized records without wrong entries. which implies that one needn't be distracted by information that's not relevant, while being able to reach the info. The aim is to mechanized the existing handiwork system by the help of computerized equipment’s and full-fledged computer software, fulfilling their needs, so that their valuable data/information are stored for a extended period with easy accessing and manipulation of the identical. Basically, the project describes the thanks to manage permanently performance and better services for the clients. This Project is also a mix of various medical services for the people of all generation and people belonging any nation or urban area. It consists of all the information about the doctors around the location of the user.

Abstract: This article gives the important aspects of technological progress in digital agriculture. This has a big impact. With the advent of artificial intelligence, machine learning and digital agriculture implementation challenges, and new applications, agriculture is transforming traditional agricultural practices into a highly modern digital agriculture.

Keywords: Digital Agriculture, Machine learning, Artificial intelligence, Digital farming.

Abstract: House price forecasting is an important topic of real estate. Machine learning techniques are applied to analyze historical property transactions to discover useful models for house buyers and sellers. Revealed is the high discrepancy between house prices in the most expensive and most affordable suburbs in the area. Significant time and expertise are needed to customize the model for a specific problem. A significant way to reduce the complicated design is by using Automated Machine Learning that can intelligently optimize the best pipeline suitable for a problem or dataset.

Keywords: House Price Prediction, Machine Learning, Google Oauth, Python.

Abstract: IoT devices are getting increasingly popular. Several IoT issues highlight the necessity for IoT security. The number of assaults on these devices is growing, and most of them are minor variants of previously known attacks that can get beyond traditional firewalls. Existing systems are incompatible with IoT devices due to their low computing capability. Signature-based intrusion detection can only detect known patterns and attacks; therefore, it can't detect newer attacks with unknown patterns. Many systems also use cloud computing, which has the disadvantage of requiring constant internet access, as well as the fact that cloud services are frequently charged. The paper employed a Random Forest ML model to develop a real-time anomaly-based detection system. When a newer attack is detected that is not screened by the firewall, the anomaly-based intrusion detection system kicks in. It can handle newer/unknown assaults that signature-based systems cannot. We are also installing the IDS on a local, higher-powered device rather than using the cloud. The model developed using the IoT network traffic dataset generated by the IoT node in question. Keywords - Intrusion Detection, Network Security, Anomaly Detection, Internet of Things.

Abstract: The discovery of Blockchain has drawn in tremendous interest as of late as it gives security and protection through unchanging disseminated record. Web based casting a ballot is a pattern that is picking up speed in present day culture. It can possibly diminish hierarchical expenses and increment citizen turnout. It takes out the requirement to printing polling form papers or open surveying stations-citizens can cast a ballot from any place there is a Web association. Because of its cordial agreement instrument and sealed information capacity, it is generally embraced in the fields where trust is given utmost prominance. Encryption using homomorphic calculations can be utilized towards work on the information as it is encoded without the information on private keys. Activities may be achieved on a encoded information without the need of unscrambling the information. An electronic democratic framework ought to be secure, and it shouldn't permit copy casts a ballot and be completely carefully designed, while safeguarding the protection of the electors.

Keywords: Homomorphic Encryption, E-voting, ballot entry, Web based Application

Abstract: The enormous growth of web and its user base has become source amount of knowledge available online. This information is also helpful for users, to suggest items or services as per their preferences. Recommender system plays the role of generating suggestions by collecting user information like preferences, interests, and locations. The research on recommender systems gained importance after the emergence of collaborative filtering. Generating suggestions in step with user preferences may be a complex task for recommender systems. Recommender system uses information from many sources to form predictions and to suggest an item for a user. This project are a one-stop tool for travellers planning their vacations by providing them suitable recommendations in step with preferences.

Keywords: Recommender Systems, Machine learning, Collaborative Filtering, Cosine Similarity, Travel and Tourism.

Abstract: As in India every person traveling from one location to another so instead of going to call a taxi person the travel website plays important role. By using travel website and use mode of transportation like train and bus reduces time. Many users are interested in the usage of smartphones for their trips. Effects of a travel website on tourists' destination images were observed and calculated. The main relationship between the information search using websites and destination image was studied and examined. A comparison design was conducted using two sets of students as experimental and control groups. A travel website search was the most important for the experimental group. Results showed that exposure to a travel website significantly affected the majority of cognitive. Additionally, experimental design was shown to be an effective method in measuring changes in destination. This study aims in investigating the determinants of their intentions to adopt information for travel decision making. This project suggests a combined model to examine person intentions to use travel information. The results show main determinants influence people intentions to use travel information on smartphones for their ease of use, social influence, and satisfaction with travel websites.

Keywords: finding routes, schedules, travel, destination

Abstract: Photo editing is that the changing of images. These images will be digital photographs, illustrations, prints, or photographs on film. Some varieties of editing, like airbrushing, are done by hand et al are done using photo editing programs like Photoshop, Gimp and Microsoft Paint. Photo editing is completed for several reasons. Many photos of models are edited to remove blemishes or make the model "better". this is often usually called retouching, airbrushing or Photoshopping, whether or not Photoshop or airbrushes aren't used. Other reasons to edit a photograph include fixing errors, practical jokes, and to trick people. Photo editing is additionally accustomed make completely new images. Photo editing is typically called photo manipulation, usually when it is accustomed trick people.

Keywords: colorized photo, Grayscale imaging, cartoonist photo, retouching photo, vintage effect.

Abstract: The Intelligent Transportation System is part of several smart city applications where it improves the processes of transportation and commutation. Its aims to organize traffic problems, mainly traffic jams. The road traffic flow prediction system has wide application in the city transportation and area management. In Some cities, it is very hardest task to manage traffic. But the prediction with reflection of some physical conditions of environment and weather like raining, thunder is found more effective. we Proposed a Road traffic flow prediction system model to predict the Road traffic flow with a duration interval of one hour up to 24 hours. The algorithms are used for research in the past, but there are not so many platforms found on which road traffic flow prediction has easy to use and access to public users. The system is Proposed to organize the problems Related with the historical and time series. Historical road Traffic data set was collected from an open source and various operations perform on it as per requirements. By using Machine learning algorithms, a system is designed, which gather the data from the roads using Vehicle detection sensors and stores into the database for future predictions. We also gathered the data of weather systems to get weather data. This road Traffic flow prediction system is developed to use the existing popular ML prediction algorithms that Support Vector Machine (SVM). After experiments, results were differentiated with the actual data to check the correctness of the algorithms. Support Vector Machine (SVM) helps to predict in short term road traffic flow prediction. But a shorter time interval Provides more accurate results.

Keywords: Traffic Prediction, Support vector machines, artificial neural network, Prediction, Jams

Abstract: Language Translation is the process of detecting the language from any kind of Text, Text File, or an Image and then translate it into target language. Implementation of a Natural Language Processing model for Language Translation is to be carried out in this project. The major task is to identify those features or parameters which could be used to clearly distinguish the language and translate it. This model makes use of Machine Learning, Artificial Intelligence, and Natural Language Processing. The project aims at detecting Japanese and translate it into English. Experiments were conducted by forming text samples obtained from online articles and social media. This corpus comprises of general articles, each of them spanning over at least 100 words. The entire corpus is split into two sets, larger unit as the training data-set and a smaller set as the test set.

Keywords: Language, Translation, Japanese, English.

Abstract: OCR has been an interesting topic for many years now. The main use of this OCR is to make documents which can be editable from existing paper documents (or) even image files. To develop this OCR we are need of approaches . To recognize the character image processing algorithms are needed. In this paper mainly focusing about MLOCR, dataset, Prediction accuraies in Neural Netwok.

Keywords: Optical Character Recognition, CNN, Pattern recognition, Handwriting Recognition, Document Image, MLOCR.

Abstract: The five daily Muslim prayer times namely Fajr, Zuhr, Asr, Maghrib and Isha vary from place to place and from day to day.The timings of those five prayers aren't even for places with equal time zones[3] .The actual timing of every of the prayer is important, due to the fact it's far compulsory for each Muslim to carry out those prayers at the perfect time . The prayer time for any given place can be mathematically determined if certain parameters such as the coordinates of the location are known[3]. The aim of our project is to build a mobile based application that serves an objective of providing features like calculating accurate prayer time, allows the users to set a reminder or set a timer on your smartphone so, that they can easily access time for prayer, keeping a track of user’s prayer, fasting tracker, Islamic calendar, site of halal food and shops in non-Muslim countries, qibla compass and also allows the users to set a reminder that notifies the user with adhaan when the respective prayer time is in his area. This application will be used as a guide and prayer time reminder through which users can get their current location and current Gregorian as well as Islamic date and month. Our app will provide these mentioned features and functionalities needed for helping to perform prayers on time, which is user friendly in order to bring comfort to the users. Keyword: mobile based application, prayer times, prayer tracker, fasting tracker, Islamic calendar, halal shops, qibla compass.

Abstract: The Internet of Things (IoT) and cloud computing (CC) have arisen as new platforms in the twenty-first century's ICT revolution. Experts believe that the Cloud IoT paradigm can considerably improve healthcare services and contribute to its ongoing and systematic improvement if it is adopted in the healthcare industry. With the latest innovations in the Internet of Things (IoT) and Cloud Computing, the sector of healthcare is becoming increasingly explored. The Internet of Things will assist physicians and hospital employees in carrying out their responsibilities in a more comfortable and informed manner. With the most recent innovative solutions, the majority of the obstacles associated with the use of IoT and Cloud Computing have been handled, and this technology has the potential to be a big revolution with several benefits in the digital future. The healthcare industry is one of the most promising applications for the Internet of Things technology. When it comes to urgent situations, the most significant application of the Internet of Things is the ability to monitor and make timely judgments. Because of this technology-based treatment strategy, there is an unparalleled chance to improve the quality and productivity of treatments, as well as the well-being of patients and the ability of the government to provide more financing. We present a complete review of the key applications of IoT and CC in healthcare in this paper. Additionally, this paper will discuss the state of the art and gap analysis of various levels of integration components by examining several existing ideas for Cloud-integrated IoT-Health systems. Moreover, this paper discusses the role of IoT in the pharmaceutical business, including its problems and uses. Finally, the author identifies research problems and future directions.

Keywords: IoT; healthcare system; cloud computing; pharmaceutical manufacturing; security; privacy.

Abstract: Brain Excrescence is thought of as one of the forceful circumstances, among kids and adults. Cerebrum excrescences develop really presto and in the event that not treated well, the endurance chances of the case are genuinely less. In advance disclosure of cerebrum excrescences is really significant. Legitimate treatment arranging and exact diagnostics is at the highest need to improve life expectation of the cases. The X-ray pictures are inspected by the radiologist. Manual assessment can be blunder inclined because of the place of entanglements associated with mind excrescences and their packages. Thus a mechanized cerebrum excrescence revelation framework is requested to descry excrescences at its beginning phase. A notable division issue inside X-ray is the undertaking of marking the towel type which incorporate White Matter (WM), Dim Matter (GM), Cerebrospinal Liquid (CSF) and every so often neurotic apkins like excrescence and so on. This paper depicts a successful framework for programmed mind excrescence division for the introduction of excrescence apkins from MR pictures. In this framework division is done utilizing K-implies grouping calculation for better execution. This upgrades the excrescence limits more and is authentically presto when contrasted with various other bunching calculations. The proposed design is more exact and compelling.

Keywords: Magnetic Resonance Imaging (MRI), White Matter (WM), Grey Matter(GM) , Cerebrospinal Fluid (CSF), Image segmentation, K- means.

Abstract: In the world of Internet of Things (IOT), interactions among physical objects have become a reality. Day by day items would now be able with outfitted of computing power and communication functionalities, permitting objects everywhere to be associated with one another. This has bought a new uprising in industrial, financial, environmental systems and triggered great challenges in data management, wireless communications and real-time decision making. Biggest IOT applications is the Smart shopping cart. The Smart Shopping system comes with the smart embedded device with RFID reader for scanning the RFID tag of products, the LCD display for displaying the bill, a data modem module for manipulation and sending data to the billing unit using wireless communication.

Keywords: Smart Trolly, Smart Trolly with Automatic Billing using RFID, Smart Trolly With Automatic Billing System through RFID using ATTINY

Abstract: E-Challan System is an online platform which basically aims at providing a wide range of support in monitoring and managing the traffic penalties, helping the users regarding the problems which they might face in paying their challan. The E-challan System is basically an online platform or an app which helps in interacting between Police and drivers easily. The prototype of this project describes how challan becomes so easy for users through keeping it online. This online platform basically aims to bring down the manual process, paperwork and helps in increasing the convenience for the users.

Keywords: E-Challan, Flutter, Android Studio, Accident detection

Abstract: The internet has produced a difficult issue for females relating to cyber security in the present era of digitization. Girls and women are constantly confronted with issues such as privacy invasion-emails, e-chats, hate speech, online grooming, spoofing, sexual misbehavior, bullying, hacking, cyber stalking, transmitting morphing, obscene materials and sexual defamation, blackmailing misrepresentation and financial gain or espionage. Low computer literacy and internet illiteracy among women is also a major source of victimization. Online abuse, rather than being a means of communication, is literally famous as a type of abuse or violence against women and girls. Privacy infringement, illegal monitoring, cyber stalking, unlawful access to data, and retaliation are all becoming increasingly sophisticated in the IT business. Key Words: Cyber crime, cyber security, cyber space, cyber law.

Abstract: Systematic case paper management system for homeopathy doctors automates activities of each and every homeopathy doctor’s in their hospital, in hospital and generates reports in few seconds. Doctors can easily add, edit, search, view and print case paper and also they can add follow up details of patient, doctors can able to see all the graph of patient like total number of case papers, last month case papers, current month cases papers, weekly cases papers and pie chart of case papers by age. All these can be very efficiently managed from our project.

Keywords: homeopathy doctors, case paper management, homeopathy case paper, software for homeopathy doctors

Abstract: Advances in colour printing technology have increased the level of printing of counterfeit note and duplication of notes on a much larger scale. A few years back, printing could not be done in a printing house, but now anyone can print a note of great accuracy using a simple laser printer. As a result, the issue of counterfeit notes instead of the actual ones has increased dramatically. India is unfortunately cursed by problems such as corruption and black money .And counterfeit money notes are also a major problem. This leads to the creation of a system that receives note of counterfeit currency in less time and in a more efficient way. The proposed system provides a way to validate Indian currency notes. Currency note validation is done for image processing concepts. This article describes the release of various aspects of Indian currency notes. MATLAB software is used to extract note features. There is therefore a need for a system that can make the process of separating counterfeit money more manageable and efficient. This paper is an attempt to create a program that will take a scanned picture of suspicious notes of Rs.10, Rs.20, Rs.50, Rs.100, Rs.500 & Rs.2000 and get fake notes to provide a promising solution to the problem of counterfeit money.

Keywords: Rs.10, Rs.20, Rs.50, Rs.100, Rs.500 & Rs.2000, Image Processing, MATLAB, Counterfeit notes, maximum accuracy.

Abstract: Pathology The diagnosis of pathology in a chest X-ray is generally complicated, even for experienced practitioners. A system that can automatically diagnose the findings in images obtained through X-rays of the chest can be useful in the medical examination of the patient as there is a shortage of experienced doctors. Classifying the chest X-ray is a multi-label classification task as a patient may have multiple diseases. In this research, we aim to develop an algorithm using deep learning techniques to identify the condition in the chest X-ray with high accuracy. In this research, we fine-tuned a pre-trained CNN architecture named DenseNet-121 to extract the features from the chest X-ray and to classify the extracted features into the pathology. The weights of the model are initially set with the weights of a model that is trained on ImageNet. Then the model is trained on a sample of the "ChestXray14" dataset.

Keywords: Chest X-ray; CNN; CAD; DenseNet.

Abstract: In 2012, 775 deaths were recorded, and many more were injured on construction sites in the United States. Of this, 415 deaths (54%) were caused by falls, slipping, walking and falling objects. To reduce mortality in construction sites at these types of events, the Occupational Safety and Health Administration (OSHA) provides Fall Prevention and OSHA-10 training to construction workers. In addition, security personnel monitor whether employees are using protective equipment (PPE) properly. Data show that construction deaths have dropped by 2% per year since 1994; however, the owners are not satisfied with this result. Various studies have shown that falls are a major cause of death in construction. One study showed that half of all deaths due to falls were due to employees not using PPE or not using it properly. In addition, studies have shown that with proper use of hard hats, deaths from falls, slipping, walking, and falling objects can be reduced. The study developed and tested a strong hat acquisition tool that uses image processing techniques to determine if employees wear strong hats. The tool sends warning messages when employees do not use hard hats.

Keywords: Hard Hat , Construction Site , Work Place Safety , Workers .

Abstract: With the rapid growth in users of social media in current years, their users get attracted to the use of social media data for sentiment analysis of people or a particular product or event. The word sentiments describe feelings like emotion or opinion. Sentiment analysis includes identifying how sentiments are expressed in texts and whether the expressions indicate positive or negative opinions toward the subject. An important part of our information-gathering behavior has always been to find out what other people think. With the growing availability and popularity of opinion-rich resources such as online review sites and personal blogs, new opportunities and challenges arise as people now can, and do, actively use information technologies to seek out and understand the opinions of others. Online shopping sites encourage users for posting reviews about products they purchase. Such reviews are useful for new users to make the decision about the product at the time of purchasing and for manufacturers of that product to make decisions about its production. Thus, sentiment analysis of product reviews is becoming popular in text mining and computational research. Social Media houses a vast amount of data that can be utilized for data mining. It has become an inseparable source that has been influencing the lifestyle of millions of people.

Keywords: sentiment analysis, opinion mining, social media, product safety, natural language processing

Abstract: Currently we are staying in the worst possible time in today’s day and age the society has ever seen in terms of our women’s security. The main aim of the following. Project is basically building an effective, very fast and a reliable system to make the women of India feel safe and also empowered. The app we made will act as a very helpful companion for the women, so they don’t ever feel that they are standing alone in the middle of any crisis or situation. This application is very user-friendly application. Which can be used by anyone who has installed the application in their respective smart phones. Our aim is to provide you with the fast and simple way to contact your loved ones or family with just a click of a button or by shaking your device. The idea is to reduce the time or makeup the time it takes to arrive at the location.

Keywords: React Native, Cross platform, Android Application, Women Safety

Abstract: In the area of the internet, various online attacks have been increased and among them the most popular attack is phishing. Phishing is an endeavor by an individual or a group to get personal confidential information like passwords, credit card information, etc from unsuspecting victims for identity theft, financial gain, and other fraudulent activities. The proposed approach can solve the problem of phishing. An image-based authentication using Visual Cryptography (VC) is used. Visual Cryptography is a secret sharing scheme which owns the technique of sharing visual information. The QR (image) is getting divided into two shares. Here the secret QR is divided into two irregular patterns of images called shares and they can be unraveled without any complicated cryptographic computation.

Keywords: Secure Server Verification, Secret QR, Visual Cryptography (VC),Card Verification Value, RSA Algorithm.

Abstract: Next Word Prediction also called Language Modelling is the task of predicting the word that comes next. It is a core problem of NLP and has several applications. The paraphrasing generation techniques help to identify or to extract/generate phrases/sentences conveying similar meanings. Next word prediction (NWP) is a major challenge in the field of natural language processing. This paper mainly talks about the Recurrent Neural Network (RNN) and introduces a more effective neural network model named LSTM for supporting next word prediction and Latent semantic analysis (LSA) is a method for evaluating a piece of text using mathematical computing and examining the link between terms in the documents, as well as between documents in the corpus for supporting the paraphrasing generation technique. These models may need a significant amount of computing work, making the model inapplicable for some sorts of applications. In conclusion, although tricky and application-dependent, Proper setting of the learning rate can reduce the lingering time of the neural network.

Keywords: Latent Semantic Analysis, Paraphrasing, Next word prediction, Natural language processing, recurrent neural network, LSTM, Character prediction.

Abstract: Bone age assessment and its comparison with the chronological age is a crucial task to determine the disorders and their effects on the bone when there are fewer documents. It is a time-consuming activity that is performed by the doctors by the method known as ossification. It can be automated with machine learning techniques. In the proposed system, the images of hand radiographs are preprocessed using data augmentation and the feature extraction is done using pre-trained Mobilenet and Xception models. The obtained results have shown that the Xception model gives the best MAE as compared with Mobilenet.

Keywords: Bone Age Assessment, X-ray images, Xception, Mobilenet, Transfer Learning, Deep Learning.

Abstract: Insurance is a means of protection from financial loss that assists you and your loved ones in recovering from a disaster, such as a fire, theft, lawsuit, or a road accident. When you get insurance, you'll be given an insurance policy, which is a legal agreement between you and your insurance provider. When you have a covered loss and file a claim, your insurance company pays you or a designated recipient, known as a beneficiary, according to the terms of your policy. Majority of insurance sales agents use social media, phone calls, text message, in-person meetings, etc to sell their policies, these techniques are not only time consuming and traditional but also have less hit ratio, because the customer may not be interested in that particular insurance or he/she already has that insurance. This paper analyses the different methods of sales and also tries to provide an alternative solution.

Keywords: insurance, sales, analysis, online insurance sales

Abstract: In the organizations, managing the sales and client’s information plays a key role so for managing that information we are going to develop a Sales Aid and Management Portal. Sale's Management portal is used to manage all the products and the services sales details and customer details in the organization. By using this portal, the sales information in the organization can be managed easily and in a secure way. This web portal is very scalable and can be used for small and also for large organizations. With this portal admin can see the agent’s progress and can also share the important messages with the agents. This portal is also used by the agents to save and manage all clients and prospect details. Agents can also manage the client’s general information, contact, opportunities, proposals, and projects details. This Sales Aid portal is specifically for the company which provides insurances such as TATA AIA, IDFC, BajajAllianz, and other similar companies. This portal helps them managing the middle party who sells their insurances to the client. There are different modules in this portal they are Agent module, Admin Module, and Customer Module. These three modules are used by three different persons. Admin module is for admin who provides access to the insurances to the agents and after that, agents shares details of these insurances to the clients.

Keywords: HTML, CSS, JavaScript, Angular.

Keywords: global positioning system, Vehicle Tracking System, Monitoring, Vehicle Location

Abstract: As quoted by Gandhi Ji "Th future of India lies in its village", So many virgin beaches, undiscovered villages, and mountains gracing our land, there is still a lot to unravel before us and the world. The research will be focusing on those unexplored and undiscovered regions and promote tourism in those areas which will help them grow economically. We will also be analysing the comments posted by our visitors as positive, negative, or neutral to help our new visitors to get an idea about that place

Abstract: It might have happened such a lot of times that you just or somebody yours would like doctors facilitate right away, however they're not obtainable thanks to some reason. The heart disease Prediction application is a user support and on-line consultation project. Here, we tend to propose a web application that enables users to induce instant steerage on their cardiopathy through an intelligent system online. The application is fed with numerous details and also the heart disease related to those details. The application permits user to share their heart connected problems. It then processes user specific details to see for numerous health problem that might be related to it. Here we tend to use some intelligent data processing techniques to guess the foremost correct illness that might be related to patient’s details. Supported result, they will contact doctor consequently for any treatment. The system permits user to look at doctor’s details too. The system may be used without charge heart disease consulting online.

Keywords: Naive Bayes classifier, heart disease prediction, Python, Machine learning

Abstract: In the past decade a lot of research has gone into Automatic Speech Emotion Recognition (SER). The primary objective of SER is to improve man-machine interface. It can also be used to monitor the psycho physiological state of a person in lie detectors. In recent time, speech emotion recognition also finds its applications in medicine and forensics. In this paper 7 emotions are recognized using pitch and prosody features. Majority of the speech features used in this work are in time domain. Support Vector Machine (SVM) classifier has been used for classifying the emotions. Berlin emotional database is chosen for the task. A good recognition rate of 81% was obtained. The paper that was considered as the reference for our work recognized 4 emotions and obtained a recognition rate of 94.2%. The reference paper also used hybrid classifier thus increasing complexity but can only recognize 4 emotions.

Keywords: Artificial Intelligence, Machine Learning, Voice Recognition, Speech Recognition, Speech Emotion Recognition.

Abstract: The Covid-19 pandemic has drastically changed the entire social world. During this pandemic everyone was on their phones scrolling or wasting time on these social networking sites. During this brief period of time, we noticed a lot of negativity on these social networking platforms in terms of hate speech, posts, video etc. In addition to that, studies have shown that this negativity on social media affects one's mental health and affects its productivity as well. The main objective of this project is to create a healthy social media platform that creates an optimistic environment thus allowing one to learn and entertain oneself while using social media. Furthermore, teenagers are the largest audience on social media and thus exposure to this kind of negativity at an early age can affect their future life. Proposed project is an application developed with help of Android and concept of Deep learning i.e CNN algorithm which detects images via data sets and see if the content is harmful or not. Moreover, the application also consists of a basic three report based system so that if the image gets slipped by the CNN algorithm the users using the application can report the content and can be removed easily. Conclusion, the proposed system provides a social networking platform with a healthy environment and finds the impact caused by positivity thus leading to greater productivity in oneself. .

Keywords: Positivity, Productivity, Social media, CNN

Abstract: The Covid-19 pandemic has drastically changed the entire social world. During this pandemic everyone was on their phones scrolling or wasting time on these social networking sites. During this brief period of time, we noticed a lot of negativity on these social networking platforms in terms of hate speech, posts, video etc. In addition to that, studies have shown that this negativity on social media affects one's mental health and affects its productivity as well. The main objective of this project is to create a healthy social media platform that creates an optimistic environment thus allowing one to learn and entertain oneself while using social media. Furthermore, teenagers are the largest audience on social media and thus exposure to this kind of negativity at an early age can affect their future life. Proposed project is an application developed with help of Android and concept of Deep learning i.e CNN algorithm which detects images via data sets and see if the content is harmful or not. Moreover, the application also consists of a basic three report based system so that if the image gets slipped by the CNN algorithm the users using the application can report the content and can be removed easily. Conclusion, the proposed system provides a social networking platform with a healthy environment and finds the impact caused by positivity thus leading to greater productivity in oneself. .

Keywords: Positivity, Productivity, Social media, CNN

Abstract: Online Voting is an inclination that is achieving encouragement in modern society. First, take a look at the traditional voting system. Large space and manpower are required to set up voting booths in multiple areas around the city or village. High security has to be maintained on the date of the election. The voter must visit the place where the voting booth is arranged. Sometimes, the voter needs to stand in a queue for a long time. Again, manpower is required to volunteer and assist voters at the place of voting. The voting process is done manually on the voting machine. Vote counting is done with the physical process. Then there is an intermission of a few days for results to be displayed. if we see here in trade national voting system, we need a lot of manpower, energy, and time to conduct this process. Now to get control of the above-mentioned situation, we are going to initiate an application called Online Voting System. Now as we all know, almost everything can be done online. Like Money transfer, Shopping, Booking, etc. And so many other activities are done with the help of the internet. So, with the effortless approach and use of the internet, we are going to take this existing voting system to an advanced level. We are going to develop an online platform with high security so that the same process could be done easily without the waste of time, afford, and energy.

Keywords: Voter, Group, Candidate, Web application, Online, Election, Voting, Results, Mobile.

Abstract: In past some decades we have seen the uses of the mirror the people traditionally use the mirror for their normal purpose like just seeing their face into the mirror but as technology get improved day by day the mirror got new purpose and can be improved as Smart Mirror. Smart mirrors are the future mirrors. It is a part of connected world where it displays news, temperature, weather and more information while looking and grooming ourselves in front of mirror every morning. Our System includes raspberry Pi model with IoT based circuit and a speech recognition device and we use specialized glass frame for encasing the system. This paper describes the design and working of the mirror build using given devices which is also known as the Smart Mirror. The features of these mirrors have been limited. Goal is to know about a Smart Mirror device that people could interact with and also to further develop the technology so that it would let you install and develop your own applications for it.

Keywords: Smart Mirror, Home Automation, Artificial Intelligence, Raspberry pi.

Abstract: In this era people using vehicles is getting increased day by day. To plan, monitor and also controlling of these vehicles is becoming a big challenge. A system is to be implemented without altering the infrastructure, so a video- based vehicle capturing and analysis of that video without affecting the traffic is required, by which traffic accidents and congestion can be determined. In this paper, we have come up with a solution for the above problem using the video surveillance considering the video data from the traffic cameras. We have used adaptive thresholding method, Gaussian based background subtraction with tracking methods such as blob tracking and virtual detector. The implementation was done using OpenCV Python as a tool. Our proposed system can identify, track the congestion and help in counting the objects precisely.

Abstract: In this study, we used deep learning techniques to recognize the face using only a single image instance for training. Model can also recognize faces under masks and other occlusions. We used a Siamese neural network to implement one shot learning to overcome the problem of data availability.

Keywords: One Shot Learning, Siamese Neural Network, Generative Adversarial Networks, Face Recognition.

Abstract: Our paper provides Detection of Cyberbullying using Machine Learning. In this project, we aim to build a system that tackles Cyberbullying by identifying the mean-spirited comments and also categorizing the comments as bullied one or not. The goal of this project is to show the implementation of software that will detect bullied tweets. As the social networking sites are increasing, cyberbullying is increasing day by day in everyone’s daily life who is using internet access. To identify such bullying tweets in the twitter handle we are going to make a software which will help to detect such mean type of comments with the help of Machine Learning model. As developing ML model, it will automatically detect the mean-spirited comments from the comment section. For this a Machine learning model is proposed to identify or detect and prevent the bullying on social media. As Machine Learning is used, we used two classifiers such as Naïve Bayes and SVM (Support Vector Machine) for training and testing the social median contents. Twitter API is used to fetch tweets and tweets are passed to the model to detect whether the tweets are bullying or not.

Keywords: Cyberbullying detection ∙ Machine Learning ∙ Twitter∙ Tweets ∙ Online harassment.

Abstract: The goal of this study is to develop a transport management system that will help organizations automate their transport operations. this method will allow them to manage their various tasks and activities. The key motive of the transport management system is to assist organizations to minimize the risks related to their transport operations. it's built on a web-based platform that may be utilized by various organizations to manage their various transport operations. The main objective of the transport management system is to permit users to manage their various transport activities. It may also be an accustomed check on their goods transport and tracking their orders. The importance of transport management is immense. It involves various techniques and tools that are required to deliver a successful project. this technique will help the users in improving their planning and scheduling, reducing their time and energy, and making their work more efficient.

Keywords: Transport Management System, automate, accustomed, planning and scheduling

Abstract: The purpose of the Grocery Store Management System is to automate the existing manual system with the help of computerized equipment and full-fledged computer software, fulfilling their requirements, so that their valuable data/information are often stored for an extended period with easy accessing and manipulation of the same. The required software and hardware are easily available and straightforward to figure with. Grocery Store Management System, as described above, can lead to an error-free, secure, reliable, and fast management system. It can assist the user to consider their other activities rather than consider the record keeping. Thus, it'll help organizations in better utilization of resources. It is possible for organizations to maintain computerized duplication. In other words, one does not have to be distracted by irrelevant information in order to succeed in the knowledge. The project is developed with the objective of making the system reliable, easier, faster, and more informative. Basically, the project describes the way to manage permanent performance and better services for the clients.

Keywords: Grocery Store Management System, Billing System, Full-Fledged Computer Software, Better Services for the clients.

Keywords: -Blockchain, access control, identity-based encryption, data Security.

Abstract: We all know that human Face is a unique and crucial part of the human body structure that identifies a person. Face detection which is the task of localizing faces in an input image is a fundamental part of any face processing system. The aim of this paper is to present a review on methods and algorithms used for face detection. The algorithm Haar cascade was described. We represent a methodology for face detection robustly in real time environment. Here we use Haar cascade like classifier to track faces on OpenCV platform which is open source and developed by Intel. The main concept of this paper is to experiment with using deep learning neural networks to detect and quickly respond to crimes in progress with effective Criminal Recognition to reduce the crime rate. Manually doing and tracking is very difficult job for the police. We can use the proposed system to trace the identity of a criminal person. With the advancement in technology, we can place CCTV at many public places to capture the criminal’s image. This system will be able to detect face and recognize face automatically as well. Using the previously captured faces and criminal’s images that are available in the police station, the criminal face recognition system can be implemented. We have used deep learning libraries and some image processing tools to achieve this task.

Keywords: Face recognition; OpenCV; Haar Cascade; CCTV; Deep learning

Abstract: IDEs (Integrated Development Environments) support software developers in their implementation work However, embedded software has specific requirements, so an off-the-shelf IDE for this purpose does not exist. In such a case, this paper recommends developing a customized IDE based on freeware software. We present a Nitro IDE project of developing such an IDE for the languages C/C++, Java, Python and HTML, JavaScript & many more. We used several open source projects with varying project status as a basis for our development. Today’s IDE are mostly not UI friend to user & having limitation, some are paid still not having new features in that. So, we are developing IDE with all of this improvement & unique features like AI chat & voice bot for helping in development, we analyzed developer communication within these open source projects and identified the benefits and the potential pitfalls for the case study Moreover, we present the effort made in terms of person months and that reuse of open source software improves cost-efficiency for the development of such IDEs.

Keywords: Integrated Development Environment, IDE, Code Editor, Software Development, Artificial Intelligence, Programming, coding

Abstract: Research shows that many workers construction is one of the high-risk industries where construction workers tend to be hurt in the work process. Head injuries are very serious and often fatal. Every worker needs to wear a helmet while working in a factory or any construction site. But many workers are ignored and do work without safety equipment. The management tried to control this problem manually but it is insufficient for the real situation. The ideal solution is to develop an electronic detection system that can be automated recognize this kind of problem without human cost. The motivation for this project is to prevent the death of workers due to head injuries by monitoring real-time if a person is wearing helmet while working using Deep Learning techniques. Here, a robust approach is tried, in which CCTV cameras are used to capture the image of humans. The proposed system uses YOLO (You look only once) v3 model that is the used as the state-of-art method for real-time detection with higher rate of accuracy. The detected humans as objects are utilized for calculating the distance between them the rough Euclidean distance calculation method. The proposed model produces reliable outcome compared with the other prediction systems. We use Convolutional Neural Network (CNN) to identify who are workers are wearing helmet while entering a premise. YOLO Dark net is used to get the dependencies.

Keywords: Convolution neural network, Helmet Detection System, Image processing, real time object detection, Machine learning, YOLO, Deep Learning.

Abstract: Most academic institutions struggle to keep track of student data, attendance, finances, admissions, and other pertinent information since they still rely on paperwork and manual processes. By deploying centralized software incorporated with various loosely coupled services that interact with one another to address the issues mentioned above, as well as improve communication between management and students/guardians via email, SMS, and push messages, a web-based school management system will reduce manual work. Because it is a server-side enterprise application, it can be used with desktop browsers, mobile browsers, and native mobile applications. A smart school is a technology-based learning environment where students are prepared for the Information Age. These teaching and learning ideas should be covered to satisfy the educational aims of smarts schools: curricular, pedagogy, assessment, and teaching-learning materials. The second pillar of a smart school is information and communication technology (ICT), which performs a variety of tasks in a smart school, from supporting teaching and learning activities to assisting with school management. Teaching computer labs, a multimedia development centre, and a server room prepared to handle programmes, management databases, and web servers are all examples of technology that can be used to outfit a smart school.

Keywords: Smart school, attendance, fees management, Library, Alumni, etc.

Abstract: Cervical cancer is the fourth top cancer-related deaths of women worldwide. Discovery of cervical intraepithelial neoplasia (CIN) in the initial stage can rise the existence rate of the patients. The structures of the unique (pre-acetic-acid) image and the colposcopic images captured at around 60s, 90s, 120s and 150s during the acetic acid test are fixed by the feature instruction networks. we recommend a deep learning framework for the exact identification of LSIL+ (including CIN and cervical cancer) using time-lapsed colposcopic images. The projected framework includes two main mechanisms, i.e., key-frame feature encoding networks and feature fusion network. Some fusion approaches are associated, all of which outstrip the remaining automated cervical cancer diagnosis systems using a particular time slot. A graph convolutional network with superiority features (E-GCN) is initiate to be the greatest appropriate fusion approach in our study, due to its outstanding explain ability consistent with the clinical preparation. A large-scale dataset, covering time-lapsed colposcopic images from 7,668 patients, is collected from the collective hospital to train and confirm the deep learning framework. Colposcopists are enquired to contend with our computer-aided diagnosis system. The proposed deep learning framework understands a classification precision of 78.33%—similar to that of an in-service colposcopist—which confirms its possible to transport assistance in the realistic clinical situation.

Keywords: Cervical cancer, acetic acid test, graph convolutional network, feature fusion.

Abstract: The patient of Parkinson's disease (PD) is facing a critical neurological disorder issue. Efficient and early prediction of people having PD is a key issue to improve patient's quality of life. The diagnosis of PD specifically in its initial stages is extremely complex and time-consuming. Thus, the accurate and efficient diagnosis of PD has been a significant challenge for medical experts and practitioners. In order to tackle this issue and to accurately diagnosis the patient of PD, we proposed a machine-learning-based prediction system. In the development of the proposed system, the support vector machine (SVM) was used as a predictive model for the prediction of PD. The L1-norm SVM of features selection was used for appropriate and highly related features selection for accurate target classification of PD and healthy people. The L1-norm SVM produced a new subset of features from the PD dataset based on a feature weight value. For the validation of the proposed system, the K-fold cross-validation method was used. In addition, the metrics of performance measures, such as accuracy, sensitivity, specificity, precision, F1 score, and execution time, were computed for model performance evaluation. The PD dataset was in this paper. The optimal accuracy achieved the best subset of the selected features that might be due to various contributions of the PD features. The experimental findings of this paper suggest that the proposed method can be used to accurately predict the PD and can be easily incorporated in healthcare for diagnosis purpose. Currently, the computer-based assisted predictive system is playing an important role to assist in PD recognition. In addition, the proposed approach fills in a gap on feature selection and classification using voice recordings data by properly matching the experimental design.

Abstract: The proliferation of user-generated content on social media has made opinion mining an arduous job. As a microblogging platform, Twitter is being used to collect views about products, trends, and politics. Sentiment analysis is a technique used to analyze the attitude, emotions and opinions of different people towards anything, and it can be carried out on tweets to analyze public opinion on news, policies, social movements, and personalities. By employing Machine Learning models, opinion mining can be performed without reading tweets manually. Their results could assist governments and businesses in rolling out policies, products, and events. Seven Machine Learning models are implemented for emotion recognition by classifying tweets as happy or unhappy. With an in-depth comparative performance analysis, it was observed that proposed voting classifier (LR-SGD) with TF-IDF produces the most optimal result with 79% accuracy and 81% F1 score. To further validate stability of the proposed approach on two more datasets, one binary and other multi-class dataset and achieved robust results.

Keywords: MS Sentiment analysis, text classification, machine learning, opinion mining, emotion recoginition, artificial intelligence.

Abstract: In the economic sector agriculture plays a vital role. Day by day the population is increasing on a large scale with this increases the demand of food. The early methods used by farmers are not sufficient enough to fulfill today’s requirement, thus new methods are invented which in return brings employment for people. Machine learning Technology in agriculture has helped humans a lot such as identifying particular climate for particular crop similarly, it’s soil type, pH value and water supply to the crop. The project consists of implementing a new method for different crop at similar time for larger productivity by predicting it accurately. In this paper we have studied various techniques presented by respected authors using Machine Learning and given below are the comparison between their respective technologies. Keyword: Agriculture Production Optimization Engine, Palm oil, Crop Production, Crop Prediction, Machine Learning

Abstract: This project is a web-based stock system for an existing shop. The project objective is to deliver the online shopping application into Java platform. This project is an attempt to provide the advantages of online shopping to customers of a real shop or Mall. Thus, the customer will get the service of online shopping and home delivery from his favorite shop. This system can be implemented to any shop in the locality or to multinational branded shops having retail outlet chains. If shops are providing an online portal where their customers can enjoy easy shopping from anywhere, the shops won’t be losing any more customers to the trending online shops such as flipcart or ebay. Online E-Mart Shopping System is a website to provide online facility to customer and buy product at from home through online. Our main aim is to provide 24/7 online service for users through online application. Now a days in order to buy product we need to go shops are call by phone and there are very stores which work 24hrs. In order to reduce this gap, we implement an online shopping store through which users can buy products from home by paying amount using credit /debit cards. Overall online product booking store will become an efficient, highly responsive and an extremely accurate system. Keyword: Online Shopping, Products, Shop (Mall), Portal, Web Application, etc.

Abstract: Human face is the critical trademark to distinguish an individual. Everybody has their extraordinary face in any event, for twins. Along these lines, a face acknowledgment and ID are expected to separate one another. A face acknowledgment framework is the confirmation framework to view personally's character through a biometric strategy. Face acknowledgment has turned into a famous strategy these days in numerous applications, for example, telephone open framework, criminal recognizable proof, and, surprisingly, home security framework. This framework is safer as it needn't bother with any conditions like key and card yet, just a facial picture is required. By and large, the human acknowledgment framework includes 2 stages which are face location and face ID. This report contains the manners by which profound learning of a significant piece of PC science field can be utilized to decide the face utilizing a few libraries in OpenCV alongside python. This report will contain a proposed framework that will help in the distinguishing the human face progressively. This execution can be utilized at different stages in machines and cell phones, and a few programming applications.

Keywords: Python, OpenCV, Face Detection, Image Processing

Abstract: Using NLP(Natural Language Processing) and ML(Machine Learning) to rank the resumes according to the given constraint, this intelligent system ranks the resume of any format according to the given constraints or the following requirement provided by the client company. We will take the bulk of the input resume from the client company and that client company will also provide the requirements and the constraints according to which the resume should be ranked by our system. Besides the information provided by the resume, we are going to read the candidate's social profiles (like LinkedIn, Github, etc) which will give us more genuine information about that candidate.

Keywords: Resume, ML, NLP

Abstract: Advances in programming face recognition have made numerous impacts in the evolving scene. A PC framework in my face recognition project will want to locate and recognize human faces in images or recordings captured by an observation camera quickly and precisely. Various calculations and procedures have been developed for working on the presentation of face recognition, but the idea to be implemented here is Deep Learning movements. Today, recording someone's presence is the most important thing for any organization. Someone's attendance at an office or association indicates that they are fulfilling their obligation to attend. This paper explains how to track participation in a simple and effective way. Face recognition provides a precise framework for dealing with ambiguous situations like fake participation. This framework uses an Open CV face recognition library for facial distinguishing proof and participation storage (Python). The picture is captured by the camera and sent to an information base organizer, which contains pictures that distinguish faces and calculate participation.

Keywords: OpenCV, Numpy, DLIB, Cmake, Face Detections, Face Recognition

Abstract: Canteen Automation helps college students and faculty check in online, select the food they need, and order the right food with their fingertips. Registered members can easily place an order by adding products to the shopping cart. As soon as a person places an order for payment and confirms payment, the concession stand will promptly guide them. It works like a full real-time application. It uses a centralized payment interface (UPI). Canteen automation reduces waiting times. This has the advantage that if the kiosk is crowded, the time and meal can be adjusted according to the customer's needs. This is most effective when large gatherings are banned in a pandemic like COVID-19. College users have a specific username and password that they can use to log into the application.

Abstract: Face recognition is a classical problem in computer vision. With the recent outbreak of covid-19 across the globe, there is much focus on face recognition systems as contact biometric methods are unsafe. To implement a face recognition system, the model must be robust and precise. In this paper, we review the past studies of face recognition. Second, this paper implements a one shot learning facial attendance system. Various network architectures are explored to improve the accuracy.

Abstract: Security was a big deal for a long time. Viruses, malware, and ransomware are other problems seen by the practitioner but as an advantage by the terrorist organizations. This paper shows the use of ransomware by terrorist organizations and the preventive methods against them. In the evolution part, the paper provides s study from the first ransomware to the current days. The study shows the light on various kinds of infection performed by ransomware including data infection and infected machines. Different attackers made choices to target various attacks; the paper provides a sight of various target types of ransomware. This paper tries to demonstrate a few ransomware attack case studies to show the problem created by various ransomware as an example. After an attack, what a victim should do after infection is also discussed at the end of the paper. How people can save their system and what are the safety measures to save the system from ransomware, are also discussed by the researcher. At the end of the paper, the researcher points out a few steps to save systems and data. Keywords - Ransomware, Security, Attack, Cryptowall, Crypto lock, Wannacry, Terrorist Organizations.

Abstract: Diabetic Retinopathy is a major disease that has affected over 290 million people globally and 69.2 million people in India, the rate of people getting affected will increase exponentially in the coming years. Diabetic Retinopathy is an ailment linked to the fundus of the eye and can have adverse effects on the patient, if at all left undiagnosed respectively. Our project aims to construct a graphical user interface that can integrate image processing techniques together in order to predict whether the input fundus/retinal image received from the patient is affected with Diabetic Retinopathy or not; if affected, the graphical user interface will display the severity along with the required action needed to be undertaken by the user / patient. This essentially reduces the processing time involved in the process of detecting the disease and also the ophthalmologists can also have our graphical user interface as a backup that can be used for validating or assist in detecting the disease

Keywords: Diabetic Retinopathy, GUI, Convolutional Neural Network, Python.

Abstract: Here we are introducing the motorized screw jack. The vehicle should be lifted for certain type of works. This cannot be done manually. To avoid such problem a jack was invented. To make the work easier than a screw jack we have introduced a new concept called motorized screw jack. We can easily lift the vehicle up and down by using the mobile application. The entire assembly is controlled by app which is made on IOT app maker and the brain of this project is the NODEMCU which controls all the motors by receiving signals from the app with help of a WIFI module, NODEMCU stores the code which is encoded into it by NODEMCU encoder.

Keywords: NodeMCU, Screw jack, Motorized screw jack, Android application

Abstract: A web based voting system for Indian election is proposed for the first time in this paper. Typically the proposed model has a greater security or in other words that decider high security pass word is confirmed before the vote is accepted in the real key database of Selection Commission of India. The additional feature of the model is usually that the voter can confirm if his or her vote moved to correct candidate/party. In this particular model a person can also political election from away from his or her allotted constituency or from his/her preferred location. Inside the recommended system the tallying of the ballots will be achieved automatically, thus saving a huge time and enabling Election Office of India to announce the end result within a very short period.

Keywords: Online Voting system, PHP, My SQL, XAMPP Server

Abstract: This system handles the patients that are victims of mass casualties, during this time, it is important to utilize the limited medical resources available in the hospital. Following this, the system prioritizes the patients pertaining to the categories and fields inherited from Glasgow Coma Scale Study and assigns the patients dynamically to the appropriate medical services. This System asks the hospital initially to set up the number of beds and then they can add patients dynamically by choosing the Glasgow coma scale values which will automatically allocate the bed and can be checked too and dynamically assign the highest priority patients to the next empty bed available. [1]

Keywords: Localhost Server, Ventilator, Discharge, Web Application, Admin.

Abstract: Alzheimer's disease (AD) is a progressive, irreversible brain illness that affects a person's thinking and causes the brain to shrink, eventually leading to death. It's required for the treatment of early stages of Alzheimer's disease in order to prevent further damage .Machine learning algorithms using various optimization and probabilistic methodologies can be used to make this diagnosis. Because no single non-amyloid protein has been proved to consistently diagnose Alzheimer's disease, using machine learning (ML) techniques to determine optimal combinations of non-amyloid proteins is a potential approach. As a result, our strategy is mostly dependent on machine learning in order to separate persons with normal brain ageing from those who are likely to develop Alzheimer's disease.

Abstract: In this bustling life individuals like to get things done to make their brain quiet and watching film is one of the thing however due to enormous informational index of film exist on the planet it is truly challenging for the client to choose film. They need to invest a ton of energy in looking and choosing film. This technique is tedious and troublesome. So suggestion framework make the things simple. In this paper we are building a film proposal framework with mix of two calculations KNN calculation and Cooperative sifting calculation. By and large suggestion framework are produced using cross breed based approach, content-based approach, cooperative sifting approach. This framework made utilizing cooperative separating with various methodology like Matrix factorization, client based proposal. I will tell you the best way to assemble a film recommender program utilizing Python. This will be a straightforward task where we will actually want to perceive how AI can be utilized in our everyday existence. Assuming you check my different articles, you will see that I like to show active undertakings. I think this is the most ideal way to rehearse our coding abilities and work on ourselves. Building a film recommender program is an extraordinary method for getting everything rolling with machine recommenders. Subsequent to sharing the items table, I might want to acquaint you with suggestion frameworks

Keywords: Films recommendation, collaborative filtering, content based filtering

Abstract: This paper describes the development of a Web application for conducting and managing of online examinations for IT-NetworkZ Infosystems, an IT consulting firm’s platform ex-am.com. The purpose of creating such platform is to facilitate organizations and educational institutions in conducting online examinations with control to various useful features. It would help them to manage candidates’ profiles and get accurate statistics on dashboard. It would help the organizations to manage payment of subscription packages for students. It will also be a platform with an easy interface for students for taking exams in a smooth manner.

Keywords: Examination system, Online examination, Computer Based Test, Web based examination.

Abstract: Big data is still an enigma to many people. It’s a relatively new term that was only coined during the latter part of the last decade. While it is still an enigma to many people since its introduction, it’s become increasingly clear over the years that what is big data and its important to so many different firms. There’s a lot of history to study and analyse and this analysis shows how big data has improved and evolved in a very short span of time and also hints at the probable changes and modifications that would come in the near future. In this paper we conduct an in-depth review of the topic evolution of big data and identify how the usage and scope of big data evolved and changed overtime.

Keywords: Big Data, Evolution, Research, History, Technology, Data, Information.

Abstract: Image Steganography is mainly used for hiding an image or secret message in a cover image. For data hiding this technique is being widely used for so many years. Image steganography is being used now by government, individual sender and receiver, in business and in so many fields. Now-A-Days this process has become very popular worldwide. People are doing research on image steganography and inventing new algorithms for image steganography. Hiding data in cover image by modifying bits of that is now optimized by so many new algorithms. Enthusiastic people are increasing demand of researching on image steganography and developing pc software and mobile application using different developing tools, programming languages and their own invention, algorithms etc. Images are the most widespread carrier medium. They are used for steganography in the following way. The message may firstly be encrypted. They’re used for steganography in the following way. The message may firstly be encrypted. The sender embeds the secret message to be sent into a graphic file. This results in the production of what is called steganography-image. Additional secret data may be needed in the hiding process e.g. a steganography key etc. This steganography-image is then transmitted to the recipient.

Keywords: Android App, Image Steganography, Image editing app, Encoding and Decoding.

Abstract: This article compares techniques to manufacturing cast molds by conventional sand-casting and 3-D printing procedures. The techniques were evaluated in terms of lighter weight, tensile strength, hardness, and microstructure. The results demonstrate that there are several advantages to using 3-D printing techniques in mold fabrication. The molds produced by 3-D printing offers a full-size sand saving, tensile strength, hardness, and microstructure.

Keywords: Magnesium alloy; Metal matrix composites (MMC); stir casting; Microstructural investigation.

Abstract: Rendering clothing objects in such a way that user can customize them as per there need. Rendering 3D objects is even more challenging on 2G/3G network bandwidth as the size of objects is quite large. So, to achieve the objective for same, implementation of 2D images rendering in 3D canvas of ThreeJs. With the event of science and technology, within the method of drawing sketch has been regenerate from hand-painted to camera work, the speed of constructing sketches and 3D model has been greatly improved. However, it's still the thanks to image sketch of digital graphic presentation, though the assembly method has been greatly reduced, however in between the homeowners and styler's within the design method of communication and mutual agreement stage continues to be a haul, therefore the homeowners and styler's within the design of the communication method, a way to use WebGL sharing and agreement once the method of however the WebGL will effectively shorten the planning process, can become a crucial analysis topic. This study can use WebGL based mostly 3.js because the core technology of the system construction, interior style is straightforward and straightforward interactive surroundings, through an online based mostly virtual house simulation system, the designers and owners’ exploitation an equivalent WebGL with an equivalent interface then looking for the appliance of this method in cooperation with one another designers and owners of feedback. The benefits and drawbacks of the system and therefore the existing modelling software system are mentioned.

Keywords: WebGL, 3D/2D Rendering Objects, ThreeJs, Blender

Abstract: As the name VISION suggests the major aim of this project is to see and learn. The visually impaired people in the world face a lot of problems in day-to-day life. They need either a human or a stick to guide them through their different daily life tasks. They often get hit by objects because they're not able to see them coming toward them. They're not able to recognize people and objects without touching or hearing them. Entertainment is also a luxury for them since they can hardly operate any device. This research paper depicts a project that can solve all the above problems and perhaps more in long run. This project has applications all over the defense industry, security systems, autonomous cars, robot development, and many more fields.

Abstract: Plant diseases pose a significant threat to agricultural produce and have disastrous consequences for farmers as the world's population grows. Early detection of plant disease can help ensure food security while also limiting financial losses. Images of diseased plants can aid in disease identification. Convolutional Neural Networks' classification abilities are used to generate consistent results. The simplicity of the created CNN model demonstrates its development and innovation; healthy leaves and backdrop images are consistent with previous CNN models. Using CNN, the model can distinguish between damaged and healthy leaves. Plants are the primary source of food on the planet. Plant infections and illnesses are a major risk, and the most common method of diagnosing plant diseases is to examine the plant body for visible signs and growth [1]. Various research efforts aim to identify realistic plant protection techniques and assist our farmers as an alternative to the old time-consuming process. Technological advancements have spawned a slew of new ways to supplement old procedures in recent years [2]. Deep learning approaches are especially effective and powerful in image classification challenges.

Abstract: With increasing road accidents due to improper and non-standard speed breakers, it is the need of the hour to address this issue appropriately, and due to this although speed breakers are built for safety, they are posing to be more of a danger. This is mainly due to building illegal speed breakers and not maintaining existing ones. The existing solutions are largely dependent on the user or the surrounding, both of which do not provide immediate accuracy and dependability. This paper presents self-improving system with minimal user involvement and aims to cover almost all the drawbacks of the current solutions. It suggests speed breaker detection by measuring the difference in the height between the road level and the vehicle. In this approach, GPS coordinates are stored in an online database system that is available to the public through a portal. When the vehicle is at a predefined distance away from the speed breaker, the user is notified resulting in improved accuracy with every usage.

Keywords: Speed Breaker, Detection, Mapping, Proximity, Alerting System.

Abstract: This paper provides a comparative study between node Mcu and Ardunio micro controller board. Node Mcu Board are used for implementing Internet of things applications. IoT IoT is technologies which can be connect with physical objects to Internet. IoT technology can be used with Sensors and any of the electrical or mechanical objects.This paper provides some algorithm such as how IR sensor connected with physical objects. Paper proposed some algorithms which shows that how different sensors connected with physical devices and provides desired solutions and an approach in the form of algorithm (step by step solution) to connect Node MCU ESP 8266 (development board or firmware) with Arduino IDE which provide low power battery operated applications or prototyping of IoT devices. This paper also provides a comparative analysis between NodeMCU development board and Arduino UNO microcontroller board. These are the development boards to generate IoT based applications.

Keywords: Internet of Things, Arduino UNO, Node MCU, IR Sensor, DHT11

Abstract: The Natural Language Processing (NLP) is a sub domain of Artificial Intelligence (AI). NLP is playing a vital role in AI, which is used to bridge the gap between human and machine. AI is a platform for learning outcomes, in that NLP is used to solve problems like conversion of one human language to another human language. NLP spreads in all domains like Questions generation, Question Answering, Evaluation of descriptive answers and knowledge graph completion. The surge of modern NLP is accredited to the evolution of a simple model, perceptions. Including of perceptions was not just a second order with techniques altogether or boosting, but rather exponential if not asymptotic, with the advent of deep neural networks. The influence of NLP has made modernized advancements into real-world applications, i.e. chatbots conversion, real-time translations, hate speech, or forged news detection. Natural Language Processing is highly influenced on human lives, so it is working on many applications like Translator, Search Autocorrect and Autocomplete, Social Media Monitoring, Hiring and Recruitment Survey Analysis, Targeted Advertising ,Voice Assistants Grammar Checkers, Chatbots, End Notes ,Email Filtering, etc.. In this article, we shall start by exploring some machine learning algorithms to give solutions for NLP approaches. The different algorithms Bayesian Networks, Maximum Entropy, Linear Regression, Logistic Regression, Decision Tree, SVM, Naive Bayes, kNN, K-Means, Random Forest.

Keywords: NLP, AI, Machine Language Algorithms, Translator

Abstract: Criminology is a complex subject. There are various factors which affect rate of crime in a particular society. Few of the main aspects are population, unemployment and education. In this article we would explore the correlation of rate of violent crimes in areas where majority of the inhabitants are afro Americans with the aforesaid aspect. Following are the effects in brief of mentioned reasons influencing rate of crime. Unemployment is one of the multiple causes contributing higher rate of crimes in contemporary society. Relation of crime with unemployment is manifested well through the offensive conducted by the unemployed. At a time when there is a death of suitable jobs or opportunities with crime is undermine by the promise of expect rewards in the mind of an individual. Good education is essential for development of professional skill / abilities in individuals. Members of community with higher level of education can avail rewarding jobs resulting in higher gross capita income. Consequently, risk associated with crime outweighs lure of benefits. Apart from the above good education tunes psychological, moral and social upbringing of an individual and thereby contributes the most to make her a better person. A person with rewarding jobs and high moral value would most likely endeavor to avoid activities which is not ethical and/or legal in the eyes of law. Rapid population growth, if not properly managed can have negative impact on crime rate. This is especially evident in areas such as those inhibited by impoverished afro American population. Reason could be deteriorated standard of living as available resources become scarce. Unfavorable living and economic condition can be conducive environment for criminal activities.

Keywords: Multiple linear Regression, Cross Validation, Confusion Matrix

Abstract: The term FINTECH refers to the junction of finance and technology, as well as how they are employed to progress finance. Fintech encompasses a diverse range of industries, including education, banking, insurance technology, payments, lending, and more. Fintech also covers the digitization of assets and the use of cryptocurrency via blockchain technology. Blockchain is a ground-breaking technology that allows users to record transactions on a decentralised, distributed ledger without the use of a middleman. Cryptocurrency is a derivation of the blockchain revolution, which some refer to as "the trust machine." This paper is mainly focused on the application of block chain technology i.e., cryptocurrency that has an impact on financial sectors. This paper focused on secondary data as perceived by many researchers through the collective references with the help of several investigations conducted by the experts. This review article is a Pure research or Fundamental research in nature. The secondary data is collected from online database, journals, and e-books respectively.

Keywords: Digitization, Cryptocurrency, Blockchain Technology, Decentralised, Ledger

Abstract: Stress is a severe psychological disorder that has a significant impact on psychological and physiological behavior of academic fraternity. To evaluate the rate of educational stress among students and teachers, a dataset of academic fraternity is collected and examined. To discover an optimal set of characteristics for a bi-objective stress diagnosis problem, three different bird-based swarm Intelligence (SI) metaheuristic algorithms namely Crow search algorithm (CSA), Emperor penguin optimizer (EPO), and Harris hawk Optimization (HHO) has been explored. The performance of these methods in discovering optimal set of features required for stress diagnosis among academic fraternity has been explained.

Keywords: Cylinder block, V8 engine, design, analysis

Abstract: Crop identification and classification are the keystone of satisfactory agricultural development. Crop yield prediction has been a topic of interest for producers, consultants, and agricultural related organizations. Many Techniques are used for crop yield prediction, including supportive decisions on what crops to grow and what to do during the growing period of the crops. In this paper, we performed a Literature survey on Yield prediction with different machine learning algorithms for satellite images with Climatic Parameters, also we survey on Wheat yield prediction using different machine learning algorithm and advanced sensing Techniques, also we survey on how to perform Measurement and Calibration of Plant-Height.

Keywords: Crop identification, Crop Classification, Yield prediction, Machine Learning.

Abstract: The advancements in fifth-generation (5G) wireless networking would offer various possibilities for distributing higher speeds and reduced latency, resulting in increased remote execution capability, a larger range of users linking devices, as well as aiding with the setup of a virtual network. 5G allows for a new type of network to link essentially anyone and everything, including computers, gadgets, and devices. Smaller cell infrastructure and denser distribution of different types of base stations is driving the trend of the next wave of wireless networks in the age of 5G networks. In this paper, we have discussed the principle of 5G technology, potential benefits, and various obstacles that the technology would face in order to deliver an effective and reliable wireless network than its predecessors. The paper begins with a brief review about the 5G wireless networking system and further discussing different features, applications, requirements and privacy schemes in the related field. As a case study, we have also addressed the survey trends and recent advances in the 5G wireless networks, presenting the verdict and finally summarizing the challenges and future directions of the next generation of wireless networks.

Keywords: 5G wireless networking systems, 5G wireless privacy scheme, Beyond 5G, Challenges in 5G, Internet of Things, Security and privacy

Abstract: The Internet of Things (IoT) is a typical internet framework with limitless possibilities. Today there is an unparalleled increase of global population. The density population of these metropolitan areas, places a tremendous burdens on the environment, which needs to be Strategically and Smartly controlled, with the ability to control the urban demand by developing new and intelligent experiences to make it more convenient everyday. IoT has unlimited prospects to improve the quality of life through its implementations in diverse devices, households, and even in cities, thanks to Artificial Intelligence (AI) and Machine Learning (ML). In today's world, IoT is implemented in nearly all of the products we use in our daily lives, ranging from a toaster to large electrical appliances such as air purifiers/conditioners, refrigerators, and so on. But this is just the tip of iceberg, as IoT can be used almost everywhere to ensure a more productive, effective, and safer atmosphere for the sustenance of our lives while still making it more convenient. In this short paper, the present and future developments in smart cities and IoT are discussed. We also go over how smart cities and IoT interact, as well as some of the driving forces behind IoT and smart city expansion and development. Finally, we go through some of the IoT's flaws and how they may be solved in the context of smart cities.

Keywords: Internet of Things, Machine Learning, Artificial Intelligence, Smart City, Smart Farming, Automation

Abstract: Despite of many challenges, security stands first as a major challenge faced by cloud computing because of its open and distributed architecture. Therefore intruders get access due to its vulnerability and in turn they affect confidentiality, availability and integrity of cloud resources and offered services terribly. As the researchers and technologists long for an improvement in cloud computing security poses a major challenge due to its open and distributed architecture. So it easily falls a prey to intrusion affecting confidence, availability and integrity of cloud resources as well as offered services. Recently, IDS has become the most necessary compounds that are used in computer system security and compliance practices that save cloud environment from several kinds of threats and attacks. This research paper is presented in tune with the cloud architecture, projecting an overview of different intrusions in the cloud in defense of the challenges and essential characteristics of cloud based IDS (CIDS) and detection technique used by CIDS and their types too.

Keywords: Cloud Computing, Intrusion Detection System, Cloud Security, Signature; Anomaly ,IDS.

Abstract: Web conferencing or online meeting tools allow remote meeting and collaborative work in any company or institute. Poor Internet service how ever makes most Web conferencing solutions unreliable for some region and developing countries in general. This paper reviews the literature on improving the user experience with low bandwidth and unstable Internet conditions for Website conferencing. We have special concentration on audio/video stream optimization, which is the most affected feature of a any conferencing system. The ongoing research in this area can be grouped into multiple domains. First thing is research on rate adaptation schemes that aims to provide the Stream high-quality content to many recipients while making the most of available bandwidth. Second thing is research on compression which attempts to reduce the bandwidth requirement with acceptable content quality. The last research studies how to weak en the influence of transmission errors and problems over the content provided.

Abstract: The Internet is one of the main sources of information for millions of people. One can find information related to practically all matters on the internet. Moreover, if we want to retrieve information about some particular topic, we may find thousands of Web Pages related to that topic. But our main concern is to find relevant Web Pages from among that collection. So, in this paper, I have discussed how information is retrieved from the web and the efforts required for retrieving this information in terms of system and users’ efforts.

Keywords: Information retrieval, Page ranking, Evaluation of information retrieval system.

Abstract: A chatbot is a computer program that can communicate with human beings using Machine Learning in messaging platforms. Whenever a user inputs a query, it responds and it saves the input query as well as the response in its chat history which helps the chatbot with some kind of initial knowledge. As the number of responses is increased, the precision and the accuracy of the chatbot also get increased. Our project is focused on creating a chatbot that can be used by the college website. The chatbot is basically divided into two modules; The College Enquiry option on the chatbot contains all the responses related to the course details, admission related queries, faculty details, information about the college facilities and infrastructure, etc. The E-Learning option on our chatbot can respond to the questions related to different subjects of IT branch i.e. C, C++, HTML, CSS, Java-Script, JAVA, Advance JAVA and Android. It is essential because when students search for some syllabus related questions on any search engine it gives multiple answer or either tells them to redirect to another links to search for answer, thus it is effective and more accurate. The future work includes training our chatbot with more data about these subjects so that it doesn’t miss any queries of user.

Keywords: E-Learning, Machine learning, Databases, Chatbot, Machine learning algorithms, Natural Language Processing, Speech Recognition, Response, Query.

Abstract: Voting online requires the highest level of security as certain things/results relay upon it. An online voting platform should have features like tamper-proof functionality, scalable, reliable, real time - updation. Major of the security related issues can be solved using the latest technologies like blockchain which ensures the safe and secured storage of data using the strong cryptographic algorithms. Ethereum provides us virtual machine which provides the environment for creating a blockchain space and moderation upon it using the smart contracts. Our proposed system will implement all the required and desired functions necessary for online voting. As earlier mention the limitations of the existing voting becomes very important to overcome those problems to ensure a safe, fast and reliable voting process. Immune Ballot is platform created on the Ethereum network to overcome major problems mention above and promise to reform the outdated voting process.

Abstract: Covid-19(sars-cov-2) has had a major global impact on the daily lives of billions of people living around the world. Social distancing has proven to be an effective measure to hamper the spread of the disease. The system presented is for analyzing social distancing by calculating the distance between people in order to slow down the spread of the virus. This system utilizes input from video frames to figure out the distance between individuals to alleviate the effect of this pandemic. This is done by evaluating a video feed obtained by a surveillance camera. The video is calibrated into bird’s view and fed as an input to the YOLOv3 model which is an already trained object detection model. The YOLOv3 model is trained using the Common Object in Context (COCO). The proposed system was corroborated on a pre-filmed video. The results and outcomes obtained by the system show that evaluation of the distance between multiple individuals and determining if rules are violated or not. If the distance is less than the minimum threshold value, the individuals are represented by a red bounding box, if not then it is represented by a green bounding box. This system can be further developed to detect social distancing in real-time applications.

Keywords: social distancing, pedestrian detection, deep learning, convolutional neural network

Abstract: In this era of the internet, e-commerce is growing by leaps and bounds keeping the growth of brick-and-mortar businesses in the dust. In many cases, brick-and-mortar businesses are resorting to having a counterpart that is internet or e-commerce-driven. People in the developed world and a growing number of people in the developing world now use e-commerce websites daily to make their everyday purchases. Still, the proliferation of e-commerce in the under-developed world is not that great and there is a lot to desire for. This paper outlines different aspects of developing an e-commerce website and the optimum solution to the challenges involved in developing one. It consists of the planning process, which starts with determining the use case, domain modelling, and architectural pattern of the web application. The entire development process is primarily divided into two parts: front-end development and back-end development. The database design is also discussed with an emphasis on its relational connectivity. This no-nonsense method of developing an e-commerce website can be easily replicated and followed in developing e-commerce websites in developing and under-developed countries where computing resources are scarce and expensive because of their socio-economic condition.

Keywords: E-Commerce, brick, and mortar, website.

Abstract: As human beings, communication is the key to accurately expressing thoughts, ideas, and emotions. In detecting emotions in speech, signals play an important role in the integration of Human-computer interaction (HCI). EDS is difficult to perform among other components due to its modification. Much remarkable research has been done on the detection of emotions. In this paper, we present comprehensive comparison methods and experiments performed to use an emotionally charged system using speech. This paper introduces an assessment of emotional acquisition using in-depth learning and compares their approach based on topic studies. Anatomy performed by audio recordings from RAVDEES, SAVEE, and Toronto of heart-to-heart talk and song. After launch, green audio files including MFCC, Librosa, Mel spectrogram frequency were used. Emotional detection can be done by extracting elements from speech and training and assessment are required for a large number of speech details to make the system work. The aim is to utilize assistance in all areas of computer and technology making it compulsory to make current programs and methods that make EDS modern. The analysis amends a sensory website, layers, a library handout model designed for emotional acquisition of speech. We mainly focus on the continuity of data collection, feature extraction, and the effect of automatic sensory detection. Inter-modal perception computing systems are considered a uni-modal solution as it performs high filtering accuracy. Accuracy varies with the number of sensors received, the output feature, the classification method, and the stability of the website.

Keywords: Emotional Discovery; Convolution Neural Network; MFCC; RAVDEES; SAVEE; Etoronto; In-Depth Reading; Speech Records.

Abstract: Water is essential for the survival of life on Earth. Both natural and manmade factors contribute to water scarcity. The amount of freshwater on Earth has stayed constant over time, but the human population has exploded. As a result, the search for freshwater becomes more intense every day. For improved and more effective water usage planning, proper management and forecasting are essential. The main parameters for an Urban Water Management are water demand and population forecasting. Machine learning is one of the most well-known forecasting approaches. Machine learning is a data analytics technology that allows machines to learn without having to be fully programmed. Machine learning, unlike previous demand forecasting approaches that were not ideal for historical unstructured and semi-structured data, takes into consideration or has the capability of assessing such data.

Keywords: water demand, forecasting, machine learning

Abstract: Acquired immunodeficiency syndrome (AIDS) of humans is caused by two lentiviruses, human immunodeficiency viruses’ types 1 and 2 (HIV-1 and HIV-2). Here, we describe the origins and evolution of these viruses, and the circumstances that led to the AIDS pandemic. Both HIVs are the result of multiple cross-species transmissions of simian immunodeficiency viruses (SIVs) naturally infecting African primates. Most of these transfers resulted in viruses that spread in humans to only a limited extent. However, one transmission event, involving SIV cpz from chimpanzees in south-eastern Cameroon, gave rise to HIV-1 group M—the principal cause of the AIDS pandemic. We discuss how host restriction factors have shaped the emergence of new SIV zoonoses by imposing adaptive hurdles to cross-species transmission and/or secondary spread. We also show that AIDS has likely afflicted chimpanzees long before the emergence of HIV. Tracing the genetic changes that occurred as SIVs crossed from monkeys to apes and from apes to humans provides a new framework to examine the requirements of successful host switches and to gauge future zoonotic risk Chimpanzees were most likely infected with AIDS long before HIV was discovered. Tracing the genomic changes that happened as SIVs transferred from monkeys to apes and then from apes to humans gives a novel paradigm for investigating the criteria for successful host shifts and predicting future zoonotic risk.

Abstract: Air pollution results from both natural (e.g., fires, volcanoes, and wind-blown dust) and man-made sources. The particles and gases that comprise air pollution are known to cause adverse health effects in humans. Air pollution is one of the major environmental issues. High population density is a huge contributory factor of air pollution in cities and urbanized areas. Hazardous chemical compounds break out to the environment through a number of natural and/or anthropogenic sports and may cause destructive results on human fitness and the environment. Increased combustion of fossil fuels inside the remaining century is answerable for the revolutionary change inside the atmospheric composition. Air pollutants, such as carbon monoxide (CO), sulfur dioxide (SO(2)), nitrogen oxides (NOx), volatile organic compounds (VOCs), ozone (O(3)), heavy metals, and respirable particulate matter (PM2.5 and PM10), differ in their chemical composition, reaction properties, emission, time of disintegration and ability to diffuse in long or short distances. Air pollutants have both acute and chronic effects on human fitness, affecting some of special systems and organs. In addition, brief- and long-term exposures have additionally been connected with untimely mortality and decreased life expectancy. Recent aggressive scientific and technological developments all these focus on a global environmental issue considering air quality system, reveals the fact that India is facing severe health hazards. In recent reports, more than 10 cities in India are listed on top. The air quality index (AQI) inIndia launched in 2014 under Swachh Bharat Abhiyan monitors air pollution on 10 scales ranging from low (green) to moderate (yellow) to serious (red) through data analysis of various air contaminating matters like pm 2.5, O3, NO2, SO2, CO. The present paper develops an Internet of Things (IoT) that enabled air quality monitoring system mobile in nature analyzing real-time surrounding data measuring Carbon Monoxide, Smoke and PPM level. The device can degree nearby area air contamination and generate analyzed records primarily based on which it alerts the humans through a buzzer tool included into the gadget. The consumer-pleasant and smooth coping with of the device generation is such that it can be hooked up in houses.

Keywords: Air Pollution, MQ135 Sensor, IOT, Arduino Uno.

Abstract: This study aimed to develop an Android-Based Study Buddy Pairing Application that helps students find a study partner for collaborative studying and peer Tutoring. The researchers used Agile software development life cycle for the development of the application. It is a method that is commonly used in a particular approach to project management that is utilized in software development. It is an iterative work sequence whereas it means that the process for calculating a desired result is by means of a repeated cycle of operations. The evaluation instrument used was Android Development Standard That contains 4 major criteria: visual design and user interaction, functionality, compatibility, performance and stability and security. As a whole, the evaluation result of the Android-based application was found to be excellent in most of its features. The developed application is a good avenue to augment studying between the learner and the tutor. It is recommended that the developed application should add more features such as file and image attachment and a profanity/obscenity filter on chat activity and an effective verification for learner and tutor. The features and functionality of the application is highly recommended to students who need peer tutoring.

Keywords: Android Application, Buddy- pairing, Collaborative Learning, Study Groups.

Abstract: Road crime is most important issue not only for Indian Government but also for common people. Mostly, it is found that road crime happening are more frequent at certain specific locations i.e. black spot. The analysis of these black spot can help in identifying certain road crime factor that make a road crime to occur frequently in that locations. In this project we apply statistics analysis and Eclat algorithm on the Fatal Crime dataset as an attempt to address this problem. Association rule mining is one of the popular data mining techniques that identify the causes of crime of road crime. In this project, we first applied Eclat algorithm to group the crime locations into A level, B level, C level crime location. Eclat algorithm takes crime level count as a factor to cluster the locations. Then we will use association rule mining to iden-tify these locations. The rules show different factors associated with road crimes at different locations. For all this we will provide crime data that are issue from Nashik city Commissioner office. Safety driving suggestions will be maked based on crime data, association rules, classification model, and clusters obtained.

Abstract: Enhancements in computing and media sciences, along with the evolution of Web, has resulted in a growth in the number of picture database and compilations, such as diagnostic images, e - library, and art gallery, which hold thousands of pictures. Conventional image extraction approaches like Text Driven Image Extraction and Histogram Analysis may take a long time to acquire the required photos from such a large collection. It's critical to create an efficient picture extraction technique that could manage such massive numbers of data at one go. The basic goal is to create a reliable tool which efficiently creates, implements, and reacts to data. An approach to develop an efficient image retrieval application that helps users to submit a query to the application and to obtain the image from a huge dataset.

Abstract: On this mission we try to implement system getting to know technique to are expecting inventory expenses. Device studying is correctly carried out in forecasting inventory costs. The objective is to predict the inventory expenses so that it will make greater knowledgeable and accurate funding choices. We advise a stock rate prediction system that integrates mathematical functions, device mastering, and other external factors for the motive of attaining higher stock prediction accuracy and issuing worthwhile trades. There are kinds of shares. you can recognize of intraday trading through the normally used term "day trading." Interday traders hold securities positions from at least in the future to the following and frequently for several days to weeks or months. LSTMs are very effective in collection prediction troubles because they’re capable of store beyond facts. This is crucial in our case due to the fact the preceding charge of a inventory is important in predicting its destiny fee. while predicting the real rate of a inventory is an uphill climb, we will construct a version on the way to expect whether the fee will go up or down.

Abstract: -Today, all government authorities are fighting day and night against the spread of communicable diseases like the coronavirus. Therefore, the goal of the system is to focus on using the latest computer technologies to limit the spread of communicable diseases like the coronavirus by imposing a strict restriction on public sputum, using camera-based real-time surveillance systems, which are responsible for the maximum replication of the virus. To implement this system, the camera will capture the flow of images from public places and record the live activities of this area. This data will then be sent via the cloud and analyzed using the YOLOv5 model to detect public sputum. The results will be made available to local authorities using a web/mobile interface. Officials can then penalize the individual. Thus, this system will help public servants manage and monitor public sputum effectively.

Abstract: The Unimodal biometrics has many problems such as noisy data, intra-class variations, confined degrees of freedom, non uniformity, spoof attacks, uniqueness and diverseness, non invariant and spoofy attack. The use of single property works as exclusive source of information for authentication (e.g. fingerprint, face, voice, gait etc.) generally leads to high false acceptance rate (FAR) and false rejection rate (FRR), Failure to Enroll rate (FER). . In order to conquered the limitations provided by unimodal system there is need of system which can combine of two or more attributes types of biometrics systems known as multimodal biometric systems. These systems are more authentic and trustworthy due to the presence of multiple, self contained, individualistic biometrics attributes. The spoofing problem is solved easily because it is very difficult for deceiver to take-off multiple biometric traits. The advantages of multimodal biometric systems are that there are multiple sources of information. As multimodal biometric systems use more than one biometric trait so it provide more security and more reliable and provide maximum accuracy.

Abstract: Decentralized net is a people-powered form of web that makes the internet greater democratic as there is no web hosting company. This lookup appears into the more than a few structures provided by using protocols that adapt to the decentralized networks and their goal to make a contribution to the shift from the modern-day centralized network. There are advantages alongside the decentralized community that act as proof for the want to change. Initially, the net was once now not designed to be centralized. This paper analyses why there is a want to alternate lower back to a decentralized machine thru the evaluation of how the community protocols work. Through the evaluation of the underlying protocols, it is feasible to locate the motivation toward a free and impervious community that is now not managed or owned by means of tech giants. This paper investigates the motives at the back of the want for a decentralized network. Focus is additionally directed closer to the functions of the structure based totally on lookup and how the existing decentralized purposes and protocols have adopted the method and put it to use to fight the challenges confronted with the aid of the centralized system..

Abstract: The aim of Online Jewellery website is to make it easier for the customers to buy jewellery with different categories like silver, gold, diamond. It reduce the manual work of customer. You can easily buy products from home and if you want to cancel it then you can easily cancel it by following some simple steps. It manages all the information about the product, customer, shipment and order.

Abstract: The continuous progression of AI models for classification and Facial recognition has gained a lot of attention and importance these days and have immensely constituted in finding solutions for complex real-life issues. The Gender and Age Prediction is a Deep Learning application and falls under the area of Artificial Intelligence. Age and gender are considered as key attributes because they play a foundational role in social interactions. Estimating age and gender based on image(s) is considered as a crucial task in smart applications. The gender is expected to be classified into one of ‘MALE’ and ‘FEMALE’ however estimating age accurately using regression is considered as a monotonous job as even humans can’t accurately predict the age by looking intently at a person. However, still it can be determined whether a person is in their 20s or in their 30s. through an approach namely Age Prediction as grouping and classification task using Audience Dataset, it consists of images labelled with subsequent age groups [(0 – 2), (4– 6), (8 – 12), (15– 20), (25 – 32), (35 – 43), (45 – 53), (60 –100)] and gender labels ‘MALE’ and ‘FEMALE’. Convolution neural networks (CNN) are extensively being used for classification and facial recognition because of its exceptional efficiency in these tasks. “OpenCV” is an abbreviation for open-source computer vision. It's also a Machine Learning Library, capable of processing real-time image, video and supports the Deep Learning frameworks -Tensor Flow, Caffe, and PyTorch.

Keywords: Facial recognition, Convolution neural networks, Artificial Intelligence, Classification, Regression, OpenCV, Adience Dataset, Machine Learning Library, Tensor Flow, Caffe, and PyTorch.

Abstract: A struggle has emerged in relation to the sacredness of one’s private information and the importance of moving forward in a digital world of social media, smart devices, and Big Data – an era known as the Age of Context. The purpose of this paper is to make a clear case for concern regarding the seriousness of keeping data private while facilitating efforts to encourage and support emerging technologies. This investigative process included the pursuit of relevant articles and published works that provided a clear and relevant picture of the current state of affairs concerning Big Data and privacy. After a review of the literature, an analysis of data collection methods, a discovery of Big Data processes and purposes, and the identification of risks pertaining to the individual, the military, and the country, it was determined that significant concerns do exist pertaining to data collection, Big Data, and privacy. These concerns not only pertain to the individual, but with military effectiveness and national security.

Keywords: Big Data , Data Security, Data Privacy

Keywords: Animal Recognition, User Alert, Convolutional Neural Network, IOT, YOLO

Abstract: -- E-Voting is a form of voting in which the individuals are able to cast their votes online, through a web interface. Through the use of online voting, the voter navigates to the designated election site using a web browser on an ordinary PC. The individual then authenticates himself or herself before the system enables the voter to view the ballot displayed on the screen. The voter is then permitted to select their chosen candidate and then cast the votes which would then be sent to the election server for processing. In “E-Voting” a voter can use his\her voting right online without any difficulty. He\She has to fill a registration form to register himself\herself. All the entries is checked by the DATABASE which has already all information about the voter. If all the entries are correct then a USER ID and PASSWORD is given to the voter, by using that ID and PASSWORD he\she can use his\her vote. If conditions are wrong then that entry will be discarded. The project is designed with a modular approach and the number of modules is decided as per the requirements of the organization. The three modules are administrator module, nominee/candidate module and the general voter module. The administrator has total authority of the organization and maintains all the aspects. The user has the provision to view the list of all candidates and results as well as vote for the desired candidates.The voting system currently being used by the association is a paper based system, in which the voter simply picks up ballots sheets from electoral officials, tick off who they would like to vote for, and then cast their votes by merely handing over the ballot sheet back to electoral official. The electoral officials gather all the votes being cast into a ballot box. At the end of the elections, the electoral officials converge and count the votes cast for each candidate and determine the winner of each election category. The Nominee details will be updated by the admin for the post of board of director and manager. The candidate will submit their own details and the admin maintain all of background details of the particular nominee and uploaded their information in correct procedure. In order to, the user or voter can view the nominee details. The user after their registration only can logon for voting. The user will view nominee details with their image before they can vote. After knowing the nominee details the user can logon for voting. They should vote for board of director and the manager in the association. The count will taken for each voting. After voting the particular person/user cannot logon to vote again. Keyterms: Blockchain framework, E-Voting application, Internet of Things

Abstract: Designing infrastructures that give trustworthy third parties (such as end-hosts) control over routing is a promising research direction for achieving flexible and efficient communication. Even so, serious concerns remain over the deployment of such infrastructures, particularly the new security vulnerabilities they introduce. The flexible control plane of these infrastructures can be used to launch many types of powerful attacks with little effort. In this paper, we make several contributions towards studying security issues in forwarding structure (FIs). We present a general model for an FI, analyse potential security vulnerabilities, and present method to address these vulnerabilities. The main method that we introduce in this paper is to use the simple lightweight is cryptographic constraint. It is possible to keep a large class of attacks on end- hosts and bound the flooding attacks. Our mechanisms are general and apply to a variety of earlier proposals such as , Data Router, and Network Pointers. Key Words : Internet architecture, cover networks, security.

Abstract: As more people are expressing their views and opinions on various social websites there has been a surge of data generated by the users, these websites have people sharing their thoughts daily because of a short and simple form of expression. We can consider such type of data as a resource and performance sentiment analysis on data of various products and services to make better data-driven decisions. This paper highlights the use of sentiment analysis along with the type of data that is being analyzed, the complex process involved in analyzing the data, the different approaches that can be used, and an experimental observation using the Machine Learning approaches. Keyterms: Machine Learning, sentiment analysis, Naive Bayes Classifier.

Abstract: An investment is a procurement or object acquired with the hopes of earning money or appreciating in long term value. An expenditure, in financial perspective, is the acquisition of products that will not be devoured presently but will be utilized to build profits in the coming years. An investment is a various financial commodity acquired with the expectation that it will generate revenue or grow in value and be transferred at a better future point in time. The term investment focuses on the current dedication of finances with the expectation of a favorable percentage of return in the future. Today’s political investing options are quite diverse. To achieve their objectives, businesses rely heavily on seed capital. That was also the stage where entrepreneurs make meaningful investments that will be essential as the firm expands. There is a lack of effective study into the process of suggesting investments that are accurate and precise for the investors. For this purpose, a number of investment related works have been analyzed in this approach to achieve an effective and useful mechanism for investment related suggestion using deep learning which will be elaborated in the upcoming editions of this research.

Keywords: K Nearest Neighbors, Linear Regression, Artificial Neural Networks, and Fuzzy Classification.

Abstract: An investment is a procurement or object acquired with the hopes of earning money or appreciating in long term value. An expenditure, in financial perspective, is the acquisition of products that will not be devoured presently but will be utilized to build profits in the coming years. An investment is a various financial commodity acquired with the expectation that it will generate revenue or grow in value and be transferred at a better future point in time. The term investment focuses on the current dedication of finances with the expectation of a favorable percentage of return in the future. Today’s political investing options are quite diverse. To achieve their objectives, businesses rely heavily on seed capital. That was also the stage where entrepreneurs make meaningful investments that will be essential as the firm expands. There is a lack of effective study into the process of suggesting investments that are accurate and precise for the investors. For this purpose, a number of investment related works have been analyzed in this approach to achieve an effective and useful mechanism for investment related suggestion using deep learning which will be elaborated in the upcoming editions of this research.

Keywords: K Nearest Neighbors, Linear Regression, Artificial Neural Networks, and Fuzzy Classification.

Abstract: When ithe ibrain's iworking iproperly, iour icapacity ito ifocus iand iconcentrate iallows ius ito iaccomplish iincredible ithings. iDistractions iare ithe imost icommon icause iof iinattention, ialthough ithey iaren't ialways ias iobvious ias iyou imight ithink. Instead, iyou ican ifeel idisorganized ior i"fuzzy," ior iyou imight iblame iyourself ifor inot ibeing imore iin icommand. Focus iand iconcentration, ias iwell ias imemory iand iother icognitive iprocesses, ican ideteriorate ias iwe iage, ialthough ithis iis inot ialways ithe icase. iIn ireality, iseveral istudies iwith iolder iadults ishow ino ireduction iin idecision-making iabilities, iand istrategic ilearning i—the iability ito iunderstand isomething iin icertain iways i— ican iimprove iwith iage. iIn icomparison ito ithose iin itheir i50s, ipeople iin itheir i70s ican ibe i"more iconscientious iand ivigilant, iwithout ibecoming ihyper-vigilant." If iyou ihave itrouble ifocusing, iyou imay ibelieve ithat iyou ionly ineed ito itry iharder, ibut ithis imethod iis iunlikely ito ihelp. i Instead, iyou imay iimprove iyour ifocus iby ifocusing ion iimproving ithe iindividual ibrain iactivities ithat icontrol iconcentration iand iawareness. iYou ican ifeel isharper iand imore ifocused iby isetting iconditions ithat imake iit isimpler ito iconcentrate iand icomplete iyour iwork, iespecially iwhen iyou ihave ia ispecific iassignment ito ido. iConsider ihow imany iof ithese ielements iaffect iyour iability ito ifocus i– ifor ibetter ior iworse i— iand ihow imany iof ithem irelate ito iyou. iStarting iat iany iof ithese ipoints ican ihelp iyou iimprove iyour iattention iand iconcentration iin iall iareas iof iyour ilife. Concentration iand ifocus iare imuscles ithat ineed ito ibe iexercised iregularly. iAlthough isome istudents iare inaturally ibetter iat ithis ithan iothers, iall istudents ican iacquire itactics ito iassist ithem ito ienhance itheir iability ito iconcentrate. iAfter iall, ichildren ineed ito ibe iable ito ifocus iand iconcentrate ifor ilong iperiods ito isucceed iin ischool iand iextracurricular iactivities, inot ito imention iwhen ithey ienter ithe iworkforce.

Keywords: iAttention ispan, idistractions, isolutions, iconcentration, iGradient iBoosting iClassifier.

Abstract: The purpose of this thesis is to address design and development issues that have been identified in the platform game genre. The issue at hand stems from the fluctuating curve of interest in the platform-game genre that can be seen from the 1980s to the present day. The problem addressed in this thesis is that modern platform-game developers are prone to overlooking and/or deprioritizing important design and gameplay elements found in previous popular games in the genre. This thesis concludes with a comprehensive presentation of the Implementation categories, complete with complexity examples for each category and a complete game. The findings of this thesis should be useful in small-scale, independent, or academic game projects in terms of design, decision-making, prioritisation, and time management.

Keywords: game development, game design, platform games, software complexity, framework, analysis, prototype.

Abstract: Today Online services, application deployment, and infrastructure management all benefit from the cloud. The use of the internet and online services is fast increasing as a result of the COVID-19 epidemic. Most IT sectors face issues in storage, software licences, processing power, physical IT infrastructure, administration, and maintenance. Cloud computing enables IT professionals to develop and deploy web application services virtually from any location, allowing them to continue working on projects in a distributed environment. Cloud-based services are one of the most secure and accessible platforms for accelerating application deployment. Users are encouraged to choose a plan based on their needs and budget. This paper discusses Microsoft Azure's cloud-based application service deployment procedure, benefits, and plans.

Keywords: Microsoft Azure, Application Services, Cloud Services, Cloud Platform

Abstract: The science of getting computers to act without being explicitly programmed is known as machine learning. Machine learning, data mining, and statistical pattern identification are all covered in this article. It examines common machine learning algorithms like the decision tree algorithm, random forest algorithm, artificial neural network algorithm, SVM algorithm, Boosting and Bagging algorithm, and BP algorithm. The machine learning development environment you use could be just as important as the machine learning methods you employ to solve your predictive modelling problem.

Abstract: Counterfeit products have risen with the rising demand and inflating prices and also shortage of supply. According to the latest reports the counterfeit goods industry in the USA is worth more than 600 billion USD. And it is destined to increase at a whopping 4% per year. To prevent the trade of counterfeit products and to help reduce counterfeit goods we have developed a technology with the help of a blockchain network. Essentially, a blockchain is a digital transaction ledger that is maintained by a network of multiple computers that does not rely on a third party. Individual transaction data files (blocks) are managed by special software that allows the data to be transmitted, processed, stored, and represented in a human-readable form. Each block contains a header with a time-stamp, transaction data, and a link to the previous block in its original configuration. A hash gets generated for every block, based on its contents, and then becomes referred to in the heading of the subsequent block. As a result, any manipulation of a given block would result in a mismatch in the hashes of all subsequent blocks.

Abstract: In this Paper, the Automatic Fake Currency Recognition System is designed to detect the counterfeit paper currency to check whether it is fake or original. The existing counterfeit problem due to demonetization effects the banking system and also in other fields. A new approach of Convolution Neural Network towards identification of fake currency notes through their images is examined in this approach which is comparatively better than previous image processing techniques. This method is based on Deep Learning, which has seen tremendous success in image classification tasks in recent times. This technique can help both people and machine in identifying a fake currency note in real time through an image of the same. The Accuracy in the proposed system is evaluated using accuracy.

Abstract: An Occupational Health and Safety Management System is an industry’s threat management strategy for managing high risk and insecure activities. A management system is a dynamic process in which a set of classified components enable an organisation to attain a set of goals. An OHSMS is a framework used in many organizations. This framework helps in monitoring the safety of an organization from various threats and reduces the possibility of occurrence of any dangerous activities. Hence, it enhances the health and safety of the employees of an organization there by gradually increasing the organization’s performance. It occurs with a plan of action and is being controlled like other aspects of a business such as social, technical or administrative functions. An OHS management system provides us the facility to safe guard our workplace and helps us promote healthy and safer working environment. By applying and executing an OHSMS in an organization, it allows us to protect the workplace, follow legal requirements and enhances the performance. An OHSMS is an internationally recognized standard that falls under ISO 45001 Standard. This ISO 45001 standard clearly explains the prerequisites for organization’s competency and liability with respect to Occupational Health and Safety management. Health and safety are an issue that affects everyone in the workplace including employees, volunteers, contractors, vendors and visitors. Effective safety management will help the industry improve employee wellbeing, workplace ambience and operations. Therefore, there is always a need for a secure working place. The idea of an OHSMS is more important and prominent in the industries. Hence, this concept is more familiar among the organizations. An OHSMS provide a systematic way of managing health and safety risks, controlling hazardous incidents in the workplace with continual improvement.

Keywords: OHSMS, Framework, Risk Management Strategy, Organization, Health, Control, Incidents, Safe Workplace

Abstract: This research paper aims at exploiting efficient ways of tackling face spoofing problem. Face recognition is one of the most prevalent bio metric approaches used. This technology has expeditiously advanced in recent years, due to it being more in-line, user-friendly and easy to use than other methods. Liveness detection creates a secured system which helps in protecting the system against spoof attacks using non real or fake faces like photographs. The approach used by us in our work are classified according to the various procedures used for liveness detection which helps to understand the solutions developed for different spoof attack scenarios. The primary goal is to provide a well-developed and impenetrable face liveness detection approach.

Abstract: AGVs (Autonomous Guided Vehicles) or AVs (Autonomous Vehicles) are employed in a broad range of applications, including bomb disposal, underwater research, and industrial transportation. Many control and guiding solutions for AV research have been presented in the literature, ranging from entirely autonomous and intelligent systems to laser and radar guided systems and line followers. This work employs the Line follower or Direction lead to give a unique way for guiding and directing autonomous vehicles. An AV with a built-in GPS receiver may be effectively controlled by a central computer with the OSM powered control mechanism installed. Transportation automation in the industrial, commerce, and service sectors is a critical component of intralogistics optimization. AGVS has applications in every sphere of industry and commerce. Assembly lines, warehouses, order picking systems, and manufacturing plants are all good examples. The major application of AGVS and the sectors in which they are employed are examined using the AGVS-Statistic Europe, which was designed and is administered by the Department of planning and controlling of warehousing and transport systems (PSLT). The AGVS-current sector's trends and developments are recognised using this database. AGVS farmers are increasingly being forced to compete on a global scale. In the future, AGVS will become more important in the field of automation.

Keywords: Vehicles, Automation, Guidelines, Automatic control, Control systems, Transportation,

Abstract: The main objective of this project is to increase mobility and automation in the student information management system at the institution. In the previous version, all information had to be viewed on a website. At the same time when searching for any information, it is very difficult to access and it takes a lot of time to search for a particular website. Therefore, to overcome this problem the Cross-platform smartphone-based app can be used to make the process easier, safer, and less flawless. The most effective information will be gained through this program. All college related news will be accessible anywhere anytime just on a single click on your mobile device. This application allows access to all notices and college related news. Also, as soon as notice is published on the main portal all mobile devices will receive notification on their mobile devices. Notice notification helps to bridge the communication gap between college management, faculty and students. This feature will allow college management to convey important messages and information directly to students. This application also connects students across all years and branches through a student discussion forum feature where students can post queries and discuss on topics. Only college students can access this feature; they can share study resources and convey some information. This application also allows students to view their internal exam results and attendance. Attendance calculator helps students to predict their future attendance. Attendance section in the application provides graph and attendance percent breakdown which helps students to better analyze their attendance.

Abstract: Recruiting freshers when they are in final semesters through off-campus drive is a time- consuming process as it needs more recruiters to assess them. It requires more recruiters to filter the best candidate. The average time to assess a candidate is 10 to 20 minutes. Then it will take more time to shortlist the best candidates to the company. So with this paper, tried to automate this process of hiring using Natural Language Processing, Bidirectional Encoders, Speech Recognition and Semantic Matching and Supervised Similarity Measuring Techniques. The answers provided by the candidates can be recorded and pre-processed using speech recognition and Bidirectional Encoder Representations from Transformers (BERT). The recorded answers can be checked and matched through semantic sentence matching using the question and answer database designed by the recruiters. This web application would be the fastest and perfect way to hire candidates to the company.

Keywords: semantic similarity, cosine similarity, soft cosine similarity, word embedding, Euclidean distance, Cosine distance, BERT, Soft Cosine Similarity, TF-IDF Vectorizer.

Abstract: Humans are prone to skin cancer, which is one of the most common forms of cancer. The Cause of skin cancer is the uncontrollable mutation in DNA that could occur due to many reasons. An important factor in increasing the chance of success is identifying the cancer in the early stages. Now a days, computer aided diagnosis applications are used almost at every field. It is majorly used areas in health sector. Data from sick people is stored in computers to create biomedical datasets.. The goal of our Project is to obtain an effective and sustainable way for early diagnosis of skin cancer by classifying our dataset images as benign or malignant. The dataset used in the project consists of 660 test images along with 2437 training images.

Keywords: Skin Cancer Detection, Artificial Intelligence, Healthcare, Image processing, Convolutional Neural Networks, VGG16, InceptionV3, Deep Learning, MobileNetV2, EfficientNet.

Abstract: The fundamental issue in today's swarmed stopping office is clog and finding an empty parking spot. during this paper, a route strategy is suggested that minimizes the stopping time, in sight of gathered constant opening data of stopping spaces. within the proposed technique, a focal server within the stopping office gathers the information (utilizing IR sensors) and assessments the inhabitancies of each stopping openings. At that time, the server utilizes this data gathered as part of on going to figure the simplest reasonable stopping space for the client upon demand. this fashion is then sent to client's advanced mobile phone as reaction by the server which is able to then be shown on an android application. In vast occupied urban communities, to locate a void stopping space is extremely difficult. We are additionally uninformed of this stopping opening within the essential region. Along these lines during this paper, we propose a wise stopping framework. In this framework, we'll carry on a focal server, within which data about the enrolled stopping is put away. This framework proposes a safe and proficient stopping framework which is able to take an effort at sensor correspondence and secured remote system. The focal server will likewise sustain the include of the unfilled openings the stopping office and it'll demonstrate it to the client. As needs be, the client will choose appropriate stopping zone. see able of this, the evaluated most brief thanks to the chose stopping are figured and perceived to the driving force. Utilizing this framework, we are able to effortlessly find empty space for stopping and stopping holding up time is decreased efficiently. during this framework, we make sure of the difficulty of activity clog utilizing route technique. we provide a framework which will without much of a stretch find empty space for stopping. We plan a focal server that sustain data about the enlisted stopping zones. It additionally continues the tally of accessible space within the stopping ability and transmit it to the client. therefore, the client can without much of a stretch take choice visible of the closest stopping accessible. during this manner by utilizing route method, the client can get the foremost limited thanks to the chose stopping zone to stay aloof from congestion. Therefore the stopping holding up time is decreased effectively.

Keywords: RFID, Infrared sensor, ADC, AVM, SDK, microcontroller.

Abstract: The purpose of the project entitled as "Hospital Management System '' is to computerize the Front Office Management of Hospital to develop software which is user friendly, simple, fast, and cost effective. It deals with the collection of patient's information like add patient, update patient, delete patient, search patient, view patient diagnosis, etc. Traditionally, it was done manually. The main function of the system is register and store patient details and doctor details and retrieve these details as and when required, and also to manipulate these details meaningfully The Hospital Management System can be entered using a username and password. It is accessible by an Admin, Doctor & Receptionist. Only they can add data into the database. The data can be retrieved easily. The data is well protected for personal use and makes the data processing very fast. The Government of India has still aimed at providing medical facilities by establishing hospitals. The basic working of various hospitals in India is still on paper as compared to hospitals in European countries where computers have been put in to assist the hospital personnel in their work. The concept of automation of the administration and management of hospitals is now being implemented in India also, with large hospitals like APOLLO and AIIMS in Delhi, ESCORTS in Chennai, having automated their existing system. Computers are not only used to increase the efficiency in all fields ranging from fixing the appointment with the Doctor to keeping the record of the Patient.

Keywords: Computerize, Patient,Doctor

Abstract: This project is a demonstration of an eco-friendly methodology for the implementation of solar powered thermoelectric refrigeration system. Solar energy is the most abundant and renewable source of energy in environment, and hence it is used in our project. In conventional refrigerators, moving parts or rotating parts like compressor, expansion valve, coolants etc. are involved which leads to some vibrations and noise. Even coolants are not eco-friendly and much more costly. But in thermoelectric refrigeration system, these mechanical parts and coolants get eliminated and a thermoelectric module is used instead. Still there are many rural areas where people have to deal with electricity problems, this module will be very helpful to them as it runs on solar energy. Food items and other different required things can be stored in it. Thermoelectric module consists of peltier plates and heat sink module which will be placed on each side of the peltier device. We are using microcontroller for this project to detect the temperature and display it to the user.

Keywords: Microcontroller, Peltier, Refrigerator, Sensors etc.

Abstract: The technology is designed to keep track of cars entering and exiting NH and city roadways. The acquired picture will be processed using the OCR (optical character recognition) technique for automated number plate recognition. The car number is entered into a database. In the event of a centralized receiver, all of the entrance records are stored, and it will check for the existence of a stolen vehicle entering the NH highways, which will be detected and the vehicle picture and information will be captured and given to an authorized person through IMAP (Internet Message Access Protocol). The number is identified using the OCR technology. In addition, the system will check to see whether the entered car information is already in the database and will retrieve it.

Keywords: object detection, image segmentation, vehicle license plate detection, Extraction Of Numbers from license plate

Abstract: Today's enterprise networks are distributed to different geographical locations and applications are more centrally located, information represents the most important asset. With the growing number of data communication services, channels and available software applications, data are processed in large quantities and in a more efficient manner. This technological enhancement offers new flexible opportunities also measure security threats poses in the networks. These threats can external or Internal, external threats divided as hacking, virus attack, Trojans, worms etc. There are thousands and thousands of different viruses these days which improve every day. Although the wild spread of new and strong viruses, it still infects and spread only with user's permission. This research paper highlights the phases of computer virus, computer virus, history of worst computer attack, type of computer virus with effect on computer & few examples of virus on their types, working of computer virus, and problem occur due to virus in computers.

Keywords: Computer virus, types of virus, infected, antiviruses, security, security threats, hacking.

Abstract: Artificial intelligence (AI) and machine learning (ML) have the potential to significantly improve particle accelerator operations, with applications in diagnostics, control, and modelling. Experimentally testing AI/ML methods before deployment to user facilities remains a challenge. The capacity to swiftly generalise and adapt these algorithms to different operational configurations inside or between facilities remains a difficulty, requiring a combination of model-independent adaptive feedback and classic machine learning technologies. These techniques can also be used to detect, classify, and avoid operational abnormalities that can result in accelerator damage or excessive beam loss during atypical operations. Broadening AI/ML approaches for early identification of a wide variety of accelerator component or subsystem problems is an opportunity. The optimization of a large number of connected accelerators is required in modern accelerator architecture.

Abstract: With the expansion of the Internet and technology over the past decade, Elearning has grown exponentially day by day. Online examination is an integral and vital component of E-learning. Face recognition is widely viewed a an alternative means of authentication to replace traditional password methods in different applications for access control. Despite significant improvements, this form of authentication remains plagued by several vulnerabilities ranging from the use of printed photographs, 3D masks, and video replay attacks.In face recognition systems, replay attacks where a pre-recorded video of the user is played and printed photograph is placed in front of the camera are the two most common ways to do the fraud while attending the examination.So there is a need for the robust face liveness detection method that can be used in detecting spoof attacks for differentiation between legitimate and illegitimate users using machine learning techniques. Using the observation that different materials reflect light differently, we propose a system that uses light reflection getting from the photo while recording a video or taking an image of examinee during an examination.

Keywords: 1. Face Fraud Detection 2. Online Examination 3. Face Recognition 4. Liveness Detection Light Reflection 6. Biometric Authentication 7. Machine Learning 8. Haar Cascade classifier, 9. Support Vector Machine

Abstract: Maintaining the quality of the water quality is one of the important aspects that play a substantial effect on the aquaculture industry especially in the tilapia industry. The quality of the water needs to be continuously monitored as any deviation from the allowed critical parameters such as water temperature and potential of hydrogen (pH) can cause unwanted scenarios such as disease, stress, higher mortality rate and profit loss. Currently, the monitoring process adopted by most fish breeders is done manually by using a portable sensor. This approach is found to be very tedious, ineffective use of manpower and time consuming particularly for the large-scale aquaculture industry. Hence, this research focuses on developing a simple, low-cost automated water quality Aquaponics is a system which combines aquaculture and hydroponics the grows fish and plant together in one system. The fish excreta are rich in Ammonia, which is then biologically converted to Nitrates by good nitrifying bacteria. The nitrate-rich water is then supplied directly to the roots of the plants. Plants take up this nitrate as nutrients. Various sensors are calibrated for different measurements to provide accurate and reliable readings of land temperature, pH level, water level and humidity. Now lot of people are coming forward towards agriculture and hydroponics is a better method through which is less capital investment and huge production can be made possible. The fishery department is keen about the development of good projects by providing proper technical assistance and awareness to the farmers. So, in such a scenario improvising the current technology of water quality management through an automated window could soon contribute to a better production. Monitoring system for the industry via LABVIEW software.

Keywords: Aquaponics, Control, Monitoring, Automation, IoT, LABVIEW, Sensor, Pump, Motor, Farming

Abstract: E-district portal is an initiative to manage all district services and provide them to people efficiently. The utilization of the health care services system is not in the expected range among district people. The information about availability of public health services is not well known. This study explored how district-level health services systems are not being used by people because the information does not reach them conveniently. To reduce the search time of people on the internet, a website is made where all information regarding health centres and services is made available for the district people. Strengthening district-level management can be an important lever for improving key public health outcomes. In this study, we will acquire knowledge and skills in health system management, administration and reachability, while providing everything on a single website. We will provide information regarding availability of vaccines at various district covid vaccination centres, real time. Index Terms E-District services, covid, vaccination, digitisation, e-governance

Abstract: Electroencephalography (EEG) has been a staple method for identifying certain health conditions in patients since its discovery. Due to the many different types of classifiers available to use, the analysis methods are also equally numerous. In this review, we will be examining specifically machine learning methods that have been developed for EEG analysis with bioengineering applications. From this information, we are able to determine the overall effectiveness of each machine learning method as well as the key characteristics. We have found that all the primary methods used in machine learning have been applied in some form in EEG classification. This ranges from Naive-Bayes to Decision Tree/Random Forest, to Support Vector Machine (SVM). Supervised learning methods are on average of higher accuracy than their unsupervised counterparts. This includes SVM and KNN. While each of the methods individually is limited in their accuracy in their respective applications, there is hope that the combination of methods when implemented properly has a higher overall classification accuracy.

Keywords: EEG Analysis, EEG Signal ,SVM.

Abstract: Plagiarism is when someone steals someone else's idea or work and passes it off as their own. Plagiarism has been classified as a moral rights infringement in a number of countries. Plagiarism has become increasingly common in today's environment of changing technology and ever-increasing Internet usage. It is often observed in many educational areas such as research papers, blogs, articles, assignments, etc. This study focuses primarily on plagiarism, which is prevalent in schools and colleges. Many students can be found to have copied assignments from their classmates. A system can be developed for the convenience of teachers that could check the amount of plagiarism in students’ assignments. This system could be mentioned as an improvement from the old manual way as it eliminates the tedious work with increased speed and efficiency. Keyword: plagiarism, cosine similarity, Data mining, Hash tag, Stop word, Cleaning, stemming.

Abstract: Annually, the field harvest damaged by the wild animals is in sharp increase in India. It sometime poses hazards to humans and animals. Since then, more and more wild animals are causing damage to crops and farmland so that humans cannot tolerate it. Therefore, they require an vital and appropriate solution to overcome this situation. The goal of this research article is to recognize animals before they are introduced in cultivation areas and implement appropriate real-time warning mechanisms. The presence of the animal will be sent to the farmer through application with an audible sound. In this study, two Convolutional Neural Networks (CNN) classification models have been developed using the machine learning YOLO algorithm as a pretrained model to detect elephants, wild boars. The two models have been merged and run on, which referred as the system processing unit for this, takes animal images, and predicts them. The findings of this research indicate that the accuracy rate of the classification model is 86 percentage. This system dramatically reduces human animal conflicts between human animals in crop fields by automatically setting up alert mechanism depending on the prediction.

Keywords: Animal Recognition, User Alert, Convolutional Neural Network, IOT, YOLO

Abstract: In this research, we present an android app for maintaining Logbook for storing daily record of professors at department level. The proposed approach can be used to maintain the record of topics which the faculty covered and total number of lecture taken by professor on daily basis. Log book maintenance registers and other papers containing information of the department and college work are included in college records.. To maintain such record on daily basis we requires registers, so to overcome this issue we proposed a app based on log book maintenance for college at department level. This will keep all record of the number of students present at respective lecture of respective faculty and the topic which the respective faculty have taken lecture with date, All records will be stored in database. This will be an online app for the maintenance of log book for faculty members which will reduce there burden of maintaining logbook in registers manually. A teacher's mobile phone can accompany him or her wherever he or she goes, including inside the classroom, allowing him or her to efficiently supervise a class. Mobile phones can now be used to improve student organisation, speed cooperation, and maximise technology portability. Recording, searching, reading, and updating a student's essential academic information will be faster, more convenient, and only a click away with the use of mobile phones.

Keywords: Log book maintenance, records, department, database, technology

Abstract: The issue of design and security is very predominant in any financial and business organization, especially such organization as a bank. Therefore, we intend to aid in security of the bank by bringing in an Artificial intelligence system that involves an individual to get an access to some items using face and voice recognition security system. This AI system is not just a normal password lock system that require a user to insert password and gain access to some items, it is a system that has an administrative authentication. In addition, with this kind of security authentication system we intend to implement, a highly secured AI feature, which enables the user with assured and highly secured transactions using their personal frame.

Keywords: Haar-Casacade algorithm, Machine learning, Face Detection, Voice Verification

Keywords: Social Network, Link Prediction, Machine learning, Performance metrics, Supervised learning, Twitch

Abstract: In the past several years, face detection has been classified as one of the most engaging field in research department. The frontal human faces are detected using the Face Detection Algorithms. Face detection is used in many applications such as face tracking, face analysis, and face recognition. The term Face Recognition and detection encompasses a extensive area of research and innovation through the image analysis and algorithm-based understanding, also known as computer vision. Voice assistants helps you perform task quickly and in real time. The humans passes voice command to the system and thus the system executes the command.

Keywords: Python, Face Detection, Haar cascades classifier, OpenCV, Google , Text to Speech(GTTS), VS code ,Arduino UNO.

Abstract: Alzheimer's disease (AD) is a progressive, irreversible brain illness that affects a person's thinking and causes the brain to shrink, eventually leading to death. It's required for the treatment of early stages of Alzheimer's disease in order to prevent further damage. Machine learning algorithms using various optimization and probabilistic methodologies can be used to make this diagnosis. Because no single non-amyloid protein has been proved to consistently diagnose Alzheimer's disease, using machine learning (ML) techniques to determine optimal combinations of non-amyloid proteins is a potential approach. As a result, our strategy is mostly dependent on machine learning in order to separate persons with normal brain ageing from those who are likely to develop Alzheimer's disease.

Abstract: Traffic congestion is a common phenomenon in most of the metropolitan cities of India. Because of heavy traffic people often lose their valuable time. One of the prime reasons for traffic congestion is parking on roadside, so a need arises to develop a parking system so that it can reduce the traffic condition in near future. Our project focuses on smart parking control application which will help you to find out a parking area in nearby your location. It has a server end to add parking spots and a customer end to book the parking spots.

Abstract: We use some verbal exchange manner to deliver rubdown digitally. digital gear allow two or extra persons to coordinate with every every other. This communication may be textual, visual, audio, and written. clever devices inclusive of cellular phone are the principal resources for communication in these days. in depth conversation via SMSs is causing spamming as well. unwanted textual content messages outline as a junk facts which we received inside the gadgets. maximum of the agencies sell their products or services by using sending junk mail texts which might be unwelcomed. In fashionable, most of the time unsolicited mail emails extra in numbers then actual messages. in this paper, we have used text class techniques to define SMS and junk mail filtering in short view, which segregate the messages consequently. in this paper, we follow a few classification techniques together with “device gaining knowledge of algorithms” to pick out what number of SMS are unsolicited mail or no longer. for that reason, we compared distinctive classified techniques on dataset series on which work completed through the usage of the Mahout tool. we were given a hundred% results from Random forest and random tree.

Abstract: Automated Teller Machines also known as ATM's are widely used nowadays by each and everyone. There is an urgent need for improving security in banking region. Due to tremendous increase in the number of criminals and their activities, the ATM has become insecure. ATM systems today use no more than an access card and PIN for identity verification. The recent progress in biometric identification techniques, including finger printing, retina scanning, and facial recognition has made a great effort to rescue the unsafe situation at the ATM. This project proposes an automatic teller machine security model that would combine a physical access card and electronic facial recognition using Deep Convolutional Neural Network. If this technology becomes widely used, faces would be protected as well as their accounts. Face Verification Link will be generated and sent to user to verify the identity of unauthorized user through some dedicated artificial intelligent agents, for remote certification. However, it obvious that man’s biometric features cannot be replicated, this proposal will go a long way to solve the problem of Account safety making it possible for the actual account owner alone have access to his accounts Keyword: Deep learning, biometric techniques

Abstract: The Internet of Things (IoT) technology has revolutionized every aspect of the average person's life by making everything smart and intelligent. The Internet of Things (IoT) is a network of things that self-configures. Intelligent Smart Farming IoT-based devices are changing the face of agriculture production by not only improving it but also making it more cost-effective and reducing waste. The goal of this project is to propose an IoT-based Smart Farming System that will assist farmers in obtaining Live Data (Temperature, Soil Moisture) for efficient environment monitoring, allowing them to increase their overall yield and product quality. The loT-based Smart Farming System proposed in this paper is built with Arduino Technology, various sensors, and a WiFi module, and generates a live data feed that can be obtained online from Thingsspeak.com. The product proposed in this paper employs an ESP32 Node MCU, a breadboard, a DHT11 Temperature, and Humidity Sensor, a Soil Moisture Sensor, jumper wires, LEDs, and a live data feed that can be monitored using a serial monitor and the Blynk mobile. This will enable farmers to manage their crops in the new farming era.

Keywords: IoT, Smart farming Systems, Moisture, Automated water pump, IoT in agriculture.

Abstract: Online Agriculture Management System is the web application which will help farmers by providing different different kinds agricultural related information and agricultural services in the website. This website will help farmers by providing them a large online market to sell their product. Customer can send a purchase request and they can purchase products through online website. Even farmers can hire working man and they can be updated with the new agricultural developments with articles and blogs module. Admin can post latest updates about agriculture and he can sell agriculture products in the website. Workers can upload their resume and they can view work schedules and after the login they can choose technology and services to the farmers, sellers and farm laborers help them to expand their business and connect them with a wider market. To provide a helping hand to the farmers and farm laborers are improving their lives through the medium of technology Hence the Agricultural sector in the Indian economy is getting better.

Keywords: B2B shop, C2C Shop, Product Based Site, Agricultural Development

Abstract: First, take a look at a traditional voting system. Large space and manpower are required to set up voting booths in multiple areas around a city or village. High security has to be maintained on the date of an election. Voters have to visit the voting booth and need to stand in a long queue. Again, manpower is required for volunteering and assistance of voters at the place of voting. The Voting process is done on a manual voting machine. Vote counting is done with the manual process. Then there is a gap of a few days for results to be displayed. So if we see, here in a traditional voting system, we need a lot of manpower, energy, and time to conduct this process. Now to overcome the above-mentioned problems, we are going to develop an application called Online Voting System. Like Money transfer, Shopping, Booking, Teaching, Data sharing, Admissions, Job search, etc. So with the easy access and use of the internet, we are going to take this existing voting system to an advanced level. We are going to develop an online platform with high security so that the same process could be done easily without the waste of time, afford, and energy. The main responsibility of this project is to give simple and easy access to the election process for both the election committee as well as participants.

Keywords: Voter, Platform, Web application, Online, Election, Voting, Results.

Abstract: Expense tracker is an android based application. This application allows the user to maintain a online diary. Expense tracker application will keep a track of Expenses of a user on a day to-day basis. It keeps a record of your expenses and also will give you a category wise distribution of your expenses. With the help of this application user can track their daily/weekly/monthly expenses. This application will also have a feature which will help you stay on budget by sending alerts. This app will generate report at the end of month to show Expense via a graphical representation. We also have added a special feature which will distribute expenses in different categories suitable for the user. An expense history will also be provided in application.

Keywords: Track, Expense, Income, Report, Payment

Abstract: Data mining is a technique for extracting meaningful patterns from massive amounts of information. The paper examines a few data mining approaches, algorithms, and some of the corporations that have successfully implemented data mining technologies to better their businesses.

Keywords: Data mining Techniques; Data mining algorithms; Data mining applications.

Abstract: Photonic technologies have changed the world of communications in the form of fiber optics, integrated optics, electro-optical components, and micro-photonics. They offer some compelling advantages compared with their traditional RF counterparts when considered for use in space applications. Thus, research and development of photonics technologies for space applications in areas of communications, sensing, and signal processing has been a major theme for several years. The use of photonic technologies for space applications has risen the problem related to the ability of optoelectronic and optic components to withstand the space environment as all optoelectronic and optic components come from terrestrial applications. Thus, the development of photonic technologies for space applications has made the selection and acceptance test criteria of all optoelectronic and optic components that are part of the photonic system imperative. The paper presents a summary of the experience of Alter Technology Group on the mechanical, thermal, radiation, and endurance testing of several photonics technologies. In addition, the paper describes an assessment related to the reliability of these parts to be used in space applications together with the critical requirements to be considered for associated environmental testing.

Abstract: In this project we attempt to implement a machine learning approach to predict stock prices. Forecasting of stock prices can be done effectively using Machine Learning. The main objective is to predict the stock prices such that we can make more informed and accurate investment decisions. Our proposed stock price prediction system integrates mathematical functions, machine learning, and other external factors. This can be used for the purpose of achieving better stock prediction accuracy and issuing profitable trades. There are two types of stocks. You may know of intraday trading by the commonly used term "day trading." Intraday traders hold securities positions from at least one day to the next and often for several days to weeks or months. In order to store past information in the sequence prediction problems, LSTMs are more powerful. This is most important in our project because the previous price of a stock is crucial in predicting its future price. While predicting the actual price of a stock, we can build a model that will predict whether the price will go up or down.

Keywords: Stock Prediction, Trading, Machine Learning, Stock Price.

Abstract: Content-based picture recovery is an interaction structure that applies PC vision strategies for looking and overseeing huge picture assortments all the more productively. With the development of huge computerized picture assortments set off by quick advances in electronic capacity limit and figuring power, there is a developing requirement for gadgets and PC frameworks to help productive perusing, looking, and recovery for picture assortments. Focusing on continuous types of progress and sound headways, the security of mechanized data has become a fundamental issue. To beat the shortcomings of energy security shows, researchers will in everyday focus their undertakings on changing existing shows. Over the latest several numerous years, nonetheless, a couple of proposed encryption computations have been shown dubious, provoking huge risks against critical data. Using the most legitimate encryption estimation is a fundamental technique for protection from such attacks, but which computation is by and large appropriate in a particular situation will in like manner be dependent upon what sort of data is being gotten. Regardless, testing potential cryptosystems independently to find the best option can occupy a huge dealing with time. For a fast and exact decision of fitting encryption estimations. We propose a RDH with triple DES block-based change calculation to accomplish the reason for picture content security. All the more significantly, under the proposed picture content assurance structure, picture recovery and picture convolution can likewise be performed straightforwardly on the substance safeguarded pictures. As an outcome, not just secure picture stockpiling and correspondence are achieved, yet in addition the calculation endeavors can be completely circulated, in this manner making it an ideal counterpart for these days famous distributed computing innovation. Security investigations are directed to demonstrate that the proposed picture encryption conspire offers specific level of safety in both measurable and computational perspectives. Albeit a higher information secrecy might be reached by taking on customary cryptographic encryption calculations, we accept it very well may be acknowledged by common clients with general picture stockpiling needs, since additional functionalities, for example content-based picture recovery and picture convolution, are given. Test results likewise exhibit the fair presentation of the proposed encryption space picture recovery and convolution with satisfactory capacity upward. All things considered, this study presents a basic and helpful method of disconnected picture look on personal computers and gives a venturing stone to future substance based picture recovery frameworks worked for comparable purposes.

Abstract: Information mining of open-source knowledge on the Web has become an undeniably significant point over a wide scope of spaces, for example, business, law requirement, military, and online protection. Text mining endeavours use characteristic language handling to change unstructured web content into organized structures that can drive different machine learning applications and information ordering administrations. For instance, applications or text mining in online protection have created a scope of danger insight benefits that serve the IT business. In any case, a less contemplated issue is that of computerizing the recognizable proof of semantic irregularities among different content information sources. In this paper, we present Secure connect, another irregularity checking framework for recognizing semantic irregularities inside the network safety space. In particular, we inspect the issue of recognizing specialized irregularities that emerge in the utilitarian portrayals of open-source malware danger detailing data. Our assessment, utilizing a huge number of relations determined from online malware danger reports, shows the capacity of secure connect to recognize the presence of irregularities.

Keywords: secure connect, Framework, semantic irregularities, malware danger, text mining, tweet analysis.

Abstract: Now a day's cloud computing is used in many areas like industry, military colleges, healthcare etc. to storing huge amount of data. We can retrieve data from cloud on request of user. To store data on cloud we have to face many issues. To provide the solution to these issues there are n number of ways. In Cloud Users can remotely store their data to cloud & realize the data sharing with other. In Some Common cloud storage system such as the electronic health records system, the cloud file might contain some sensitive information. Encrypting the whole shared file can realize the sensitive information hiding, but will make this shared file unable to be used by others. In cloud computing more Sensitive information hiding in cloud. This is very big problem that remote data integrity auditing scheme that realizes data sharing with sensitive information hiding in this cloud. In our System, our scheme makes the file stored in the cloud able to be shared and used by others on the condition that the sensitive information is hidden, while the remote data integrity auditing is still able to be efficiently executed. Meanwhile, the proposed scheme is based on identity-based cryptography, which simplifies the complicated certificate management.

Keywords: Cloud service provider (CSP), cloud server (CS), Encryption, Decryption, Delay, Integrity.

Abstract: Plant disease identification by visual way is increasingly difficult and simultaneously less accurate. However, in the event that disease detection technique is used, it will take less time and processing power and proves to be progressively exact. Some broad maladies in plants appears dark coloured, yellow spots, and some are infectious, viral and bacterial diseases. Image processing is being used for estimation of infected area. Image segmentation is the process of collecting images into different parts. Now a day there are various strategies used for preforming image segmentation, stretching out from the fundamental thresh holding procedure to forefront concealing picture division systems. Computers does not any special technique for intelligent objects recognition, so a great number of techniques have been developed. The segmentation procedure relies upon various features found in the image. This might be shading data, limits or fragment of an image Plant disease identification by visual way is increasingly difficult and simultaneously less accurate. However in the event that disease detection technique is used, it will take less time and processing power and proves to be progressively exact. Some broad maladies in plants appears dark coloured, yellow spots, and some are infectious, viral and bacterial diseases. Image processing is being used for estimation of infected area. Image segmentation is the process of collecting images into different parts. Now a day there are various strategies used for preforming image segmentation, stretching out from the fundamental thresh holding procedure to forefront concealing picture division systems. Computers does not any special technique for intelligent objects recognition, so a great number of techniques have been developed. The segmentation procedure relies upon various features found in the image. This might be shading data, limits or fragment of an image.

Keywords: Multi disease detection, pre-processing, classifier algorithm, feature extraction, Convolutional neural network (CNN) etc.

Abstract: With the fast progression of digital data exchange in electronic way, information security is becoming much more important in data storage and transmission. Cryptography has come up as a solution which plays a vital role in information security system against malicious attacks. This security mechanism uses some algorithms to scramble data into unreadable text which can be only being decoded or decrypted by party those possesses the associated key. These algorithms consume a significant amount of computing resources such as CPU time, memory and computation time. In this paper two most widely used symmetric encryption techniques i.e. data encryption standard (DES) and advanced encryption standard (AES) have been implemented. After the implementation, these techniques are compared on some points. These points are avalanche effect due to one bit variation in plaintext keeping the key constant, avalanche effect due to one bit variation in key keeping the plaintext constant, memory required for implementation and simulation time required for encryption.

Keywords: Computer Communication- Networks, Distributed Systems, Social Network, Rating

Abstract: Water is crucial to the existence of life on Earth. The causes of dehydration are natural and phylogenesis. Within the world, the number of fresh remains constant for an amount of your time, however the population has already reached it. Therefore, aim for something fresh that's stronger day by day. correct management and prognosis is needed for effective and economical water use systems. Water demand and statement at the mainstays of urban water management. Machine learning is one among the foremost well‐known strategies of prediction. Machine learning could be an information analysis methodology that provides a machine the flexibility to browse while not being fully organized. In contrast to ancient strategies of predicting needs that were incorrectly structured and poorly structured historical information, machine learning appears or has the ability to investigate that information. This technique predicts the annual water demand for the succeeding year employing a statistical algorithmic program and water demand for industries, agriculture, domestic and public gardens. This multi‐method prediction suggests potential for extension to advanced probabilistic prediction issues in alternative fields.

Keywords: water demand, statement, multivariate analysis, trade applications, environmental management, machine learning.

Abstract: A FoodHub website shows restaurants based on their locations. Users can view restaurant listings based on where they are located. Registering a restaurant on this website and editing its items as necessary is easy. Users get the recommendation of their choice and get a discount which is very profitable and creates a hook for the customers to continuously use the website. Website interface is very user friendly through which the customer can easily order the food items of his/her choice. This paper will show the increase in demand for food ordering apps and our FoodHub website insight. How we made our website work and added new features to make the customer experience better.

Abstract: Internet of Things provides the ability to transfer data over a network without requiring human-to-human or human-to-computer interaction. Smart mirror is one of the most important applications of IoT. This mirror provides common information most people check their smart phones or tablets. This allows the users to think their plan for the day while getting ready in the morning or night. Raspberry Pi4 controlled mirror application software designed and developed by means of software to display the data like news, see a traffic report, weather forecast for the day, and your day’s schedule. We are utilizing our voice services to make our gadget intelligent. As the world get developed day by the day technology get improved as a result of this Smart Mirror can proved the best alternative for the Normal mirror .it will replace our mirror with the Smart Mirror which will help the consumers to live a easy and comfortable life without any hurdles. We have proposed the system in such way that the feels comfortable while using the system and anyone can use the system easily. Smart Mirror is the mirror which is a combination of the 2-way mirror, Display, Raspberry pi, PIR sensor, Microphone, Speaker etc., project generally help the people to use the Mirror in Smart way for the better life. We have used the Alexa for the voice Service. Python and Javascript (Node.js) programming tools are used for programming of the Project. We have connected to the two mirrors with the display and connect it with the raspberry pi kit which is further connected with the PIR sensors and microphone and speaker.as Bluetooth module is already present in the raspberry pi kit sso there is no need to connect the one. It is very convenient to access the media and other information with the help of the Smart mirror. As the internet of things (IOT) allows devices to communicate in different and important places at the same time. Smart Mirror is the one of the important Application of the internet of things (IOT). The project generally works on the reduce the need of the user to make time to check the PC or the Tablet and mobile phone while morning and the night routine for the information they need.

Keywords: SMART MIRROR, ARTIFICIAL INTELLIGENCE, RASPBERRY PI

Abstract: Social media is very important factor in analysing modern society as a whole, their values, norms, and behaviours, as being a part of our everyday life. This study is oriented towards analysing social media in order to allow users to create their own preferences to follow (analyse) a specific social media source. The web application has been developed to allow a user to follow specific Facebook accounts and categorize the Facebook posts on those accounts based on the user defined taxonomies. Results of this study are various reports generated from the Facebook posts and their statistics that are clustered based on the user defined taxonomies. The benefit of this project is that any user can track in real time when people are talking about some topic, and it enables anyone to have better insight about society as a whole, their values, norms, what they find interesting, and many other things. This tool is also useful for different companies to track the user feedback on social networks for their products.

Keywords: Social media, people, society, generation.

Abstract: The extensive use of medical imaging has become a routine practice in modern medical health care centres. It is used almost in every stage of patient management system. However, it is intuition or expertise of physician to choose a modality or alternative modality wisely for managing the patient as single modality has limitations. Therefore, single modality is necessarily ruled out in diagnosis and treatment processes. Multimodality medical image analysis plays a significant role in the diagnosis, treatment planning, delivery of treatment, and review of patient’s response to the treatment. In this thesis an attempt is made to aid radiologist with new fused image created from two modality images for the better visualization and interpretation of abnormalities in context with the purpose of accurate diagnosis, to prepare precise treatment plan, to classify the stages of diseases, and to review the effectiveness of the treatment. The proposed research work presents the feature based fusion algorithms in wavelet domain to combine the relevant and complementary spectral features of two modalities namely computed tomography (CT) and magnetic resonance imaging (MRI). The directional features of source modality images are extracted using various proposed wavelet transforms viz. nonsubsampled rotated wavelet transform, nonsubsampled rotated dual tree complex wavelet transform, dual tree complex wavelet packet transform, M-Band wavelet & MBand complex wavelet transforms, and rotated Daubechies complex wavelet transform. These spectral features are combined in new composite space using appropriate fusion rules. The corresponding inverse transform is used to create fused image. The multimodality medical image fusion is a powerful technique for analysis of lesions. The fusion approaches presented in this thesis are used for three main applications i.e. radiotherapy (RT), diagnosis and stage identification of neurocysticercosis (NCC), and the disease management in hepatocellular carcinoma (HCC). The fused images are useful in radiotherapy for accurate localization of tumour, to visualize its complete spread, and precise treatment plan for the target volumes without affecting critical organs. In second application, fused images help radiologists to identify the stage disease of neurocysticercosis. It is beneficial to finalize the treatment plan as per the stage disease. In HCC, the fusion results are presenting the level of damage to liver, accurate localization of masses, classify the disease, and confirming diagnosis which is helpful in conclusive treatment plan. Fusion process is also useful in the post treatment follow ups of neurocysticercosis.

Keywords: Medical, imaging, image processing technique

Abstract: The extensive use of medical imaging has become a routine practice in modern medical health care centres. It is used almost in every stage of patient management system. However, it is intuition or expertise of physician to choose a modality or alternative modality wisely for managing the patient as single modality has limitations. Therefore, single modality is necessarily ruled out in diagnosis and treatment processes. There are millions of imaging procedures done every week worldwide. Medical imaging is developing rapidly due to developments in image processing techniques including image recognition, analysis, and enhancement. Image processing increases the percentage and amount of detected tissues. This chapter presents the application of both simple and sophisticated image analysis techniques in the medical imaging field. This chapter also summarizes how to exemplify image interpretation challenges using different image processing algorithms such as k-means, ROI-based segmentation, and watershed techniques.

Keywords: Medical, imaging, image processing technique

Abstract: In this era, online shopping is the most common way to buy things without going out. With less effort, people can buy products by staying at home. Shopping on e-commerce websites is increasing day by day, and today's young people prefer online shopping to local stores because of the accessibility and efficiency of the Internet. In this online shopping, many items are not delivered on time and can take up to 2-3 days. Local markets are also influenced by the popularity of e-commerce sites and online shopping. The proposed solution provides local businesses with an online platform based on location preferences. If the owner of a local store can register and sell the item on this platform and the customer can buy the item online at the nearest local store. This will allow customers to view and purchase all products available in the shop. To make the platform readily available on almost all Android devices owned by the majority of the population.

Keywords: Mobile App Development, Flutter, Ecommerce, Firebase, Local trading

Abstract: The design of a mobile robot is a challenging task. A truly autonomous robot must be able to sense its environment and react appropriately. This issue becomes even more important if the environment is varying. One of the goals in robotics is to mdow robots with the ability to move and operate autonomously in an environment with unknown, perhaps moving obstacles.

Keywords: Information retrieval, Page ranking, Evaluation of information retrieval system.

Abstract: Communicating with the person who is having hearing disability is always a major challenge. The work presented in the paper is an exertion (extension) towards examining the difficulties in classification of characters in Indian Sign Language (ISL). Sign language is not enough for communication of people with hearing ability or people with speech disability. The gestures made by the people with disabilities get mixed or disordered for someone who has never learnt this language. Communication should be in both ways. In this paper, we introduce Sign Language recognition using Indian Sign Language. The user must be able to capture images of hand gestures using a web camera in this analysis, and the system must predict and show the name of the captured image. The captured image undergoes a series of processing steps which include various Computer vision techniques such as the conversion to gray-scale, dilation and mask operation. To train our model and identify the pictures we can use Convolutional Neural Network (CNN). Our model has achieved accuracy about 95%.

Keywords: Indian Sign Language (ISL), hearing disability, Convolutional Neural Network (CNN), Communication.

Abstract: The new healthcare delivery system is unaffordable complex, unreliable, and unsustainable. Machine Learning (ML) has revolutionized the way companies and individuals use data to increase system performance. Machine learning algorithms can be used by strategists to process a variety of organized, unstructured, and semi-structured data. This technology provides a virtual assistant who can communicate with patients in their native language to understand their symptoms, provide physician advice, and monitor health indicators. In addition, natural language processing algorithms and deep learning analytics are used to analyze customer reviews and find the nearest specialist that can help with the user's illness. A deep bilinear similarity model is also proposed in the architecture to enhance the created SQL queries used in algorithms and predictions.

Keywords: Personal Health records, Natural Language Understanding, Speech recognition

Abstract: The purpose of Online Food Ordering System is to automate the existing manual system by the help of computerized equipment’s and full- fledged computer software, fulfilling their requirements, so that their valuable data/information can be stored for a longer period with easy accessing and manipulation of the same. The required software and hardware are easily available and easy to work with. Online Food Ordering System, as described above, can lead to error free, secure, reliable and fast management system. It can assist the user to concentrate on their other activities rather to concentrate on the record keeping. It will help organization in better utilization of resources. The organization can maintain computerized records without redundant entries. That means that one need not be distracted by information that is not relevant, while being able to reach the information. The aim is to automate its existing manual system by the help of computerized equipment’s and full-fledged computer software, fulfilling their requirements, so that their valuable data/information can be stored for a longer period with easy accessing and manipulation of the same. Basically the project describes how to manage for good performance and better services for the clients.

Keywords: Apache, PHP, MySQL, NetBeans

Abstract: A Personal Digital Voice Assistant is a software agent that is used to interpret human voices or speeches. It can also respond to verbal commands of the user. Personal Digital Voice Assistant is considered a platform to perform the daily tasks of the user. The personal digital voice assistant is an assistant program that works on the desktop.it is connected to the web browsers to perform web searches the digital voice assistant aims to provide a hands-free experience to the user. Voice assistant is an experiment that changes the way of living life, here the GTTS (Google Text-To-Speech) converts text into audio (mp3) files, and later the audio is played as output by using python play sound package. In this paper, we focus on the development of the personal voice assistant and also on how the AI-based assistant will execute its task. Our focus is to provide a hands-free experience for the user. The entire assistant is designed using the python programming language.

Abstract: Hospitals are the most widely used means by which a sick person gets medical check-ups, disease diagnosis and treatment recommendation. People consider it as the most reliable means to check their health status. The proposed system is to create an alternative to this conventional method of visiting a hospital and making an appointment with a doctor to get a diagnosis. If one is not very serious and only wants to know about the kind of disease facing, this system is the cure for all ills. Here, the system allows users to share their symptoms and gives the predicted disease with suitable treatment. Once the user enters the symptoms, the data is classified from the dataset and finally the disease will be predicted. After prediction this system also suggests suitable treatment for the disease and also the list of doctors specialized in that field and users can take appointments using this system.

Keywords: Machine Learning, Random Forest Classifier, Django, Data Preprocessing

Abstract: In current technical market, new small level startup are going towards automatic hosting and paying a lot of money to multiple hosting companies. They don't have control over scaling up and down and quality of hosting. Now we are introducing a tool, which can help a startup to scale up their infrastructure as per different architectural setup. We are setting the startup setup over AWS cloud so that they can get the benefit of "pay as we go" model. Now startup company would have full control over infrastructure as well as bills. Technical

Keywords: AWS Cloud Computing, Access key, Secrete key, AWS CLI, Authorization, Authentication, MFA

Abstract: A big repository of terabytes of statistics is generated every day from contemporary records systems and digital technologies which includes internet of factors and cloud computing. Evaluation of these massive statistics calls for numerous efforts at a couple of levels to extract knowledge for selection making. Therefore, large facts analysis is a modern-day place of research & improvement.The fundamental objective of this paper is to discover the capability impact of huge records challenges, open studies problems, and diverse tools related to it. As a end result, this text presents a platform to explore big records at severa levels. Additionally, it opens a new horizon for researchers to broaden the solution, based totally on the challenges and open research problems

Keywords: Massive data; Structured data; Unstructured Data;iot; Big data analytics; Hadoop;

Abstract: Deforestation detection by using RCNN is a new approach to monitoring the emergence of deforested areas. In recent decades, illegal logging has intensified, threatening the environment and contributing to climate change. Deforestation is increasing day by day as no adequate protection is provided. They eventually found one of the most endangered trees in our country. Therefore, in order to protect the trees, the project proposed a way to detect deforestation and fire burning near trees using in-depth learning strategies. The main goal is to see if there is a suspicious person in the forest who could cut down and chop wood and see a fire in the forest that will avoid dangerous damage such as burning trees. A major role is to make a divider that gets a man-made saw. This project is based on the RCNN (Recurrent convolutional Neural Network). After the fire is detected, the system will generate a voice alert and send an email alert to the forest department. To detect the theft of a tree, the system will generate an email alert and send it to the relevant forest department via IMAP protocol and a voice alert is also activated. So we can avoid losing fire by extinguishing a fire if it is a fire alarm or by catching a wood thief trying to steal firewood in case of a theft alarm

Abstract: This paper describes a real-time soil monitoring for the agriculture farmlands to provide optimal and integrated data collections. Real- time monitoring provides reliable, timely information of crop and soil status plays an important role in the decision making in the crop production improvement. Agriculture depends on many parameters such as inter and intra variability of plants to give better yields such as soil parameters, climatic parameters and so on. Here the system is designed to collect the data set for major parameters such as temperature, humidity, soil pH, soil moisture, light intensity and carbon-dioxide of the fields. The system consists of an ATmega 328 microcontroller, DHT11 Sensor, soil hygrometer, light intensity sensor, soil pH sensor, MQ-135 sensor and DC motor. Data sets collected were used for the analysis of selection of crops and their vulnerabilities for regulating the irrigation parameters which will be of help in the agricultural practices, it will make easy way for farmers to take decision on planting a crops, watering and fertilizing them by avoiding the interference of hydro geologists and soil scientists by giving precaution. The obtained results were compared with the standardized optimum values for the particular crops and based on the differences inputs for the crops are varied. The automated watering helps the crops to get flow of water to fields based on the parameters, which is controlled by the DC motor. Multi sensor implementation for acquiring primary parameters essential for plant growth is the main aim of the paper. Easily available sensors were a motivation for the development of this project.

Keywords: ATmega328 microcontroller, DHT11 sensor, soil hygrometer, light intensity sensor, soil PH sensor, MQ-135 sensor and moisture sensor.

Abstract: Rapid advancements in digital data collecting techniques have resulted in massive data volumes. Unstructured or semi-structured data makes up more than 80% of today's data. Finding acceptable patterns and trends to interpret text documents from huge amounts of data is a major challenge. The process of extracting interesting and nontrivial patterns from large amounts of text documents is known as text mining. There are a variety of strategies and tools for mining text for useful information for future prediction and decision-making. The suitable and appropriate text mining technique is used to increase the speed and reduce the time and effort necessary to retrieve relevant data. Text mining techniques and their applications in various spheres of life are briefly discussed and analysed in this work. Furthermore, text mining difficulties that affect the accuracy and relevancy of results are identified.

Keywords: Information Extraction; Patterns; Classification; Knowledge Discovery; Applications;

Keywords: QR code, Quick Response Code, Storage Capacity, Online QR Code Generator.

Abstract: The Internet of Things is both a new revolution and a technique that is rapidly evolving at the moment. It is possible to connect all of the gadgets that are used on the Internet in daily routines with the IoT. The Internet of Things (IoT) will have a significant impact on people's lives because it makes various strange things possible. IoT systems generate vast amounts of data that are exceedingly precise, trustworthy, and valuable. It's difficult to extract useful information from a massive data set. Data mining is critical to making the IoT framework intelligent enough to provide relevant facilities and applications. The availability of data is the most crucial aspect of IoT.

Abstract: In this paper, The human face is an important organ of an individual‘s body and it especially plays an important role in extraction of an individual‘s behavior and emotional state. Manually segregating the list of songs and generating an appropriate playlist based on an individual‘s emotional features is a very tedious, time consuming, labor intensive and upheld task. Various algorithms have been proposed and developed for automating the playlist generation process. However the proposed existing algorithms in use are computationally slow, less accurate and sometimes even require use of additional hardware like EEG or sensors. This proposed system based on facial expression extracted will generate a playlist automatically thereby reducing the effort and time involved in rendering the process manually. Thus the proposed system tends to reduce the computational time involved in obtaining the results and the overall cost of the designed system, thereby increasing the overall accuracy of the system. Testing of the system is done on both user dependent (dynamic) and user independent (static) dataset. Facial expressions are captured using an inbuilt camera. The accuracy of the emotion detection algorithm used in the system for real time images is around 85-90%, while for static images it is around 98- 100%. The proposed algorithm on an average calculated estimation takes around 0.95-1.05 sec to generate an emotion based music playlist. Thus, it yields better accuracy in terms of performance and computational time and reduces the designing cost, compared to the algorithms used in the literature survey

Keywords: Extraction, upheld task, expression, playlist, emotion detection.

Abstract: In this paper, The human face is an important organ of an individual‘s body and it especially plays an important role in extraction of an individual‘s behavior and emotional state. Manually segregating the list of songs and generating an appropriate playlist based on an individual‘s emotional features is a very tedious, time consuming, labor intensive and upheld task. Various algorithms have been proposed and developed for automating the playlist generation process. However the proposed existing algorithms in use are computationally slow, less accurate and sometimes even require use of additional hardware like EEG or sensors. This proposed system based on facial expression extracted will generate a playlist automatically thereby reducing the effort and time involved in rendering the process manually. Thus the proposed system tends to reduce the computational time involved in obtaining the results and the overall cost of the designed system, thereby increasing the overall accuracy of the system. Testing of the system is done on both user dependent (dynamic) and user independent (static) dataset. Facial expressions are captured using an inbuilt camera. The accuracy of the emotion detection algorithm used in the system for real time images is around 85-90%, while for static images it is around 98- 100%. The proposed algorithm on an average calculated estimation takes around 0.95-1.05 sec to generate an emotion based music playlist. Thus, it yields better accuracy in terms of performance and computational time and reduces the designing cost, compared to the algorithms used in the literature survey

Keywords: Extraction, upheld task, expression, playlist, emotion detection.

Abstract: Visually disabled people find difficulties detecting obstacles in front of them, during walking in the road, which makes it dangerous. The smart stick comes as a proposed result to enable them to identify the world around. In this paper we propose a result, represented in a smart stick with infrared detector to descry stair- cases and brace of ultrasonic detector to descry any other obstacles in front of the stoner, within a range of four measures. Also, another detector is placed at the bottom of the stick for the sake of avoiding billabongs. Speech advising dispatches and the vibration motor are actuated when any handicap is detected. This proposed system uses the microcontroller bedded system; vibration motor and ISD1932 flash memory. The stick is able of detecting all obstacles in the range 4 cadence during 39 mins and gives a suitable respect communication empowering eyeless to move doubly his normal speed because she/ he feels safe. The smart stick is of low cost, fast response, low power consumption, light weight and capability to fold.

Keywords: Smart Stick, Sensors, Buzzer, Blind, IR sensors, Water sensor, GSM.

Abstract: People are undergoing a routine and busy schedule that leads to stress and anxiety. In addition to this, the percentage of people who are obese, stressed, and addicted to cigarettes is going up drastically [4]. This is leading to heart diseases. Heart diseases are one of the utmost causes of death in the world. The number of people affected by heart disease increases irrespective of age in both men and women [4]. The challenge behind these diseases is their timely prediction. While factors like gender, diabetes, and BMI also contribute to this disease, the chances of having heart disease also increase with the age. Men have a greater risk of heart disease. However, women also have the same possibility after menopause. Leading a stressed life can increase the chance of coronary heart disease. In the proposed research, to pre-process data we’ve used techniques like the removal of noisy data, removal of missing data, filling default values if applicable, and classification of attributes for prediction and decision making at different levels. The performance of the diagnosis model is obtained by using methods like classification, accuracy, sensitivity, and specificity analysis [16]. This project proposes a prediction model to predict whether people have heart disease or not and to provide awareness or diagnosis on the same [16]. This is done by comparing the accuracies of applying rules to the individual results of Support Vector Machine, KNN classifier, Decision Tree Classifiers, and logistic regression on the dataset taken to present an accurate model of predicting cardiovascular disease.

Keywords: Coronary Heart Disease; Decision Tree Classifier; K Nearest Neighbor; Machine Learning; Naive Bayes; Support Vector Machine

Abstract: In recent years, data mining and text mining techniques have been frequently used for analyzing questionnaire and review data. Data mining techniques such as association analysis and cluster analysis are used for marketing analysis, because those can discover relationships and rules hiding in enormous numerical data. On the other hand, text mining techniques such as keywords extraction and opinion extraction are used for questionnaire or review text analysis, because those can support us to investigate consumers’ opinion in text data. However, data mining tools and text mining tools cannot be used in a single environment. Therefore, a data which has both numerical and text data is not well analyzed because the numerical part and text part cannot be connected for interpretation. In this paper, a mining framework that can treat both numerical and text data is proposed. We can iterate data shrink and data analysis with both numerical and text analysis tools in the unique framework. Based on experimental results, the proposed system was effectively used to data analysis for review texts.

Keywords: Text mining, data mining, data analysis support, TETDM

Abstract: This study looks at the benefits of data mining in everyday life, particularly in healthcare. Statistical analysis has gotten a boost thanks to the prevalence of computing technologies. Data mining uses and improves existing statistical approaches to forecast human behaviour in a variety of fields, from supermarket purchases to cancer vaccine production. The paper begins with a quick overview of data mining, including examples of common and daily retail uses. The technology and methods used in data mining are briefly discussed. A brief conversation with a company that uses data mining to its advantage is mentioned. The publication then goes on to describe a number of research studies that have employed data mining to answer important health problems. What age group is the most vulnerable to cardiovascular disease? Which cancer vaccine trial is the most popular? How many of these experiments were successful? What is an effective treatment for a rare paediatric disease? How can data mining be utilised to solve challenges in medical applications in different countries? How can one reliably calculate life expectancy? This document answers the majority of these questions. The legal and ethical implications of data mining are then discussed. Finally, we end on a positive note about this intriguing technology's future possibilities.

Abstract: Photon checking imaging can be used to get obviously photon-confined scenes. In photon checking imaging, information on event photons is gotten as twofold edges (bit plane housings), which are changed into a multi-digit picture in the propagation cycle. In this cooperation, it is vital to apply a deblurring methodology to enable the catch of dynamic scenes without development dark. In this article, a deblurring strategy for the extraordinary piece plane packaging changing of dynamic scenes is proposed. The proposed method incorporates the deblurring of units of article development inside a scene through the use of development compensation to pixels having comparative developments. This technique achieves more useful development dark camouflage than the usage of direct deblurring to pixel block or spatial region units. It furthermore applies an original methodology for accurate development evaluation from the piece plane packaging even in photon-confined conditions through the real appraisal of the transient assortment of photon rate. As well as deblurring, our exploratory results moreover revealed that the proposed strategy can be applied for denoising, which further develops the zenith signal-to-uproar extent by 1.2 dB. In summary, the proposed method for bit-plane generation achieves incredible imaging even in photon-confined special scenes.

Abstract: Jet engines are required to operate at a higher rpm for the same thrust values in cases such as aircraft landing and military loitering. High rpm reflects higher efficiency with increased pressure ratio. Turbofan Power Ratio, which is a compound thermodynamic value of various pressures and temperatures across the engine, is proportional to the thrust output of the turbofan, and the same relationship was proven by the author earlier regarding turbojet engines with fixed geometry exhaust nozzle. This work provides the review on performance parameters related to turbojet engine. All simulations will be done on MATLAB Tool.

Keywords: Jet Engine, Energy Efficiency, Engine Pressure, Exhaust Nozzle etc.

Abstract: All mechanical systems exhibit vibrational response when exposed to external disturbances. In many engineering applications vibrations are undesirable and may even have harmful effects. In active control of vibration, the ability to actuate the system in a controlled manner is incorporated into the structure. Sensors are used to measure the vibrations and secondary inputs to the system are used to actuate the flexible body in order to obtain some desired structural response. This work provides the review on mechanical vibrations system based on gear and bearing structure. All analysis will be done using MATLAB tool.

Keywords: Mechanical Vibrations, Signal Simulations, Non-Stationarity, Mechanical Bearings, MATLAB etc.

Abstract: Clean water is a basic requirement for all living things. It is impossible to survive on Earth without water. Water covers around 70% of the Earth's surface, but just 3% of it is pure water. The wastes created by humans floating on water are extremely hazardous for the water life. Because most diseases nowadays propagate through water, an aqua waste collection robot is required. This paper illustrates aqua garbage collecting robot and collect many types of floating wastes and collect more amount of waste. It is easy for the user operation and environmental friendly. In our approach, conveyor belt mechanism is used to replace a traditional way of collecting a garbage from river. Conveyor Belt Mechanism is monitored remotely for collecting wastes from river. The sensor senses the garbage level in the collector bin and shares the information by message. Based on the obtained information the robot is being controlled. The trash is pushed into a bin located just behind the conveyor. This will be used to clear surface garbage from rivers, ponds, lakes, and other water bodies. Thus it reduces water pollution and aquatic animal deaths. This also lessens the problems faced by humans as it removes the surface garbage like plastic bottles.

Keywords: Garbage collection, Arduino controller, Conveyor belt mechanism, remote monitoring.

Abstract: Computers have been aiding us to perform herculean tasks for decades. From carrying out complicated calculations to automating a lot of our daily life’s processes - all has been made possible due to advancement in technology and making computers smarter. In a similar fashion, we can implement a program that mimics the way the human eye works (Computer Vision) and make it recognize the patterns that it comes across. Our goal is to make a program that is able to recognize gestures made by our hand. The program is written in Python programming language along with OpenCV libraries. In order to use this program, the user needs to be in front of a computer webcam that will be used to recognize the gesture made by the user’s hand. The program will display results of recognized hand gestures on a live video frame stream. Keywords - Computer Vision, OpenCV, Python, Gestures

Abstract: Crypto is the future of transactions in the upcoming future and people are moving towards it. But people should have knowledge of how to use and where to use their crypto. It is a great responsibility of ours to provide a resourceful and trust based platform to the people. In order to provide these services, we’re implementing Cryptopunk to help the people with no charges and no service fees.

Keywords: Cryptocurrency, Deep Learning, NFT, LSTM, Prediction

Abstract: Educational institutions (schools, colleges, and universities) in India are currently based only on traditional methods of learning, that is, they follow the traditional set up of face-to-face lectures in a classroom. Although many academic units have also started blended learning, still a lot of them are stuck with old procedures. The sudden outbreak of a deadly disease called Covid-19 caused by a Corona Virus (SARS-CoV-2) shook the entire world. Around 32 crore learners stopped to move schools/colleges and all educational activities halted in India. The outbreak of COVID19 has taught us that change is inevitable. It has worked as a catalyst for the educational institutions to grow and opt for platforms with technologies, which have not been used before The World Health Organization declared it as a pandemic. This situation challenged the education system across the world and forced educators to shift to an online mode of teaching overnight. Many academic institutions that were earlier reluctant to change their traditional pedagogical approach had no option but to shift entirely to online teaching–learning. The article includes the importance of online learning and Strengths, Weaknesses, Opportunities, & Challenges (SWOC) analysis of e-learning modes in the time of crisis. This Research paper also put some light on the growth of EdTech Startups during the time of pandemic and natural disasters and includes suggestions for academic institutions of how to deal with challenges associated with online learning. The Research paper will attempt an analysis of Origin of Covid 19, its impact on education, Role and importance of Internet during covid 19, internet barring in Kashmir, and More importantly this paper will through a shift of light to the important scenarios of Covid 19

Keywords: information technology, social media, social media Keynotes: Orgin of covid 19, postive and negative impact of covid on education, internet connectivity in J@K, Life of Private scool teacher

Abstract: Cyber-physical systems (CPS) are becoming increasingly widespread, and their security has become a major concern. CPS refers to the integration of physical devices with computer systems, which can result in a broad range of applications, from autonomous vehicles and smart cities to industrial control systems. While this integration brings new opportunities and benefits, it also exposes the systems to new threats and vulnerabilities. This research paper presents a security algorithm that can be used to prevent cyber-attacks on CPS. The proposed algorithm uses a combination of encryption and digital signatures to secure data transmission and authenticate communication between physical devices and computer systems. The paper also discusses the implementation of the algorithm in CPS and its effectiveness in preventing cyber-attacks.

Keywords: Cyber-physical systems, Security algorithm, Cyber attacks, Encryption, Digital signatures, Authentication.