VOLUME 10, ISSUE 5, MAY 2021

Abstract: The deployment of cellular networks assisted by device-to-device (D2D) communications has great significance to improve spectral efficiency. In D2D communications underlay scenario, the D2D user equipments (DUEs) reuse the same frequency resources assigned to cellular user equipments (CUEs) for spectral utilization. Unfortunately, introducing D2D communications into cellular networks bring interference signals to CUEs and other DUEs. Therefore, to fully reap the benefits of D2D communications, efficient resource allocation with interference management is highly required. In this paper, we propose a system model for D2D communications underlaying cellular network, where multiple D2D pairs reuse the same frequency resources allocated to a single CUE. In addition, we propose a many-to-one frequency reusing resource allocation algorithm for D2D communications with the aim of maximizing the network sum-rate. To solve this NP-hard problem, we first propose an interference management algorithm based on graph theory to find the least interfered D2D pair groups, followed by proposing an optimized power allocation algorithm based on linear programming, and finally proposing a process matching algorithm to find the best sets of CUEs and D2D pair groups for spectral reusing. Simulation results demonstrate that the performance of the proposed many-to-one spectral reusing resource allocation algorithm exceeds the one-to-one resource allocation for D2D communications in terms of sum-rate.

Keywords: Device-to-Device communications, power allocation, interference management, matching process, graph theory, matching theory

Abstract: Unlike their physical health, individuals generally lack insight into their psychological/cognitive health which can also lead to body health problems. This blind spot, in addition to the stigma of seeking the help of mental health professionals, results in many disorders related first to brain and then to both body and mind. This ultimately requires extensive use of Prescription Drugs (PD) which focus on treating symptoms rather than cause of health problems. For Self-Study and -Care (SSC) of initial/emerging health problems, who is the decision maker for addressing health problems without using PD? While brain is in-charge of survival, mind is decision maker for anything and everything humans do. This paper introduces and describes creative health approaches for SSC using new scientific model of mind which is an algorithm based on data generated along the Microbiome-Gut-Brain-Axis (MGBA). This is a valuable tool to study how brain areas act in concert to participate in a variety of cognitive processes including attention, learning, social cognition, and emotional states. For the first time, this study defines new scientific mind concepts of Complete Mind (CM), Emotional Mind (EM), Female Mind (FM) and Mirror Mind (MM) all of which affect the strategy used by a human for SSC with CM defined as an algorithm based on EEG (Electroencephalogram) data from MGBA. CM for females is same as FM except the latter also includes multitasking. When a human is under stress CM may be reduced to EM. CM is used for decisions regarding herbal remedies, reflexology, meditation, self-healing, environmental affects, food, stress, single-sensor FTIMS (Fabric- and Tattoo-Embedded Inexpensive Micro Systems) for data upload to a smartphone and analysis using MATLAB.

Abstract: The Healthcare industry contains very large and sensitive data and needs to be handled very carefully. Diabetes is one of the growing, fatal diseases all over the world. Medical professionals want a reliable prediction system to diagnose Diabetes. Different machine learning techniques are useful for examining the data from diverse perspectives and synopsizing it into valuable information. The accessibility and availability of huge amounts of data will be able to provide us with useful knowledge if certain data mining techniques are applied to it. The main goal is developing a decision support system for the diagnosis of diabetes using a machine learning model. Diabetes contributes to heart disease, kidney disease, nerve damage and blindness. So, efficiently mining the diabetes data is a crucial concern. The data mining techniques and methods will be discovered to find the appropriate approaches and techniques for efficient classification of the Diabetes dataset and in extracting valuable patterns. The RStudio software was employed for diagnosing diabetes. The Rivers State University Teaching Hospital dataset was acquired from the Health Database of the Hospital used for analysis. The dataset was studied and analyzed to build an effective model that predicts and diagnoses diabetes disease. In this study, we aim to apply the bootstrapping resampling technique to enhance the accuracy and the applying Logistic regression model.

Keywords: Logistic Regression Classification, Healthcare, Diabetes.

Abstract: The rapid development of Information Technology (IT) has altered the appearance of the network perimeter. Data is all around, with users who access it from around the world and from all types of devices. At the same moment, Information Technology (IT) teams are implementing analytics, cloud, as well as automation to quicken the delivery of innovative applications and drive business development. These essential changes have created a threat environment that reveals weaknesses in legacy security technologies, for example, the port-based network security, as well as the different tools and technologies which are not natively incorporated. This concern has driven many enterprises to look for more sophisticated capabilities to improve their cybersecurity. Traditionally, a normal firewall follows preset Web protocols. It does not have the capability to differentiate between different types of Web traffic. This restriction forces the system in order to only permit or prohibit traffic, depending upon a specific set of built-in standards. Therefore, the protection it offers for particular protocols, ports, and IP addresses is no longer sufficient. Businesses need tougher security that is not tied down to preset settings. Modern-day firewalls need more advanced rules to control website access as well as app usage inside the enterprise networks thus the advancement of next-generation firewalls (NGFWs) and Web Application Firewall (WAFW). The main objective of this research paper is to analyze the evolution of next-generation firewalls (NGFWs) and Web Application Firewall (WAFW) and their characteristics. Also, what it is going to take to safeguard the enterprise's environment for the foreseeable future.

Keywords: Next-Generation Firewalls (NGFWs), Web Application Firewall (WAFW), SQL Injection, Cross-site Scripting (XSS), Web Scraping, OWASP Top Ten threats.

Abstract: From the instant the payment systems came to existence, there have continuously been those that can notice new ways in which to access someone’s finances illicitly. This has become a significant drawback within the era, as all transactions will simply be completed on-line by solely getting into your mastercard data. Even within the 2010s, several yankee retail web site users were the victims of on-line group action fraud right before ballroom dancing verification was used for looking on-line. Organizations, consumers, banks, and merchants square measure place in danger once a knowledge breach ends up in financial stealing and ultimately the loss of customers’ loyalty in conjunction with the company’s name. Finally, the accuracy of the results information is optimized. In this system we offer double verification to enhance user information security. during this system user have to be compelled to 1st enter verification code that is send to the user once scanning information of user completed by the system. this method allow dealing if user clear all the stages of verification and security rules.

Keywords: credit card, fraud detection , transaction, verification, security, prevention.

Abstract: In this paper, a six band microstrip patch antenna design for wireless applications is proposed and simulated. The proposed antenna resonates at (4.084-4.185GHz), (5.857-6.043GHz), (6.218-6.407Hz), (6.784-6.976GHz), (9.553-10.46GHz), and (10.474-11.24GHz) with a minimum return loss of-35.99dB (5.94 GHz). The FR-4 material is used to isolate ground and patch with a 4.3 dielectric constant and 1.6 mm thickness and uses a microstrip transmission line. In this design, the return loss is minimized by adding an extra three rectangular blocks to the patch. CST microwave studio simulation software is used for the design and simulation of this proposed antenna. The design is simple geometry and provides good bandwidth with appreciable gain. The proposed antenna can be used for different applications in the C, X bands of wireless communications. Keyword:- FR-4, CST, E-shap, square slot, rectangular block.

Abstract: Text mining has become a research field that incorporates different techniques such as information retrieval, information extraction, natural language processing, among others, allowing the discovery of important information patterns. This research analyses and describes in a clear and detailed way the elements that comprise it, also shows the most frequent applications that exist today.

Keywords: Text Mining, pre-processes, Text Mining Applications, Text Mining Techniques.

Abstract: Chess is a game that is played between two players, it has its own rules of play which help to enhance and improve the mental and intellectual activities of the player. This game has a large number of followers around the world. This document works with a complete computer chess game, for the first time, the game sets the computers of two players to play chess according to the legal rules of chess on the computer. Secondly by making the game more enjoyable which will allow users to play directly against the computer so the mental power of the computer is added.

Keywords: AI , Zero-Sum game , Evaluation function , Alpha beta pruning.

Abstract: Tourism is an integral a part of human life. We always search for changes and adopt them. Now-a-days the tourism industry features a great importance in capitalism and finance. Since 2000 the tourism industry has been giving the variety of advantages to countries worldwide. The amount of foreign tourists visiting India which has given exchange earnings to the Country. Here, we've focused on the expansion and performance of the Indian tourism industry. Nowadays, everything a traveller must do is out there on an internet site. Employing a website, travellers can plan where they need to travel, weigh budgets and make bookings and cancellations and compare options. Doing this involves reading copious amounts of descriptions, terms and conditions, instructions and user comments before arriving at decisions. The opposite option is to supply a chatbot that's a conversational app that reduces the quantity of interaction required by refining intent and context into the conversation.

Keywords: Artificial Intelligence, tourism

Abstract: This software document is a research paper draft in IEEE format for the project submission for 3rd semester.

Abstract: Telecommunication, especially mobile phones have the potential to provide solution to the existing information asymmetry in various lagging sectors like agriculture. India’s agricultural sector suffers from low growth rates and low productivity. Issues in access to information are weak points at every stage of the agro-supply chain. For small farmer-based economy like India, access to information can possibly enable better incomes and productivity to the farmers. Information and Communication Technology (ICT) in agriculture is an emerging field focusing on the enhancement of agricultural and rural development in India. Using innovation is a key measure in the rural domain. The advancement of ICT can be utilized for providing accurate and timely relevant information and services to the farmers. We propose an android based mobile interface consisting several applications which include agro-based crop information, weather updates, government policies updates, etc. In a country like India where rural base is wide, its relevance cannot be overlooked. In addition to facilitating farmers in improving the efficiency and productivity of agriculture and allied activities, the potential of IT lies in bringing about an overall qualitative improvement in life by providing timely and quality information inputs for decision making; IT can also be effectively used to strengthen the supply chain for agro-based companies for leading to better price realization by farmers.

Keywords: Agriculture , Market Rates , Farming .

Abstract: With the ever increasing amount and variety of data to be stored and transmitted in various mediums, the specification of security which has to be established at various levels of medium access and the accompanying issues of authentication and authorization has become a critical factor. Various steganographic, watermarking and data-embedding algorithms have usually manipulated the actual data in order to either hide any coveted information or to provide some level of access control over the medium. The mediums are usually images, video, audio etc., wherein specific portions or the overall space is usually 'corrupted' with 'significant' data. We attempt to bring out the significance of the steganographic techniques that are employed in information processing algorithms for data security. It deals with the problem of data security, focusing mainly on images, and tries to state the various properties and characteristics that the steganographic algorithms should possess. We also highlight the technique of masking used in the conventional steganographic LSB algorithms and in its variants.

Keywords: Steganography, LSB Algorithm, AES Algorithm, ASCII codes.

Abstract: In the current situation, the majority of the patients have been infected with pandemic diseases like as COVID-19, SARS, and others. Fever, fatigue, and a dry cough are the most well-known side symptoms of corona virus infection. The majority of individuals recover from their ailment without the need for therapy. This condition can be complex in rare cases since it is more serious in older persons and can potentially be deadly. People who are older or who have other health problems may become increasingly powerless in the face of serious illness. They died before the medical concerns were properly diagnosed. Because it necessitates a significant financial commitment in maintenance, diagnosis, and treatment, as well as time to administer tests and study the patient's prior health history. Numerous studies have been conducted all around the world in order to find a better answer to this problem. Patients' previous healthcare records were saved in the cloud as a database in the suggested solution. Unauthorized people cannot access the patients' medical records. This cloud-based database gives doctors access to the patient's prior medical history, allowing them to save the patient in an emergency. Additionally, telemetry techniques are used to continually monitor the present condition of pandemic patients. The health professional advises medications and/or recommends precautions based on the patient's report state, and provides effective therapy without direct contact with them.

Keywords: Covid-19, Diagnosis, Internet of Things, Pandemic.

Abstract: As the remarkable blast of different substance created on the Web, Recommendation procedures have gotten progressively crucial. Countless various types of proposals are made on the Web each day, including music, pictures, books suggestions, inquiry ideas, and so forth Regardless of what sorts of information sources are utilized for the suggestions, basically these information sources can be displayed as diagrams. Suggestion frameworks are generally utilized in web-based business applications. The driving force of a current proposal framework prescribes things to a specific client dependent on client inclinations and past high appraisals. Different suggestion plans, for example, shared sifting and substance-based methodologies are utilized to fabricate a proposal framework. Affiliation rule mining is an information mining strategy. It is utilized for discovering the things from an exchange list which happen together oftentimes. The greater part of current suggestion frameworks was created to fit a specific area like books, articles, and films. We propose a half and half structure suggestion framework. In this paper, targeting giving an overall structure on digging Web diagrams for suggestions. We initially propose a novel dispersion strategy which spreads likenesses between various suggestions and suggest items utilizing Apriori based affiliation rule mining. At that point we outline how to sum up various proposal issues into our diagram dispersion structure. The proposed system can be used in numerous suggestion errands on the World Wide Web, including question ideas, picture proposals, and so forth We additionally propose a novel framework for limiting and offering cycle to be fused in the web application.

Keywords: Collaborative Filtering, E-Commerce, Data Mining, Apriori Algorithm

Abstract: The emerging e-commerce systems open the way for several applications to be viable from off-line to online system. E-Auction is an effective ecommerce system that allows bidders and sellers to interact through online platforms. However, providing completely secure e-auction system that satisfies security conditions for all players in these systems requires very complex efforts in the traditional design. Blockchain and smart contract, as a revolutionary technology, has attracted the interest of different industries including the designing of e-auction systems. In this paper, our aim is to provide a prototype of secure blockchain e-auction system that lowering the uncertainties about identities of long-distance complex trade in an e-auction system that can be implemented in UAE services, especially, UAE Auction. In our implementation, we use smart contract in order to guarantee the necessary security requirements. The smart contract contains important information about the transaction details such as auctioneer data, the start time and the deadline of auction, the current winner data, and the current highest price.

Keywords: Bidding, Blockchain, Security, Auction

Abstract: Digital technology is unlocking unprecedented opportunities for growth in the sports industry, offering the potential to draw fans closer through innovative and customized experiences. Digitization of sports has solved many traditional flaws that had dwelled in the system. One such flaw that still lives is the lack of ease with which a centralized body can organize sports events on a small scale. This project aims to resolve this issue and also simplify the process of scorekeeping at the same time. It is for a fact that, in any sports tournament or an event, keeping track of scores and the results could be quite a tedious job if there aren’t proper tools available. Thus, providing a platform accessible through a handheld mobile device that would allow users to digitize their experience while keeping track of the scores, results, player profiles, and match statistics is the final goal for the project.

Keywords: Scorecard, React-native, Sports management, Mobile application, Cross-platform, Android, IOS.

Abstract: In order to facilitate serial communication, an infrared communication-based system is developed for transmitting data from the transmitter end to the receiver end using infrared light radiation equipment. In this paper, the authors are trying to transmit data using an IR transmitter by converting it into the low-level format i.e., binary format (0’s and 1’s) once these bits are transmitted, they are received at the receiver end using an IR receiver and then again converted to the original format which is understandable by us. The intriguing part and epicenter of this paper is studying and formulating a technique of how these bits can be transmitted via infrared radiation. The system has low-cost, reliable transmission of data, stable performance, high-speed communication and almost no limitations of bandwidth range.

Abstract: To track the massive spike of the cases in this pandemic situation of corona virus or technically known as COVID-19, we decided to create an Android application. This corona virus was first discovered in China and then from there it started spreading all over the world and to track the record of the cases, deaths and recovery we decided to develop an Android application. This application was developed to spread awareness in our country (India) about this situation. This app provides the information about the COVID-19 cases, the confirmed cases, the total deaths, total recovered patients and the active cases in our country (India). This app shows the above mentioned details of our country (India) and the foreign countries too. Even this application shows the state wise information. All the symptoms and the steps to take against the corona virus is available in the application. Red zone areas and the helpline numbers are available of all the states of India. This application provides the live information of cases in numbers. With this application the people will get aware of the situation and even they can check whether they are in the red zone area by searching in the application. The users can see the active cases, total confirmed cases, total death, total diseased people, and total people who fought against this virus and had won (recovered people) of all the states in India and even get helpline numbers of all the states. We have created this very simple and straight forward application which make it very easy to use and its UI is user friendly easy to understand. All the provided information is perfect and accurate. The information provided in the application is taken from WHO (World Health Organisation).

Keywords: “Corona Virus”, “COVID-19”, “Cases”, “India”, “Awareness”, “Pandemic”

Abstract: The Online Examination System is web based solution for several organizations to take objective and subjective exam. The study reveals the aspect of online examination system like its accuracy, automation, security which made system being perfect. Online examination banishes the conventional technique of exam and introduces the all new method of exam without wasting papers and time. In conventional technique the enormous challenges is to preserve the data and there security, these system made all the challenges achievable. As we concern about digital India, so we can take one step forward towards digitalization by using Online Examination System. The system can smoothly float for colleges and universities, and bestow a superior examination platform. Keyword: Online Examination System, Php, MySQL Database, authorized, automation.

Abstract: A reputation score for an individual IP address is generated by an IP reputation platform, which can be used by businesses as a signal in a fraud risk scoring system. It is a common technique to identify malicious domains that are involved in spamming and phishing activities. IP reputation providers are becoming a popular risk assessment tool because they not only advise you if an IP address is hosting malicious content, but also whether it is involved in automated bot activity. Prior to the introduction of IP reputation services, organizations relied on solutions that linked the universal resource locator (URL) to malicious content such as spam, phishing emails, and viruses. URL-based solutions, on the other hand, were useless since they were sluggish to identify attacks and were easily circumvented by fraudsters. IP reputation services are now facing similar issues, as fraudsters leverage new tools and technologies to avoid detection.

Keywords: IP Reputation, Security, Threat Intel Feeds, Blacklists, Automation, Web Scraping.

Abstract: Cloud Cryptography is one amongst the vital facet within the world of knowledge security. It includes completely different encoding and secret writing techniques that square measure wants to keep our Data safe and secure on cloud. In Cloud Cryptography we have a tendency to use public and personal keys for Encrypting and Decrypting Data to keep up the integrity of knowledge. The quality with that cloud computing manages Data secrecy, and data security makes the market hesitant concerning cloud computing thus, during this paper we are going to discuss this parameter conjointly to clear the professionals of the cloud cryptography.In this paper we discussed about various survey on Cloud Cryptography.

Keywords: Cloud Security, Cryptographic algorithm, , Hybrid cloud,security infrastructure

Abstract: The next generation wireless systems are supposed to handle high data rate as well as large coverage area. It should consume less power and utilize bandwidth efficiently. At the same time, the mobile terminals must be simple, cheap, and smaller in size. In wireless communication, the quality of received signal level degraded due to various fading phenomenon. To combat these problems the new technology cooperative communication becomes popular to the research community. In which cooperation among nodes has been the subject of great interest among the researchers because it creates spatial diversity in wireless network, even if individual nodes do not use antenna arrays for transmission and reception. Different diversity combining techniques can be used to improve the performance of the wireless link. In this paper outage analysis of cooperative relay network has been carried out with selection combining and switch and stay combining. The results are simulated which shows that the outage performance of selection combining gives better results than switch and stay combining.

Keywords: Cooperative communication; diversity combining technique; Rician fading; selection combining; switch and stay combining.

Abstract: Multi-degree of freedom robots are playing very important role in different application of automation. They are providing much more accuracy in carrying out a typical procedure as compared to the manual work done by human. In recent years the design, fabrication and development of robotic arms have been active research areas in robotics all around the world. So keeping need of automation and industry in mind, we have praposed design and implementation of Six axis robotic arm which should perform industrial task such as pick and place of fragile objects operation. This robot arm being controlled by micro-controller has base, shoulder, elbow, wrist rotation and a functional gripper. The microcontroller implement forward kinematics and position control of DC motors. The design aims to provide fine manipulation in performing pick and place task, while still maintaining the simplicity of design.

Keywords: Six Axis, Bluetooth Module, Micro-controller, Stepper Motor.

Abstract: This Project is based on the idea of making an application which makes it easier to find the weather of any location. The Application will be created by using JAVA, so that it remains platform independent.

Keywords: Weather Application, Weather Report, Weather Forecast, Location based.

Abstract: Supply chains are evolving into automated and highly complex networks and are becoming an important source of potential benefits in the modern world. At the same time, consumers are now more interested in food product quality. However, it is challenging to track the provenance of data and maintain its traceability throughout the supply chain network. The traditional supply chains are centralized and they depend on a third party for trading. These centralized systems lack transparency, accountability and auditability. In our proposed solution, we have presented a complete solution for blockchain-based Agriculture and Food (Agri-Food) supply chain.

Keywords: blockchain,food adulteration,food wastage,customer satisfaction,

Abstract: Image and video-based vehicle insurance claim processing is an important area with a large scope for automation in the insurance sector. At present, the insurance claim process and validation are done manually resulting in a time-consuming process with less scalability and more prone to error. Especially during the pandemic times, manual inspection is a difficult process and claim amounts primarily rely on the type of damage and damaged part of the car, so rise the need for an automated system for the whole process of car insurance claim as which can efficiently classify and detect damage and helps to minimize the claim leakage. Also, there is a chance of faking car damage images using image forgery or deepfake generation techniques. To analyze and design an automated vehicle insurance claim platform that can perform car damage detection and classification along with image forgery & deepfake detection.

Keywords: Transfer learning, YOLO, image copy-move forgery detection (CMFD), speeded-up robust feature (SURF), polar complex exponential transform (PCET), Deepfakes, LSTM

Abstract: In today’s world where there is tremendous amount of information available on the internet, it is really important to perceive right information quickly and efficiently. The answer to this problem is an “Automated text Summarization”. As it can be done manually as well but, there is a chance that humans can be biased during the process and another disadvantage of doing it manually is that it can be very time consuming. It will also help us to extract the most important information from a large amount of data which is going to achieved using Natural Language processing algorithm. We have made our project using Python as a programming language along with React for the front end.

Keywords: Summarization, Natural Language processing, Python, React.

Abstract: Online bus reservation system is a project which presents a portal for bus ticket reservation. This application lets in users to book bus tickets from somewhere and anytime. The consumer can without difficulty e book their tickets and cancel tickets. The person can view all the small print of the website, bus, and drive. The user can additionally view the details of the journey and the important points of the ride.

Keywords: Electronic Ticketing, ITC, OBTRS, Transportation, Reservation.

Abstract: A Four element slot based Multiple Input Multiple Output(MIMO) antenna is presented. The antenna elements are planar in structure and designed on a single substrate. The substrate used for antenna design is FR4 epoxy with a dielectric constant of 4.4 the dimensions of the dielectric is 42×25×1.6mm3. The antenna design is optimized to cover various frequency bands from 4.2~7.2GHz making it applicable for WLAN. The proposed antenna is suitable for communication applications. The simulation of the antenna has been performed using High Frequency Structure Simulator (HFSS). The maximum measured gain of the antenna is 1.8dB. The envelope correlation coefficient (ECC) did not exceed .248 in the entire operating band of the MIMO antenna.

Keywords: Multiple Input Multiple Output(MIMO), HFSS.ECC,WLAN,VSWR

Abstract: Online E-learning system is a android application. Computer-based learning and interactive communication are included in this E-learning scheme. This E-learning method makes use of internet technology to provide students with information on a wide range of topics. Only registered users have the ability to add, display, or ask questions about topics. This project ensures that students receive an efficient and successful education. This method allows students and lecturers to communicate easily. E-Learning platform can be proposed to provide a good learning environment for learners. The e-Learning platform has a three-layer architecture to efficiently facilitate sharing, reusing learning materials, and interoperability among various learning material. Therefore, learners can make use of available learning objects without having to be affiliated with other Learning Management System. The E-Learinng system manages and stores e-books information electronically according to categories. All the users can use the app to keep track of the materials available in the system, download them, or use them online.

Keywords: Online learning platform, Electronic Learning System, Educational platform, Learning management systems, E-learning systems, Mobile-based learning systems.

Abstract: Conversational systems have made considerable strides in recent years as a form of human-computer interaction. Human-computer interaction has paved the way for large-scale natural language processing techniques. A chatbot in medical field [10] does instant research on people’s problems and prescribes medicine and assistance without any delay [9]. This system proposes a medical assistant chatbot that uses NLP concepts such as cosine similarity and TF-IDF approaches to replay to users, which will be pocket friendly, fast, accurate and a one place halt for a user to avail home remedies and easy cures for common diseases. Index Terms: Natural Language Processing (NLP), Natural Language Toolkit (NLTK), Term Frequency-Inverse Document Frequency (TF-IDF), Cosine Similarity.

Abstract: Emotion Recognition Systems is used to identifying the emotions of humans with their accuracy. This paper by using Audio-visual Data to recognizing emotion. We have to use machine learning. This emotion recognition system automatically identifies the human emotional states from his or her voice and face images. An audiovisual emotion recognition system is used to develop uses fusion algorithm. In this system firstly separate emotion recognition systems that use voice and facial expressions were tested separately. These two databases are used in this system Berlin EMODB database and Assamese database. This paper is dependent on recognizing human emotion and voice emotion. This system uses many emotional persons.

Keywords: Facial Expression Recognition, Emotional Model, Social Interfaces, Emotion Recognition, Machine learning.

Abstract: Coronavirus disease (COVID-19) is an infectious disease caused by the Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-Cov-2). To prevent ourselves, we should avoid touching the contaminated surface. At the same time, we should wash our hands. The sensor faucets of the present world will serve the purpose of water conservation and impediment to infection control. Generally active infrared (AIR) sensing technology is used in the hand free faucets. The receiver of this technique will demand a reflected ray (reflected by human hand) which activates the solenoid valve, so this design is complex and expensive. The sensor design of this approach will make things easy and cost efficient. Sometimes we could touch the faucet and soap bar carelessly after we wash our hands and the faucet could be contaminated. The person would then touch his/ her eyes, nose or mouth, and he/she has a higher chance of contracting this coronavirus disease. To prevent this from happening, we can use a dynamic faucet.

Keywords: COVID-19, Dynamic Faucet, Water, Hand wash.

Abstract: In this project our main motto is to create the students ERP(Enterprise resource planning) system. Now a days it’s very difficult to manage all the record and also difficult to analyse all the record in any department .A manual work is very lengthy and time consuming for entire departments. So for that needs of central system is arising which gives the effective and efficient result within a few time. All departments can access the data with the system and also they can perform a desire task. With that all the data can easily manipulate and get easily whenever anybody wants.The objective of this paper was to propose a design of ERP for college management system which provides a simple interface for maintenance of different student, department, faculties, library and other information. It can manage daily activities of college which include the management of Employees, Students, Books and Library Records, Parents details, Assignments, Admission Process, Results and Reports, Exams, Events, Attendance, Timetable, Fees and Other Report. It uses C4.5 algorithm to analyse student based on their performance and placement prediction of student.

Abstract: Crime is one of the serious issues in our society. It is the most predominant aspect of our society. It is also predominant in society. So, the prevention of crime is one of the important tasks. The crime analysis should be in a systematic way. As the analysis makes it important in the detecting and prevention of crime. The analysis detects the investigating patterns and helps in the detection of trends in crime. The main of this paper is the analysis of the efficiency of the crime investigation. The model is designed for the detection of crime patterns from inferences. The inferences are collected from the crime scene and these inferences, the paper demonstrates the prediction of the perpetrator. The paper gives the research way for the prediction of perpetrator age and gender. This paper gives two major aspects of crime prediction. One is perpetrator gender and the other is perpetrator age. The parameters used are analysis of the various factors like the year, month, and weapon used in the unsolved crimes. The analysis part identifies the number of unsolved crimes. The prediction task involves the description of the perpetrator’s age, sex, and relationship with the victim. The dataset used in this paper is taken from the Kaggle. The system predicts the output using multi-linear regression, K-Neighbor’s classifier, and neural networks. It was trained and tested using a machine learning approach.

Keywords: Crime Prediction, KNN, Decision Tree. Multilinear Regression; K-Neighbors Classifier, Artificial Neural Networks.

Abstract: As we all know today, world is suffering from an ongoing global pandemic. This pandemic has brought chaos and problems for everyone. It presented unprecedented challenge for human health, food system and world of work. The worst of the effect is on public social and economic life. Therefore, it is imperative to design an application which may help in the crisis in factor of economic recession. To overcome this challenge, we are designing an application on android platform for mobile devices. We chose mobile application because it is an essential part of everyone’s life and most people use it today. Targeting public devices on mobiles will be much easier than on a web application. It is proposed to use React Native and Node.js for the programming of the software for the devices. The application mentioned here will help people searching for job and those people who wants their work done by a professional. It’s an integrated software for consumer as well as service provider.

Keywords: Pandemic, economic, application, android application, jobs.

Abstract: Electronic Commerce is a process of doing business through computer networks. A person sitting on his chair in front of a computer can access all the facilities of the internet to buy electronic commerce is process of doing business through computer networks. or sell the products. Here we introducing multipurpose e-commerce website with security during registration level as well as transaction level. So, this research is an attempt to make a multipurpose e-commerce system with more secure and prevent unauthentic operations. In our system we categorize users need into three, which are shopping, social and services. This system can be used for all kinds of shopping, for house shifting and also for daily news update. Instead of using multiple websites for multiple purpose, users can use this single website for multiple purpose. This website is secure from hacker’s attack and also end to end encrypted.

Keywords: E-Commerce, Security, Shopping, Social, Services.

Abstract: It is known that social media is one of the largest sources of unstructured data. Analyzing that data and harvesting meaning out of that is a tedious job. Recently opinion mining has become an emerging topic due to the vast amount of opinioned data available on the various social networking sites. Microblogging has appeared relatively recently, and twitter is the most popular microblogging sites used by the people. It is one of the biggest free, open data-source. In the world today, twitter often witnesses a lot of opinions. Opinion mining and sentiment analysis help researchers to gain insight into public emotions. In this paper, Twitter is used as a source of opinioned data. Twitter APIs are used for the collection of tweets. In this paper, R is used for the acquisition, preprocessing, analyzing the tweets, then sentiment analysis is performed based on the different approaches. In this paper, Tweets were collected from the period of Jan 2019 to March 2019. Using that tweets, sentiment analysis was performed to gain the opinion polarity of the folks concerning general elections held in India. Two candidates were considered for this study: Candidate-1 and Candidate-2. It was concluded that Candidate-1 is more liked and is famous as compared to Candidate-2. The result obtained in our paper was in full compliance with the actual election results obtained in May 2019.

Keywords: Twitter mining; Text Mining; Sentiment Analysis; Social media

Abstract: Having to deal with sight loss or low vision is merely one of the challenges that the visually impaired are facing when living life. Unsighted persons find themselves vindicated to go out individually. There are millions of blind people in this world who are always in need of helping hands. But coming to the point of Blind people, no matter what advanced technology you give them, they may not operate because they don’t have the ability to see and use the devices. Not only devices, they need to depend on others completely even for small tasks. In order to fulfill the above missing parts of the blind people, we proposed a device embedded with advanced technology which will allow the person to do their own work rather than being dependent on others. In this project, we will be using Raspberry pi which will make smart sticks for blind people, embedded with pi camera modules and ultrasonic sensors. Pi Camera detects and identifies the type of object with the help of deep learning and its representative tools. An ultrasonic sensor is used to detect real-time hurdles while walking on the roads. The proposed system can provide more abundant surrounding information with the help of this Assistive device

Keywords: Raspberry Pi,Pi camera,Ultrasonic sensors.

Abstract: This paper proposes the real-time hand signs language detection system. As communication is an important part of life. And communication plays a vital role. Learning and remembering hand signs is not easy because of the above major issue, there is a huge communication gap present between mute/deaf persons with normal persons. To avoid the misleading interpretation of communication is being improved by this proposed system. The above problem is giving a serious impact on their lives, by clearing this problem the object can be involved freely environment and express the communication. The given proposed system is to solve the above communication problem, by evaluating the pre-defined dataset of signs images.

Keywords: Real-Time Detection, Hand Signs Detection, Image Processing, Object Detection, American Sign Language.

Abstract: Nowadays, due to users critically reviewing the restaurant and related services, there is an abundance of the reviews that are available on the internet. There is an opportunity to get more detailed information from the customer’s review using sentiment analysis. Certain steps are taken to conduct this sentiment analysis. Implementing a machine learning based approach for sentiment analysis increases the performance and accuracy of the sentiment analysis task, as compared to the lexicon based approach. The accuracy achieved for the chosen dataset was between 75% to 80% and it can be increased furthermore with some changes to the process. The model is trained using domain specific data, so it performs better than a lexicon based approach.

Keywords: Sentiment analysis, Data mining, ML, NLP, SVM

Abstract: The amount of computing resources required by current and future data-intensive applications is increasing dramatically, creating high demands for cloud resources. We provide a method in cloud to analyze the resource requirements for the tasks and allocate those resources at right time. In addition, it ensures a stable cloud structure and rapid resource allocation. In the proposed system, the tasks are classified based on its size. The resources are allocated for parallel completion of those by VMs. It uses KNN and Naive Bayes algorithm for task clustering and resource allocation respectively. It is simple to implement, improves flexibility and reduces resource allocation time.

Keywords: Cloud computing, resource demands, KNN(K Nearest Neighbor) and NB(Naive Bayes) algorithms, prediction accuracy, physical machine(PM), virtual machine(VM).

Abstract: One may surmise the current century as the changing face in world innovation, which is additionally affecting an extraordinary arrangement to eatery proprietors arranged by the use of imaginative and tweaked advances. This Paper center around android based tablet and Smartphone applications, that are seriously less expensive and more client cordial rather than crude PDS-based requesting framework. At client end, it comprises of a Smartphone or tablet having menu subtleties. A typical Wi-Fi associates both kitchen show and the client end tablet, client arranges straightforwardly reaches to kitchen end module. This interface plan improves proficiency of eateries and furthermore significantly save time and killing human blunders and furthermore works with client criticisms, with the input of the client; proprietor can improve the nature of administration. In remote menu card client can make installment without remaining in the line. Utilizing this component client can take care of the bill via seating on the saved table.

Keywords: Touchscreen, Restaurants, Wi-Fi modules, Smartphones, etc.

Abstract: In the modern world of digitalization, processing of data in real time requires an increase in the operating speed of a system. In digital epoch, the thirst for high speed is fulfilled by the accomplishment of digital multipliers. Multipliers play a fundamental role in many high-speed applications where the complex multiplications are carried out by squaring operations. Vedic Mathematics is a part of Atharva Veda which deals with the easiest methodology for all types of arithmetic calculations. Dvanda Yoga is one of the squaring algorithms of Vedic Mathematics. In this project, the design is simulated and realized with the help of Xilinx 9.2i.

Keywords: Multiplication, Squaring Architecture,Vedic mathematics, Xilinx 9.2i.

Abstract: Coronavirus disease 2019 (COVID-19) is a contagious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The first case was identified in Wuhan, China, in December 2019. The disease has since spread worldwide, leading to an ongoing pandemic. We know that at this moment almost 80 % users in India had smartphones so if they get any medium to see the cases it becomes informative for them also, because of this we came to design and develop web application ”Covid-19 Tracker”. Along with it, our proposed application provides the contact details of on NGO’s, free food providers and essentials services. It will surely help people to survive in this global pandemic situation.

Keywords: disease, vendors, NGO.

Abstract: In the present reality Automatic structures are being preferred over manual system. With the snappy augmentation in the amount of customers of web over the earlier decade has made Internet an indispensable piece of life, and IoT is the latest and rising web development. Power is one of the basic necessities of individuals, which is usually utilized for homegrown, mechanical and agrarian purposes. SEM is an electric gadget having energy meter chip for estimating the electric energy devoured and a remote convention for information correspondence. This undertaking presents a brilliant energy meter for a programmed metering and charging framework. In this energy meter the force used the comparing sum will be ship off both the clients and power board utilizing android application and web application separately and conveyed to the controlling base station. An extra strategy measures and recommendations are incorporated to help providers in exploring, distinguishing and forestalling burglary. The whole framework is valuable for anticipation of burglaries and worldwide associated medium to picture the meter perusing to its clients adequately.

Keywords: IOT Module, Webpage Energy Meter, 4-channel Relay Module, Cloud.

Abstract: The extensive spread of pretend news can have a significant negative impact on individuals and society. it's brought down the authenticity of stories ecosystem because it is even more widely spread on social media than most well-liked authentic news. it's one in every of the largest problems which has the flexibility to vary opinions and influence decisions and interrupts the way during which people responds to real news. Most of the smart phone users choose to read the news via social media over internet. The news websites are publishing the news and supply the source of authentication. The question is the way to authenticate the news and articles which are circulated among social media like WhatsApp groups, Facebook Pages, Twitter and other micro blogs & social networking sites. It is very harmful for the society to believe on the rumors and pretend to be a news. the requirement of an hour is to prevent the rumors especially within the developing countries like India, and concentrate on the proper, authenticated news articles. This paper demonstrates a model and the methodology for fake news detection. With the help of Machine learning and tongue processing, it's tried to aggregate the news and later determine whether the news is real or fake using Passive Aggressive Classifier. The results of the proposed model is compared with existing models. The proposed model is functioning well and defining the correctness of results up to 93.6% of accuracy.

Keywords: Fake News, Impact, social media, Machine Learning, Passive Aggressive Classifier.

Abstract: Among brain tumors, gliomas are the most common and aggressive, leading to a very short life expectancy in their highest grade. Thus, treatment planning is a key stage to improve the quality of life of oncological patients. Magnetic Resonance Imaging (MRI) is a widely used imaging technique to assess these tumors, but the large amount of data produced by MRI prevents manual segmentation in a reasonable time, limiting the use of precise quantitative measurements in the clinical practice. So, automatic and reliable segmentation methods are required; however, the large spatial and structural variability among brain tumors make automatic segmentation a challenging problem. The use of small kernels allows designing a deeper architecture, besides having a positive effect against over fitting, given the fewer number of weights in the network. To investigated the use of intensity normalization as a pre-processing step, which though not common in CNN-based segmentation methods, proved together with data augmentation to be very effective for brain tumor segmentation in MRI images. In addition to this tumor length, width and exact location is detected accurately. An extensive experimental evaluation on benchmark data demonstrates the effectiveness and efficiency of our approach.

Keywords: Image Segmentation, Brain tumors, Magnetic Resonance Imaging, Convolutional Neural Networks, Tumor segmentation etc.

Abstract: Technology has played a vital role in health sector for past decades whether in detection of various diseases from early stage or in case of targeted treatment. In many Lung disease cases it's the same scenario the early stage detection of the diseases increases the survival rate of patient In this project the first step used in order to detect the lung disease based on unsupervised learning algorithm modelling is done by using LocNet and the optimized CNN is used for image dataset to compare. For the second step the images are differentiated based on whether lung tumor is either malignant or benign using supervised learning algorithm. In the project here two sets of images with data are considered to estimate the diseases where one set of data contains around 5,606 images whose size 1024 x 1024 pixel with height and width there are 15 classes and another set of data and images is the "full-dataset" that as 112,120 total images whose size 1024 x 1024 pixel with height and width.

Keywords: Optimized CNN, Supervised learning, unsupervised learning, Lung diseases

Abstract: To build the online news portal that will be helpful for all the people. The world is going to be more digital, and digitization is the need of every business, every Industry. Online News Sites play a vital role in educating and informing Mass with latest updates, current happenings around the globe. People don’t have much more time to read the Printed newspaper with yesterday’s happening, so they always follow web portals or Electronic Media for getting latest News. With Electronic media, there is a certain problem like Costing of On Air is higher, and everyone is not always in front of Television set, but they can access their mobile, social sites, Whatsapp, Facebook etc. so they will defiantly update them self very fast and less time consuming methods. Online News Website and social media can give the fastest news Updates. The online news portal has been developed to override the problems prevailing in the practicing manual system. This software is supported to eliminate and in some cases reduce the hand ships faced by this existing system. The Purpose of the project is to develop an online news portal and provides news for all viewers. All the news regarded to the category will be updated. User satisfaction related to portal will be fullfilled. Online news portal allows customers to read up to date news related to many fields like Entertainment, National, International, Business, Bollywood ,Hollywood, Politics, Sports, Education etc. Without any payment or login . User can also contact us to give suggestions and can also give us feedback related to our site . In this portal news are categories into different categories.

Keywords: News, Portal, Digital, User satisfaction, Electronic Media

Abstract: The conventional approaches to analyze the sentiment of text do not consider the relationship between words that show emotion and modifiers, they simply accumulate the words of the sentence to obtain the sentiment of short text. Along with sentiment analysis, the increasing amount of online information, and recourse texts, text summarization has also become an important subject with aims to preserve and show the main purpose of textual information. It is exceedingly difficult for human beings to manually summarize large documents of text. With this project, users would save a lot of time as well as conserve the resources which can be employed for better enterprises. The project would also sustain the bulk of the spam as well and give a brief of the complete information. It also helps to analyze the overall sentiment of the article and classifies it based on the data present.

Keywords: Sentiment recognition, text summarization, News classifier, Spam Check.

Abstract: In this age, the Internet has empowered the flow of thoughts and data and has thus expanded the knowledge base among individuals. Be that as it may, this has its own disadvantages in terms of false and fake data. The need to uncover such bogus data and disdain discourse during this COVID-19 pandemic has never been more important. Data mining is fundamentally used to identify relevant required data available on the internet or any data source. Consolidating the information mining using different methods like content mining, NLP and computational insight, we can arrange Corona virus tweets as great, awful or unbiased. The objective of this work is on the characterization of feelings of ‘Corona virus tweets' information assembled from Twitter. Moreover, we can characterize the Covid-19 Texts as phony or not. To improve characterization we are utilizing AI methods for improving the effectiveness and quality of the proposed approach.

Keywords: NLP, Naïve Bayes, Covid-19 data, Fake news detection, Sentiment Classification

Abstract: Humans share a universal and fundamental set of emotions which are exhibited through consistent facial expressions, talking and writing/texting. An algorithm that performs detection, extraction, and evaluation of these expressions will allow for automatic recognition of human emotion in images, voice and text. Presented here is a hybrid feature extraction and facial expression recognition method that utilizes Viola-Jones cascade object detectors using Haar cascades extract faces and facial features, pyttsx3 which is a text-to-speech conversion library in Python and text2emotion support vector machine to determine emotion from text.

Abstract: Human history is observing a very strange time fighting an invisible enemy; The novel COVID-19 coronavirus. COVID-19 is a specific disease caused by newly discovered coronavirus. Various journals are offering to freely publish the articles about coronavirus. So here in this short abstract we will discuss the website about COVID-19 that we will provide to all the internet users around.This website is specifically for those who are looking for information about symptoms, prevention or treatments. Some of the features that the website is mainly focused on are health information, safety and prevention tips. Also this website will show the people about the data & insights, resources to help, support relief effort and the latest news. The impact of pandemic COVID-19 is observed in every sector around the world. The education sectors of India as well as world are badly affected by this. It has enforced the world wide lock down creating very bad effect on the students' life. Around 32 crore learners stopped to move schools/colleges, all educational activities halted in India. The outbreak of COVID-19 has advised us that change is inevitable. It has worked as a catalyst for the educational institutions to grow and opt for platforms and techniques, which have not been used before. The education sector has been fighting to survive the crises with a different approach and digitising the challenges to wash away the threat of the pandemic. This paper highlights some measures taken by Govt. of India to provide seamless education in the country. Both the positive and negative impacts of COVID-19 are discussed and some fruitful suggestions are pointed to carry out educational activities during the pandemic situation

Keywords: COVID-19, pandemic, emerging infectious diseases, social distancing.

Abstract: The paper looks at the possibilities of using blockchain technology for charitable purposes. To ensure data protection, fund integrity, and donation control, problems in this field necessitate the introduction of new storage tools and the transfer of information between donors, foundations, donation recipients, and other charitable actors. Via assured data protection and the ability to monitor the movement of funds and transactions, using the blockchain would increase the interest of potential donors in charitable organisations. The authors of this article examine needs and emerging blockchain-based charity networks in Russia and around the world. They provide an example of how distributed registry systems can be used to create a forum for making and monitoring charitable donations. The authors collaborated with local funds and non-profits during their research to validate the solution, gain a deeper understanding of ecosystem needs, and share their findings in the report. Donors are suspicious of how their money is spent. Blockchain technology is currently being used in a variety of industries. You will use blockchain technology to make payments Transparency in the donation and fund-transfer process. It is necessary to create a single database for monitoring donations that will monitor all details about donations, transactions, and donors. The aim of this paper is to describe the implementation of a blockchain-based framework for monitoring donations. Centered on blockchain technology, the System provides open accounting of operations for donors, charitable foundations, and recipients. should provide a clear donation route, allowing public users and donors to track and control where, when, and to whom charity funds were distributed. Keyword— Charity Blockchain, Smart-contracts, Ethereum, Transparency

Abstract: Internet of Things (IoT) is a system of interrelated computing devices where all the things, including every physical object, can be connected - making those objects intelligent, programmable and capable of interacting with humans. As more and more data are generated each day, IoT and it's potential to transformhow we communicate with machines and each other can change the world. The user operates the smart home devices year in year out, have produced mass operation data, but these data have not been utilized well in the past. This project focuses on the development of home automation system based on internet of things which allows the user to automate all the devices and appliances of home and merge them to provide seamless control over every side of their home. The data can be used to predict the user’s behavior custom with the development of a machine learning algorithm, and then the prediction results can be employed to enhance the intelligence of a smart home system. The designed system not only gives the sensor data but also process it according to the requirement, for example switching on the light when it gets dark and it allows the user to control the household devices from anywhere. The cloud is used to send the sensor data through Wi-Fi module and then a decision tree is implemented which decides the output of the electronic devices also, it is used to achieve the power control and local data exchanging which provide the user interface, store all the information corresponding to the specific house, and query the function information of an individual home appliance.

Keywords: Embedded c, IoT, Cloud, Google Assistant,etc.

Abstract: In today’s era the advancement in artificial intelligence(AI),the automatic analysis of video interviews to apprehend individual personality traits has become a progressive area of research. Progress in computer vision and pattern recognition based on deep learning(DL) have guided to the foundation of convolutional neural network models that can effectively recognize human nonverbal cues and impute their personality traits with the usage of a camera. In this paper, an end-to-end AI interviewing system was developed using video of the interview fetched and CNN model to perform automatic personality recognition (APR) based on the features extracted from videos and the personality from the facial expressions and self reported questions. The AI interview agent can replace existing self-reported personality assessment methods that job seekers may control to achieve socially desirable effects.

Keywords: Big five, convolutional neural network (CNN), personality computing, TensorFlow, Deep learning.

Abstract: The term "digital campus construction research" refers to the creation of a campus in an infinite math space on the Internet. It is a digitalization of campus resources in the real world, allowing different resources to be integrated and generating an ecology. The virtual campus interacts powerfully with the physical campus, improving the efficiency of campus operations and promoting the university's long-term development. This paper introduces the study and creation of a virtual digital campus based on the web platform, using the wisdom campus system as an example. We begin by discussing the history of virtual digital campuses and the creation of wisdom campuses, before outlining the research. The system's design and development. Finally, we propose in our country, there are issues with the creation of digital campuses, and the corresponding solutions are presented.

Abstract: This Project is based on the idea of making an application which makes it easier for students who are struggling to comprehend derivatives and integration. The Application will be created by using JAVA, so that it remains platform independent.

Keywords: Mathematics, learning application, derivatives, integration.

Abstract: The majority applications of pollution monitoring systems are in industries. The control of the parameters which causes pollution and deteriorates the industrial and natural environment pattern is a great challenge and has received interest from industries especially in Paper making industries, Water treatment industries and Sugar manufacturing industries. The main objective of our project is to design an efficient and robust system to control the parameters causing pollution and to minimize the effect of these parameters without affecting the plant or natural environment. The proposed methodology is to model a system to read and monitor pollution parameters and to inform pollution control authorities when any of these factors goes higher than industry standards. A mechanism using IoT is introduced in this proposed methodology, which will automatically monitor when there is a disturbance affecting the system. The system investigates level of pH in industry effluents, level of CO2 gas released during industry process and temperature of the machineries. The through this project we try to prove that control of pollution can be computed and the data can be transferred online. Our proposed method is more accurate to derive the desired parameter Similarly, the response to industrial impacts is also highly variable. The main reason for the assessment of the quality of the industrial environment has been, traditionally, the need to verify whether the observed industrial quality is suitable for intended uses. The use of monitoring has also evolved to determine trends in the quality of the water, air and soil environment and how they are affected by the release of contaminants, other anthropogenic activities, and/or by waste treatment operation (impact monitoring).

Keywords: Internet of Thing,

Abstract: Custom T-shirt Designs is an online application. The reason for this project is to give a site that would permit clients to have the option to tweak T-shirt and submit a request of custom T-shirt. Clients can join, sign in, select T-shirt tone, add text, pick Font, pick Font tone, transfer an picture, apply channels to pictures, change text or pictures, pick T-shirt size and save plans for future references. Clients would have the option to add the plan to a truck, oversee truck and checkout with their charge card to buy for the request and view their past orders.

Keywords: Html 5, Css, Bootstrap, JavaScript, MYSQL

Abstract: Home automation is a modern technology that modifies our home to perform different sets of tasks automatically. It guarantees security, surveillance, automation of devices for the user to make their life more comfortable. In the proposed method, voice recognition and web app are used to control the functioning of electrical appliances like fans and lights. A small-scale prototype is also implemented for intrusion detection and web app using Raspberry pi. This method is integrated with a wireless home automation system and it sends email alerts to the respective user. Face recognition is done for the security features for the purpose of identifying the unauthorized person.

Keywords: Internet of things, Raspberry pi, Voice recognition, Web app.

Abstract: The main purpose of this paper is to build an automatic system for solar panels so, that the system will provide better alignment and a better cleaning mechanism. The proposed system will change the direction of the panels in a dual-axis to trace the sunlight with the help of sensors. This system helps to improve the tracking ability of the panel's inefficient way and cleaning of panels on a regular basis. The Dual-axis system has superiority over the single-axis solar tracker system.

Keywords: Photovoltaic Panels, Arduino Atmega, Light Dependent Resistor.

Abstract: Today’s modern world cardiovascular disease is the most lethal one. This disease attacks a person so instantly that it hardly gets any time to get treated with. So diagnosing patients correctly on timely basis is the most challenging task for the medical fraternity. A wrong diagnosis by the hospital leads to earn a bad name and loosing reputation. At the same time treatment of the said disease is quite high and not affordable by most of the patients particularly in India. The purpose of this paper is to develop a cost effective treatment using data mining technologies for facilitating data base decision support system. Almost all the hospitals use some hospital management system to manage healthcare in patients. Unfortunately most of the systems rarely use the huge clinical data where vital information is hidden. As these systems create huge amount of data in varied forms but this data is seldom visited and remain untapped. So, in this direction lots of efforts are required to make intelligent decisions. The diagnosis of this disease using different features or symptoms is a complex activity. In this paper using varied data mining technologies an attempt is made to assist in the diagnosis of the disease in question. Keyword : cardiovascular disease, data mining, intelligent decisions, symptom.

Keywords: Machine learning algorithm, Knn Classification, Heart disease prediction, Report generation.

Abstract: Quantum theory is one of the most fortunate theories that have influenced the course of scientific progress all through the 20th century. Quantum mechanics has given us the concept of quantum computers by using principles like superposition and quantum entanglement which seek to significantly boost the computational power and now it has become an evolution in classical computer science. We know that Current cryptography systems are based on the process called prime factoring which is vulnerable due to both significant enhancement in computational power and advancement in mathematics to reverse one way function like Shor’s algorithm. To solve this problem, we need to induce quantum physics in current cryptographic system which leads us to the topic “Quantum Cryptography” which works on the principle of “Quantum Key Distribution”. QKD is the scheme which allow the generation of shared private key, which can be used with a traditional encryption algorithm or as a one-time pad which encrypts each message for one time use key. But QKD only works if we can successfully transfer entangled quantum states or qubits over long distances perfectly intact, leading us to the concept of “Quantum Information Theory” or quantum internet. The scope of this paper covers concept of quantum computing, weaknesses of current cryptosystems, post quantum cryptographic system, fundamental concept of quantum cryptographic system and quantum information theory with challenges of implementing it in real world and its limitation and finally about upcoming future of transition of digital age to quantum age.

Keywords: Quantum Computers, Quantum Key Distribution, Quantum Information Theory, BB84 Protocol

Abstract: Accurate identification of patients remains not less than a headache in many countries in the sub-Saharan region. Still, correct patient identification remains a cornerstone of safe & high quality healthcare. A series of reasons explain the defective patient identification procedures in Sub-Saharan hospitals: a decentralized patient administration is often found in larger hospitals where the implementation of a certain level of financial and managerial autonomy of clinical departments has promoted the multiplication of duplicate administrative patient management systems (every department wanting to take care of it’s own bookkeeping). As a result, patients end up with multiple department specific medical records and ID numbers. Added to this, the absence of a master patient index (MPI) is a general rule: no central patient identification systems are in place that refer to existing departmental patient records. Key Words: patients, healthcare, master patient index (MPI)

Abstract: The technological advancements to be depicted in the course called emerging trends was a challenging task and therefore it was decided to prepare a learning material with the involvement of industrial and academic experts for its uniformity in the aspect of delivery, implementation and evaluation.

Keywords: AI, Machine Learning, Deep Learning, IOT.

Abstract: Defence of the Ancients 2 (DOTA2) is a well-known multiplayer Action RTS game developed by Valve Software Corporation. It is well known among lots of children and even among mature audiences. The rules and regulations of this game are well-known in the eSports scene. This case study is meant for implementing a different fast-paced version of this game without losing its attraction. This game comes with a multiplayer mode. Path of Valor is an easy game for all. The graphics of the game system is good and smooth to control for the users. Talking approximately the gameplay of the system, the game has a simple character that has few skills sets and the users are supposed to use those skills to obtain kills on the enemies. In Arena of Valor, the player has to use their motor and analytical skills to kill the enemy units. The game requires the players to use spells using the keyboard and manage the movement of their units using mouse clicks. It is a 5v5 multiplayer game and the victor is decided based on which team reaches a targeted number of kills first in the game. This game has a simple aim to provide a fun time to the players and allow them to refine their reaction time in the game.

Keywords: Real Time Strategy, eSports, Game Graphics, Multiplayer

Abstract: Now every day the usage of credit cards has dramatically inflated. As master card becomes the foremost well-liked mode of payment for every on-line still as regular purchase, cases of fraud associated with it square measure are rising that there are several possibilities for used of our account by unauthorized person / Hackers therefore the knowledge in your account could loss and client could suffer through loss of cash, for these reason System detects unauthorized person by giving the security at client registration level by implementing system unauthorized person will access the account details or if it’s attempt to access then account are getting to be block.

Keywords: Global data, Credit card, Genetic Algorithm, Electronic commerce, fraud detection.

Abstract: IOT-Internet of things, Internet being the ecosystem for physically connected devices, works with no human intervention for exchanging the data. “Smart Cradle”, an automatic cradle, a venture designed especially for those moms who are excessively busy and occupied with work. This system considers all the minute details required for the care & protection of the Baby in the cradle. The design of smartness & innovation comes with the use of technologies/methodologies which include Internet of Things, Cry Detecting Mechanism, Cloud Computing & User Friendly Web application. In order to detect each & every activity of Baby, different Sensors/Modules are attached to the Cradle. Humidity & Temperature Sensing Module for detection of Wetness of the bed, Cry Detection Circuit to analyze Cry Patterns. The data which is been taken from the sensors will be stored in Cloud& analyzed at regular intervals. A Health Algorithm is applied to these datasets to get information about the body conditions which is helpful as any regular symptoms of a disease can be identified easily.

Keywords: Baby monitoring, Smart cradle, Internet of Things, Sensors.

Abstract: For past few years, there have been several an accident of children falling into an abandon bore-well which is left uncovered and get trapped. These bore-wells in turn have many innocent lives. In addition to this an ultrasonic sensor. In order to determine the feasibility of the system a prototype was designed and fabricated. The prototype consists of all mechanical and electronics set up as discussed above but in miniature version. The prototype has a control module which consists of LCD display, motor driver IC, Nodemcu inbuilt micro controller with wi-fi module, control switches, buttons and power supply unit. Present scenario there have been several incidents reported on abandoned bore-wells which are turning in to death wells. Many innocent children are being trapped into these bore-wells and losing their lives. The actual purpose of bore-wells is to save lives, but these bore-wells in turn have started taking many innocent lives. Usually these rescue operations are very lengthy, complicated and very time taking processes. This paper presents a simple and effective method to rescue the child from the bore-well. This is the main electronic unit which controls and co-ordinates the whole systems operation. The project is intended to reduce the risk involved during the child rescues operation by analyzing the simulation.

Keywords: Bore-well, IOT, Child rescue.

Abstract: In this paper we propose a Go-Kart Management System. This system which is based on Go-Kart event management and provide the functionality through the system. This system allow user to register into the system and registered user allow to login to the system. This web based application introduce to organize the activities regarding go-karts event like participation in Go-Kart, building electric or general go-karts, team activity, performance, etc. Through system, user can allow to participate in ongoing race event or proposing the Go-Kart Vehicle Design. The database stores all of the user's information as well as their communications.

Keywords: User, Admin, Event, Chatterbot, Conversational Dialog Engine Chatbot.

Abstract: Google Tag Manager (GTM) is very important thing in the Digital Marketing world. Google Tag Manager (GTM) is a free tool that lets in you manipulate and deploy advertising tags on your website or Mobile app without having to modify the code. It provides unique solution to a product marketers, analysts, and developers. Manage all your website tags without modifying code. GTM has made the manner of handling analytics and marketing tags less complicated than ever earlier than. GTM can provide easy, reliable, without difficulty included tag management solutions— free of charge.

Keywords: Google Tag Manager, GTM, Google Analytics.

Abstract: This project addresses a cost-effective, flexible solution of underground mine workers’ safety. A module of MEMS and temperature-based sensors are used for underground environment monitoring and automating progression of measurement data through IOT communication technique is proposed with high accuracy, smooth control and reliability. Arduino microcontroller is used for collecting data and making decision, based on which the mine worker is informed through server. Sensor data transforms into digital signal and effectively communicate wirelessly with the ground control centre computer

Keywords: Temperature Sensor, Micro Controller, IoT.

Abstract: According to the World Health Organisation (WHO), 285 million people are estimated to be visually impaired worldwide among which 90% live in developing, countries and 45 million blind individuals worldwide. though there are many existing solutions to the problem of assisting an individual who is blind to read our solution bring out a smart and autonomous system that assists by reading out the page and provides a page-turning mechanism and interactive query session for them The system is developed in such a way that the user has to do is place a book in the system and the system does all the remaining tasks like reading out the text, turning the page after the text on the present page has been done reading. The system also helps the user understand the meaning of any word which he or she may not have understood completely with the help of a dictionary query feature where the user interrupts the system and asks the meaning of the world. The user can also pause or end the reading according to his or her wish. This is done by the press of the required buttons.

Keywords: Raspberry Pi, Dictionary Query, Buttons, Turning.

Abstract: In this paper survey of different signal processing algorithms for detection of live human behind the wall or barrier is discussed. For all life detection systems, it is difficult to detect the weak life signals from strong echo waves of background noise. The detection signals due to respiratory movement are always weak so that they are easy to be buried by noise, which will increase detection difficulty and even reduce the detection accuracy. Many clutters and noises of system influence seriously. For proper detection of life signals behind wall or barrier, system performance is most important. The performance of system mainly depends upon signal processing algorithm or technique.

Keywords: Life Detection, Signal Processing, Radar Echo, Clutter.

Abstract: Patients diagnosed with diabetes mellitus must monitor their blood glucose levels in order to control the glycaemia. Consequently, they must perform a capillary test at least three times per day and, besides that, a laboratory test once or twice per month. Diabetes is an incurable disorder which produces various problems related to the body. It is a fast-growing disorder, about 500 million people in the world and 50 million people in India are the victims of diabetes. All problems related to diabetes can be reduced through physical exercise, proper and balanced diet, and medication. The current invasive technique which is painful and inconvenient because people have to prick their finger to draw the blood for the measurement of glucose concentration in the blood on a daily basis so it is not recommended for a lifetime. People living in villages do not have facilities to check their blood sugar level regularly because of unavailability of glucose measurement devices and procedural cost. To overcome the difficulties caused by invasive method we are using non-invasive method in our project. In this project we are displaying the glucose value on LCD and this data can be stored in database, and also this data sent to the doctors through web/android application so that patient can get early medications and they can take precautions.

Keywords: IoT, Raspberry Pi, Health Care, Non-Invasive Glucose level Monitoring.

Abstract: Health Care System is a web application developed for hospitals to manage staff data and patient's data effectively. A Chatbot is software that authorize you through start a conversation between the user and the system. It is AI based software that can be set up as web applications. Normally users don’t know about the whole symptoms of a particular disease. Chatbot is question answering system that uses NLP. Chatbots are making a mark in the stream of medicine and provide an actual method to handle patients of medical organizations. Medical chatbots can conduct one-on-one conversations with patients and evaluate each patient’s individual requests. Project’s goal is to analyze the existing e healthcare system that involves a novel human – machine interaction and proposes an alternative system: A Chat Interface that is designed and instructed to react and interact with patients as a human being. Also, the Patient can book an appointment with the physician.

Keywords: AI (Artificial Intelligence), Disease Prediction, Health Tips, Doctor’s Appointment, Chatbot, Healthcare.

Abstract: Attendance is a ritual followed in every class every day. In the present academic system, regular class attendance of students’ plays a significant role in performance assessment and quality monitoring. The conventional methods practiced in most of the institutions are by calling names or signing on papers, which is highly time-consuming and insecure. The management of the attendance can be a great burden on the teachers if it is done by hand. With the advent of technology the manual attendance system can be applied with help of computer vision. Computer vision plays a major part in recognizing facial parts of students for putting up automated attendance without use of paper and pen. This attendance is managed properly and for long-time with help of automation. The attendance can be accessed by teachers, students and parents from anywhere anytime. Image Processing with deep learning is applied to easier assessment of attendance which is time-consuming and cost saving. The System has add-on function of temperature check and Hand sanitization to deal to covid situation.

Keywords: Face recognition, Face detection, Naive-Bayes, Machine Learning.

Abstract: Kidney is consisted of four different structures with different functions. That is renal cortex, renal column, renal medulla and renal pelvis. Different kidney diseases affect different part of kidney. For example, kidney tumor usually occurs in renal cortex, renal column hypertrophy may exist in renal column, medullar cystic kidney disease usually exists in renal medulla, and transitional cell cancer, renal pelvis and ureter cancer may attack renal pelvis. To proposed a fast fully automatic method for kidney components segmentation. The proposed method consists of two main parts: localization of renal cortex and segmentation of kidney components. In the localization phase, a fast localization method which effectively combines 3D GHT and 3D AAM is proposed, which utilizes the global shape and texture information. In the segmentation phase, a modified RF method and a cortex thickness model are proposed to efficiently accomplish the multi-structure segmentation task. Finally obtain the diseases in kidney.

Keywords: Renal Column, Renal Medulla, Renal Pelvis, Generalized Hough Transform, Kidney, Renal Cortex, Active Appearance Models, Random Forests..

Abstract: Malaria is a very extreme infectious disease caused by the genus Plasmodium peripheral blood parasite. Occasionally, traditional microscopy, which is now "the gold standard" for the diagnosis of malaria, has proven ineffective as it requires time and findings are difficult to replicate. Automation of the assessment process is of high significance because it presents a significant global health concern. In this work, an accurate, quick and affordable malaria diagnosis model was established using stained thin blood smear images. A collection of intensity-based features was suggested and the performance of these features was assessed using an neural network classifier on the red blood cell samples from the generated database.

Keywords: malaria disease, pre-processing, classifier algorithm, feature extraction, Convolutional Neural Network (CNN) etc.

Abstract: The traditional way of generating time table is very time consuming and ends up clashing either with same labs, classes, etc. The main motive of this project is to help the staff to generate time table with minimum efforts using some automated tools. As per requirements, teachers can enter the data in this tool and plan the class wise lectures. The project generates three different time tables; student’s class wise lectures, Lab time table and teacher’s personal time table. The output of this tool can be accessed by the students of the class and the output can also be generated in the pdf format.

Keywords: “Module”, “Interface”, “Database”, “Trends”, “Clashing”, “Customization”.

Abstract: Smart Street Lamp System uses IOT hence they are fully automated. In most of the states in India, Street Light system are controlled manually. In our proposed project the condition for street lamps is determined by surrounding light conditions. Using surrounding conditions, it is determined whether the street lamp should be powered ON or OFF. The primary objective of Smart Street Lamp System is to preserve the amount of energy that is being consumed by the traditional street lamps. When the IoT based Smart Street Light system is in well-lit environment it adjusts the lamps to shut down automatically, and power them ON when it detects less lightning conditions. The light intensity is adjusted by the environment to match the conditions. The energy is also conserved at night time also. As our project will be using IR sensor, which will detect movement of any objects or cars or vehicles in the surrounding, then the system will allow the lamps to glow more than usual. The intensity will be increased automatically by detecting the environmental conditions such as peoples, cars, animals, etc. When no one will be around at night, the LED lamps will glow in dim light Thus, the energy is conserved and it does not distribute the energy where it is not needed.

Keywords: IR sensor, LDR Sensor, LED Bulbs, Arduino kit. IoT

Abstract: Currency Converter System Android App is mainly developed for the user to get the live currency status of all the country’s currencies exchange in one app. The main aim of this application is to provide a web-based interface for exchanging money from one currency (say $) to another currency (say Rs). The application is developed to represent dynamic functionality as that of currency converter. This Android app helps the user to know about the currency value update regularly with advanced features and functionality. Major functions and features have been integrated to enhance the performance of the app to give better results for the users. Currency Converter Android App Source Code gives accurate corresponding exchange result value in their user hand by utilizing online information sources. It is used in knowing the currency value of different countries and make available to common people quickly and easily. They can utilize anywhere and at any time. It helps travelers who are travelling across the borders. It can be further developed by including more currency option and by showing currency value table and a graphical representation for delivering exact information to the users

Keywords: Java, Currency Converter Android App Source Code.

Abstract: In more recent times, there has been an increase in the number of people using computers, as a result of which there is widespread use of the Internet. The use of the Internet enables hackers to access computers using new, more sophisticated, and more complex forms of attacks, to protect computers from them Intrusion Detection System (IDS) is employed, which has been trained using a number of machine learning techniques as well as datasets. In some networks, the datasets used are acquired over time and usually contain up-to-date data. Furthermore, they are imbalanced and unable to store enough data to withstand all types of attacks. The efficiency of current IDSs is harmed by these inconsistencies and out dated datasets, especially for attacks that are infrequently encountered. We propose a machine learning-based IDSs in this paper, using K-Nearest Neighbour, Decision-Tree, SVM, LSTM, and SMOTE algorithms. To make IDS more logical, an up-to-date security database, CSE-CIC-IDS2018, can be used in place of older and more widely used datasets. The selected database is also not balanced. As a result, utilizing a data model known as the Synthetic Minority Oversampling technique (SMOTE), the rate of inequality in the dataset is lowered to improve the reliability of the system and to avoid inconsistent access and false alarms, a mechanism based on the types of attacks was developed. Data is processed in small classes, and their numbers grow to medium data size in this fashion. The proposed strategy considerably boosts the detection rate of attacks that are infrequently encountered, according to experimental results.

Keywords: IDS, intrusion detection, SVM, LSTM, SMOTE, machine-learning, CSE-CIC-IDS2018.

Abstract: Drowsiness detection has many implications including reducing roads traffic accidents importance. Using image processing techniques is amongst the new and reliable methods in sleepy face. The present pilot study was done to investigate sleepiness and providing images of drivers' face, employing virtual-reality driving simulator. In order to detecting level of sleepiness according to the signal, information related to 25 drivers was recorded with imaging rate of 10 fps. Moreover, on average 3000 frames was analysed for each driver. The frames were investigated by transforming in grey scale space and based on the Cascade and Viola & Jones techniques and the images characteristics were extracted using Binary and Histogram methods. The MPL neural network was applied for analysing data.70% of information related to each driver were inserted to the network of which 15% for test and 15% for validation. In the last stage the accuracy of 93% of the outputs were evaluated. The intelligent detection and usage of various criteria in long-term time frame are of the advantages of the present study, comparing to other researches. This is helpful in early detection of sleepiness and prevents the irrecoverable losses by alarming.

Keywords: Drowsiness, Driving, Image Processing.

Abstract: Pattern lock has been widely used in smartphones as a simple and effective authentication mechanism, which however is shown to be vulnerable to various attacks. In this paper, we design a novel authentication system for more secure pattern unlocking on smartphones. This project is written in J-script and click are automatically recognized by the code and no external configurations are required. Android pattern lock is still popularly used for mobile user authentication. Unfortunately, however, many concerns have been raised regarding its security and usability. User-created patterns tend to be simply structured or reduced to a small set. Complex patterns are hard to memorize. Input patterns are susceptible to various attacks, such as guessing attacks, smudge attacks, and shoulder surfing attacks. Our basic idea starts from turning the lock pattern into public knowledge rather than a secret and leveraging touch dynamics. Users do not need to create their own lock patterns or memorize them. Instead, our system shows a public pattern along with guidance on how to draw it. All the user needs to do for authentication is to draw the pattern as shown. For adversaries, the above-mentioned attacks are rendered useless by this new mechanism. Specifically, we study how to generate the public patterns and how to perform authentication. You have probably seen this on a touchscreen smartphone you have 9 dots and you have to draw a pattern. It works great: drawing a shape on a small touch screen is far easier than typing on those small keyboards AND far easier to remember too. Once you've got used to it, typing passwords in general gets pretty annoying A proof of concept project illustrating the use of the Android Pattern Lock Screen inside a HTML

Keywords: “J-script”, “Android”, “Smartphone”, “HTML”, “Pattern Lock”, “9 dots”.

Abstract: Music is an important entertainment medium. With the advancement of technology, the optimization of manual work has gained a lot of attention. Currently, many traditional music players require songs to be manually selected and organized. Users need to create and update a play-list for every mood, which is time-consuming. Some of the music players have advanced features like providing lyrics and recommending similar songs supported the singer or genre. Although some of these features are enjoyable for the user, there is room to improve in the field of automation when it comes to music players. Selecting songs automatically and organizing these supported the user’s mood gives user’s a far better experience. This can be accomplished through the system reacting to the user’s emotion, saving time that might are spent entering information manually. Emotions are often expressed through gestures, speech, facial expressions, etc. For the system to understand a user’s mood, we use facial expressions. Using the mobile device’s camera, we will capture the user’s countenance.

Keywords: Music, Emotions, Music Players, Users, Songs.

Abstract: Due to the development of information technology, every enterprise has a lot of data which magnifies the difficulties of selecting the most relevant. Hence, appears the error of measuring too many things. Owning an excessive amount of information will cause to vagueness, the other effect of a measuring system. This phenomenon does not depend on the manager’s ability to compute and communicate, but rather on the ability to provide adequate information, to make good decisions, and to compare results with the planned objectives. These are often done through an interface – Dashboard, which may be a tool that permits the alignment of business processes and methods implementation. Dashboards are quite a set of indicators and graphics, they're found in several forms and interfaces. Dashboards answer to several questions of the organization and are addressed to various types of audience. Once an enterprise has identified a requirement for dashboard, managers must undergo the method of defining what they are going to include in their dashboard. In the case study is created a dashboard for sales analysis of an enterprise, using Power BI.

Keywords: Dashboard, Data visualization, Power BI, MySQL, Business Intelligence.

Abstract: The aim of the project is to introduce customers to various amenities and attractions in the hospitality and tourism industry, enticing them to stay at certain hotels or visit specific locations. In order, for any business to succeed, marketing is essential. Hotels and other related businesses have become increasingly interested in augmented reality in recent years, because it allows them to improve the physical environment that they are selling (such as their hotel and rooms), or to improve the experience of exploring the surrounding area. In addition to the fact that guests tend to ask for a lot of information, both when they arrive and when they leave, AR is a key reason for its flourishing in the hotel industry. Through augmented reality, Customers can have access to a lot of this information anytime and anywhere, improving their experience. Innovation in augmented reality additionally impacts the way people discover and engage with nearby attractions, cultures, and adventures.

Keywords: Augmented Reality, E-marketing, Virtual Environment, A 3D view, Mobile Technology, Customer.

Keywords: Co-extracting algorithm, co-extracting model, opinion targets, Opinion Relation Graph, opinion words, Topical Word Trigger Model.

Abstract: Many people who have private vehicles do not use their vehicles at all times so that over time the vehicles become poorly maintained and eventually damaged. Online Rental Application is here to help private vehicle owners to maximize the use of their personal vehicles while helping private vehicle owners to earn extra income. The purpose of writing is to develop applications that allow users to choose the vehicle according to their needs and to process the rental of vehicles both motorbikes and cars. The development method used is the waterfall method which consists of communication, planning, modelling, construction, deployment. The results are evaluated with 8 golden rules of interface design and the results of the questionnaire show that the application can be used by users and providers to make the process of renting and renting a vehicle. It was concluded that this application can be used well and can carry out the process of renting and renting vehicles for cars and motorbikes.

Keywords: Marketplace, Mobile Application, Private Vehicle, Rental Online.

Abstract: This paper is a report of a review on Sentiment Analysis for classification of Opinions on social Networking sites that explored the methods, social media platform used and its application. . In this a generic deep learning framework for predictive analytics utilizing both structured and unstructured data will be presented. The social media, blogs, forums, e-commerce web sites, and so on encourages people to share their opinion, emotions and feelings publicly. Today these Internet Sites are very popular and this resulted a huge amount of raw data that has been uploaded by users in the form of text, photos, audio and videos. People’s sentiments and experiences are very valuable information in decision making process of any business but to get benefit from these opinion and experiences, the accumulated content should be extracted and analysed properly. This can be done by using sentiment analysis. A systematic review of studies published between 2015-2020 was undertaken using the following trusted and credible database including IEEE Xplore, ACM, Emerald Insight, Science Direct and Scopus. After the initial and in-depth screening of paper, 24 out of 85 articles have been chosen from the review process. The articles have been reviewed based on the aim and objectives of the study. The result shows most of the articles applied opinion-lexicon method to analyses text sentiment in social media, extracted data on microblogging site mainly Twitter and sentiment analysis application can be seen in world events, as improving quality and strategy in business, Market Research, Decision Making, political forecasting an election result, monitor disease outbreak, create awareness on the importance of data security, perception towards a particular spot, and improve locate and response to the disaster.

Keywords: Opinion, Sentiment, Machine learning (ML), Natural Language Processing (NLP), Social media.

Abstract: MANET (Mobile Ad hoc Network) is a collection of two or more devices to form a communication network. There are various types of MANET routing protocols for different purposes. In this paper we had implemented AODV (Ad hoc on demand distance vector) and some other routing protocols. comparative analysis of these protocols has done. To find out which one is faster and effective compare to other. All this implementation has done in ubuntu using NS3 simulator.

Keywords: MANET, AODV, NS3, DSR, AD-HOC.

Abstract: Driver in-alertness is an important cause for most accident related to the vehicles crashes. Driver fatigue resulting from sleep deprivation or sleep disorders is an important factor in the increasing number of the accidents on today’s roads. Drowsy driver warning system can form the basis of the system to possibly reduce the accidents related to driver’s drowsiness. The purpose of such a system is to perform detection of driver fatigue. By placing the camera inside the car, we can monitor the face of the driver and look for the eye-movements which indicate that the driver is no longer in condition to driver is no longer in condition to drive. In such a case, a warning signal should be issued. This paper describes how to find and track the eyes. We also describe a method that can determine if the eyes are open or closed. The main criterion of this system is that it must be highly non-intrusive and it should start when the ignition is turned on without having at the driver initiate the system. Nor should the driver be responsible for providing any feedback to the system. The system must also operate regardless of the texture and the color of the face. It must also be able to handle diverse condition such as changes in light, shadows, reflections etc. In given paper a drowsy driver warning system using image processing as well as accelerometer is proposed. Key words: Drowsy, system, fatigue, template matching

Abstract: Recently, the outbreak of Corona virus Disease (COVID-19) has spread rapidly across the world and thus social distancing has become one of mandatory preventive measures to avoid physical contact. This survey paper emphasizes on a surveillance method which uses Open-CV, Computer vision and Deep learning to keep a track on the pedestrians and avoid overcrowding. The implementation can be done using closed circuit television (CCTV) and Drones where the camera will detect the crowd with the help of object detection and compute the distance between them. The Euclidean distance between two people will be calculated in pixels and is compared with given standard distance and if it is observed to be less than the standard distance the local authorities or local police authorities will be notified.

Keywords: Covid-19,Monitoring,Social Distancing,OPEN CV

Abstract: Breast cancer is the most common malignancy in women. It is often characterized by lack of early symptoms, which results in late detection of the disease. Breast cancer can occur in both men and women. It is projected that there will be rise in new cancer cases and cancer deaths in the United States. The early diagnosis of breast cancer can increase the survival rate, as it can promote timely clinical treatment to the affected patients. The mammography is the most common method for diagnosis through which we can have knowledge of abnormalities from the input image. This paper covers image processing based analysis of mammographic image. Firstly the image is converted from 3D to 2D array. Then the image is binaries twice, first to identify breast tissue and second to identify cancer affected region. Considering region of interest that indicates affected pixels and normal pixels the percentage of disease affected areas is calculated.

Keywords: Breast cancer, Mammogram, segmentation, thresholding, Binarization, ROI, python 3.

Abstract: We propose a low-cost internet of things (IoT)-enabled COVID-19 standard operating procedure (SOP) compliance system that counts the number of people entering and leaving a vicinity, ensures physical distancing, monitors body temperature and warns attendees and managers of violations. The system comprises of multiple sensor nodes communicating with a centralized server. The data stored on the server can be used for compliance auditing, real-time monitoring, and planning purposes. The system does not record the personal information of attendees nor provide contact tracing information.

Keywords: IoT; compliance monitoring; coronavirus; pandemic; COVID-19; internet of things; IoT applications; smart sensor; crowd counting; COVID compliance; social distancing

Abstract: This paper presents an e-Guide application for supporting information in schools and colleges.The application recommends the new visitor to the school or college campus.Generally This project is used to provide a detailed information about each and every lab of any department without need of any person.it is developed using Raspberry Pi 3 B+.This type of applications for mobile phones are distinct from other domain in respect of the type of content to be provided,the way this content is made available to the user and the way these types of application are developed.

Keywords: Smart Guide,Raspberry Pi 3 B+,Python

Abstract: Usable security has interesting usable difficulties in light of the fact that the requirement for security regularly implies that standard human-computer communication approaches can't be effectively legitimately connected. A vital convenience objective for validation frameworks is to help clients in choosing better passwords. Clients frequently make paramount passwords that are simple for aggressors to figure, yet solid framework doled out passwords are troublesome for clients to recollect. So analysts of current days have gone for elective strategies wherein graphical picture are utilized as passwords. Graphical passwords basically use pictures or portrayal of pictures as passwords. A human mind is great in recalling pictures than printed character. There are different graphical password plans or graphical password programming in the market. Notwithstanding, next to no exploration has been done to break down the graphical password that is as yet juvenile. In this paper, Users click on a point for every picture for a grouping of pictures. So it becomes easy and interesting at for client. That is Cued Click Point algorithm. Client can login into any application or system by using our graphical password system.

Keywords: Cued Click Point (CCP), Tkinter, Authrntication, GUI.

Abstract: The only way speech and hearing-impaired people can communicate is by using the sign language. The main problem with this kind of communication is that the non-impaired people, who cannot understand the sign language, would not be able to communicate with these people or vice versa. This thesis is about intentionally researching a algorithm which can to allow deaf and dumb communities to communicate effectively. Thus, this study is also aimed to extract features from finger and hand motions. This paper shows the American sign language which recognizes 26 hand gestures. The system contains four modules such as: pre-processing and hand segmentation, feature extraction, sign recognition, and sign to text and audio. The project uses an image processing system to identify, especially English alphabetic sign language, and convert it into text. The proposed model takes image sequences and extracts temporal and spatial features from them. We then use a CNN (Convolution Neural Network) for recognizing spatial features.

Keywords: Convolution Neural Networks (CNN), Machine learning, Sign Recognition, Rectified Linear Unit (ReLU)

Abstract: A block chain is a developing listing of facts, known as blocks which might be related using cryptography. Each block incorporates a cryptography hash of the previous block, a timestamp, and transaction data. With the aid of design, a Blockchain is resistant to change of the information. On this we suggest a machine to say budget allotted to the government as they tour via the authorities method at every degree. This device makes use of block chain era to maintain the transparency and protection at every degree as the fund go with the flow in advance. This gadget lets in to hold the crystal smooth document with all customers who are connected inside the chain to transaction the facts on a want to understand basis. The machine makes use of encryption to at ease transactional data the use of hash values to hold a block of transactions in a chain manner that is maintained and confirmed by using every node involved to verify the Transaction and hold the statistics in obvious shape in the authorities. The utility allows for a whole proof, secure and authentic fund allocation and fund monitoring utility help to form an incorruptible authorities process.

Keywords: Blockchain, security, transparency, encryption, government funds, cryptography

Abstract: An e-study platform that consists of a user login for upload and download purposes. The project is beneficial for students, various learners looking for the platform for study with the ease of availability of the study materials like notes, books, question papers and other things in the form of pdf, docx and pptx formats which will help the learners enhance their knowledge level and better understandings. The E-Study Platform allows the students/users to create their profiles and download all the required materials not including any payment requirements onto the system. The platform also consists of a facility for the user login where various registered users can upload their own notes, books and question papers etc. for the other students, users or learners so that the concept of “Sharing Is Caring” can be made true. The software system allows students, users or learners to view a list of study materials that have been uploaded for others. The admin has overall rights over the system and can moderate and delete any materials not pertaining to the platform’s dignity and rules. The system handles uploaders as well as downloaders to upload and download any data and efficiently displays all the data at the whole database panel. As we have faced the biggest issues of lacking of study materials due to COVID19 Pandemic. So, this project focuses on the provision of the study materials in such a critical time when all the book shops and stores were closed or in normal time. This platform is highly useful, especially for student and selfstudying learners. This platform is being made considering many problems and can be accessible from anywhere at any time for free of cost. The main objective of the project on E-Study Platform is to manage the database of study materials of students as well as any learners of any age of various courses, colleges and institutes for the ease of availability of the study materials.

Keywords: E-Study Platform, study materials, online materials reading, online platform, online study, e-study, pandemic time study solution, COVID19 study platform.

Abstract: COVID-19 disease caused by a severe respiratory syndrome coronavirus. It was identified in December 2019 in Wuhan city, China. It’s resulted in an ongoing pandemic that caused infected cases including many deaths. The rampant coronavirus disease 2019 (COVID-19) has brought global crisis with its deadly spread to several countries. Due to large population and lesser availability of vaccines, to maintain social distancing is that the only one feasible approach to fight against this pandemic situation. To implement Social distancing, group activities such as functions, social gatherings, travelling, workshops and even praying of people are banned by government during quarantine period. Social distancing, also called physical distancing is the only effective measures taken to prevent the spread of contagious disease by maintaining physical distance between people and reducing the number of times people acquire close contact with one another. Today`s unfortunate circumstances due of spread COVID-19, keeping distance among people is crucial. The goal is to detect people using Haar cascade classifier and find the space between people to check whether a norm social distance of 50 inch is maintained by people. Hence, this work aims at minimizing the spread of the COVID-19 virus by evaluating if and the way persons go with social distancing rules.

Keywords: Covid-19, Social distancing, Python, OpenCV, Deep neural network.

Abstract: Heart disease is a common problem that can be very serious in the elderly and also in individuals who do not have a healthy lifestyle. In addition to maintaining a decent eating habit, it can prevent it to some extent with periodic check-up and diagnosis. Hospitals produce a large amount of patient data, such as heart pain results, chest pain results, personal health records (PHRs), etc. Based on the symptoms, which are explicitly the attributes needed for prediction, the decision tree classifier is implemented. Using the decision tree algorithm, we will be able to classify certain attributes which are the best ones that will lead us to a better prediction of the datasets. The data that is generated from the hospitals are not used effectively. Some of these tools are used to extract data from the heart disease detection database, and other functions are not accepted. Various optimization algorithms such as (Fuzzy Logic, Random Forests, and Q-Learning) and health care data are used in this report to identify patients whether or not they have heart diseases according to the details in the record. The system is able to predict the heart disease as well as COVID-19 disease possibility in a detailed report. Try to use the data as a model that tells the patient whether or not they have heart disease.

Keywords: Heart disease prediction, machine learning, supervised learning, classification, cardiac disease, prediction system

Abstract: The manner in which person and robot interact has been developed using different techniques. Using gestures to control the robotic vehicle is main way to enhance interaction. The user does not need to have any physical contact with the device in this interactive technique. It helps bridge the interactive systems technological gap. The robotic vehicle is intended in this proceed by defining the users real-time motion instructions that are implement using image processing algorithms and integrated methods.

Keywords: Robotic Vehicle, Gesture, Image processing algorithm

Abstract: Examination has an important role in student’s continuous assessment process. The traditional method of conducting examination is through manual question paper generation. This is a very tedious and time-consuming process. To overcome this problem, we have proposed Automatic Question Paper Generator System. The system can store different sets of question paper on the database. It can also store diagrams and they can be fetched inside the system for representation in papers. We have implemented Keyword based Shuffling Algorithm with Randomization for generating question papers which is fast, secure & randomized. The system prevents duplication of questions and also avoids repetitions. The system can also generate class test paper which helps to maintain coverage of whole syllabus. This system tends to improve the overall quality of exam assessments.

Keywords: Generate Question Paper, Duplication, Randomization, Keyword, Shuffling Algorithm, Repetitions.

Abstract: Fire alarm systems are very common nowadays and commonly installed in Banks, shops, offices, home etc. They detect the fire and trigger a loud alarm to aware everybody. But what if nobody is there to hear that alarm, like in night time or when nobody is at home. So to inform the authority about any fire incident today we are building a IoT based Fire Alarm system which not only trigger an alarm but also sends a Email alert to concern persons. This method can also be used to inform fire department automatically in case of fire occurs

Keywords: Thermistor, Variable Resistor(POT), Diode, Capacitor, Resistor, BC547 Transistor, Speaker.

Abstract: The coronavirus disease (COVID-19) is a global pandemic that was discovered by a Chinese physician in Wuhan, the capital city of Hubei province in mainland China, in December 2019. Visualization techniques have been front-and-center in the efforts to communicate the science around COVID-19 to the very broad audience of policy makers, scientists, healthcare providers, and the general public. In particular, the project is focused on visualizing live COVID-19 trends. In this paper, the authors develop a data visualization module that specializes in improvising current COVID-19 Data Visualization Techniques and providing methodologies which enhance viewer-friendliness and boost visual clarity. The module uses authentic sources of data, like the John Hopkins University Covid GitHub Repository, to develop accurate, real-time visualizations which erase discrepancies in visualizations due to inaccurate and irregular streams of data. The authors suggest alternative data visualization techniques to represent data which has the potential of being visualized better than it currently is. Various data visualization libraries such as Plotly, Matplotlib, Seaborn, Ggplot2, GeoPlotlib, etc. have been used to create a variety of visualizations such as scatterplots, bubble charts, histograms, boxplots, distplots, heatmaps, choropleth maps, etc. Keywords – Coronavirus, COVID-19, Data Science, Data Visualization, Modeling, Pandemic, Simulation, Statistics

Abstract: With the quick developing world, the capacity of technological know-how and era has made viable the whole thing a human thinks of. By a decade ago, people had various issues with rising of Urbanization, results one such serious issue of discharge of municipal waste which affected the lives and health of every society. This paper presents a state-of-the-art autonomous smart dustbin i.e., a self-driving vehicular bin which facilitates a best way to overthrow the societal waste. The autonomous bin is capable of locate the rubbish trash containers correctly and autonomously with the aid of using a deep neural network for waste stuff recognition. In addition, the approach of ground segmentation to use a DNN (deep neural network) which is a totally precise navigation strategy is reckoned to guide the self-driving car to move around. This paper presents an artificial intelligence subset deep learning strategy to recognize waste and assess tidiness progressively. Firstly, a digital camera established at the autonomous automobile which gather the road lane images. Secondarily, processed data is transmitted to the information server to examine inside the network. At constant time, quicker RCNN i.e. (region with convolutional neural network) used to observe the road garbage’s bin, pedestrian, building, etc. Also, RCNN perform classification of these categories to perform estimation of number of garbage’s detected on digicam’s frame. Finally, the result has pictured the containers detected on the road lane, which is convenient to regional municipality to allot a clean-up method to the street effectively. This smart approach when implemented, go to facilitate to form the society an improved place. Index Terms: Computer Vision, Deep learning, Image processing, Convolutional Neural Network, Garbage Bin and Sign Detection, Internet of Things.

Abstract: Containerization has become a major trend in the IT industry. It is starting to pose stiff competition to VMs. It is believed that in the near future that containerization would dominate the IT industry. This paper will give insights into the pros and cons of containerization. It will also provide some knowledge on the road ahead for containerization and end with an example of one significant container implementation.

Keywords: containers, container engine, microservices, containerization, virtual machines

Abstract: Using Artificial Intelligence and Machine Learning our project proposes a system named Dictation Module. It is a device that can help society to ace their work and help people in multitasking. As it is rightly said that “If a person cannot perform multiple tasks at the same time, he cannot achieve everything he wants”. Multitasking is the basic asset of every individual in the society. Unlike others, the socially active businessmen or lawyers are forced to be dependent on this aspect. So we have proposed a device that helps to do multiple tasks anywhere you want. Imagine you are driving and you realize you forgot to mail someone something very important, how will you do it in the traditional way is to reach out to the destination and then start typing your mail and send it, which will cost you lots of time as well as some mishap can occur due to this process. But using our module you can dictate the mail to the machine and tell it to send it to the desired person while driving the car simultaneously. We have also included an additional thing to our basic idea that now we are going to store all the files in an online storage i.e. in Telegram using a Telegram Bot so that user can access it from anywhere even if he doesn’t have his local storage with him/her.

Keywords: Artificial Intelligence, Machine Learning, PySimpleGUI ,Voice Recognition, Speech Recognition, Text to Speech , Speech to Text conversion, Yagmail ,Telegram.

Abstract: A ChatBot is a software that can chat with people using AI. This software is used to perform many task such as quickly reply to user helping the user, buying the product and providing best service for user. we present the general working principle and the basic concept of AI chatbot using python programming. these is used as various sectors like banking, college, health, customer call centre and e-commerce. Additionally, these are used in the apps like Amazon, Flipkart, udaan. these helps like Assistance.

Keywords: chatbot, customer service, social service

Abstract: The state-of-the-art technique for animal detection and alerting for crop protection with the goal of achieving high precision with a real-time performance in addition to overcome the disadvantages of the traditional system this computer vision-based system will add more efficiency. In earlier, traditional system consist sensors and registers to identify the movement of object. Some human interventions are required to handle the traditional system, overcome that problems this Image processing based system will work efficiently. The resulting system is fast and accurate, thus aiding those applications which require animal detection.

Keywords: Smart Farming, Wild Animal, Image Processing, Machine Learning, Computer Vision technique.

Abstract: Load prediction of residential buildings is a major area in which research has been going on.The primary aim is to improve the efficiency of demand prediction models. The conventional systems using fixed set point based products like SCADA is not seen to be giving the desired results. In such models the large gap between actual and predicted values of energy consumption causes huge error and it makes such systems unsuitable for use. In such a situation the use of thermal energy model with ANN(artificial neural network)is found to be giving better results with less gap in energy demand and prediction. This project is aimed to study the energy consumption pattern of residential buildings in kerala. Few physical parameters are considered in developing the the building model

Keywords: Load Prediction, SCADA, ANN, TOD, DISCOM.

Abstract: Water is generally regarded as precise and tonic of life.Water shortage has become an important heartbreak. Water shortage is defined as the lack of sufficient available water in all the water resources particularly to meet the demands of water usage.For this core factor we need to save water in all the aspects possible. When we are going to buy a home in residential apartment/society. Therefore,society must have important amenties like automatic water maintenance bill to detect usage of water by individual flats .The objective of IOT based Society Water Management with Automatic Bill Generation system is to provide smart monitoring of water flow in pipes and purity of drinking water, to minimize the wastage of the water and to distribute the water bill according to the usage of water per flat.A comparative study of pros and cons of these approaches have been perceived and the performance metrics of purity, leakage in water pipes and time of responses have been discussed in this survey paper.Also description of IOT based Society Water Management with Automatic Bill Generation using ESP8266 controller.

Keywords: Water wastage, IoT, Water Quality, Water Management, ESP8266.

Abstract: In the fast-growing field of software development and even more fast growing sector of game development the future is hard to predict. I am working with this game as my project and as a part of my degree I choose this type of work for doing better with development cycle, development period, graphics, scripting, adopting new technology, animation, etc. In general, this software project is focusing on the creation of the a 2D game. So measure a Success can be measured by taking a look at the resulting software. In a game development project, the product is a game. But and here comes the point: A game is much more than just it is software. In this we are trying to provide content to become enjoyable. This is important part of game effect on the project as a whole. The part of the software project is not the only one, and it must be considered in connection to all other part s: The environment of the game, the story, characters, game plays, the artwork and so on

Keywords: movig car ,SPEED ,GUI

Abstract: A secure data cluster sharing and conditional dissemination theme with multi-owner in cloud computing, within that knowledge owner can share private data with a gaggle of users via the cloud in associate extremely secure manner, and data person can publicize the information to a different cluster of users if the attributes satisfy the access policies at intervals the ciphertext. we've got an inclination to further gift a multiparty access management mechanism over the disseminated cipher text, at intervals that the information co-owners can append new access policies to the ciphertext because of their privacy preferences. Moreover, three policy aggregation ways in which, in conjunction with full allow, owner priority and majority allow, are provided to unravel the privacy conflicts draw back caused by fully completely different access policies. several schemes area unit recently advanced for storing data on multiple clouds. Distributing knowledge over fully completely different cloud storage suppliers (CSPs) automatically provides users with a precise degree of information run management, for no single purpose of attack can leak all the data. However, unplanned distribution {of data |of knowledge |of data} chunks can cause high information revealing even whereas exploitation multiple clouds. associate economical storage arrange generation algorithmic program supported cluster for distributing information chunks with least knowledge escape across multiple clouds. thus to supply additional security to user’s knowledge we'll divide our knowledge into blocks and transfer every block to completely different cloud suppliers.

Keywords: Data Sharing, Conditional Proxy re-encryption, Attribute-based encryptionn, Privacy Conflict, System Attackability, Remote Synchronization, Distribution and Optimization

Abstract: Online College Management System provides a simple interface for maintenance of student information as well as all the operations related to college. It can be used by educational institutes or colleges to maintain the records of any college operation. The creation and management of accurate, up-to-date information regarding a college academic career is critically important in the university as well as colleges. ERP System for College management system deals with all kind of student details, academic related reports, Promotional things, college details, course details, curriculum, batch details, placement details and other resource related details too. It will also have faculty details, batch execution details, students’ details in all aspects, the various academic notifications to the staff and students updated by the college administration. It also facilitate us explore all the activities happening in the college, Different reports and Queries can be generated based on various options related to students, batch, course, faculty, exams, semesters, certification and even for the entire college The placement officer is responsible for updating the placement related information like eligible criteria for a particular company, arriving date for the company which is coming for recruitment, the list of students who are eligible for attending the recruit.

Keywords: Enterprise Resource Planning, Python, Django, REST Framework, Application Programming Interface, Web APIs, MVC, JWT, MD5, College, Management, LMS.

Abstract: Most existing fair payment solutions use traditional electronic cash systems to generate payment tokens, which requires a trusted authority to prevent double-spending. Hence in this paper we have presented a system which doesn’t require any third party, safe and secure payment system using blockchain. Index Terms - Blockchain, Cloud deduplication, ethereum, SHA and Secure

Abstract: Many researchers have been going on in recent years for the development of ultraviolet based sanitization. In this research contactless determination of Sanitization Robot system where in passing thorough confined space in constrain area, when said robotic system has to be placed in the closed room where no human is needed for further effective operation. The robot can be operated from the laptop or computer by running specific language coding instruction with a unique compiler system. The program has to be run from VNC viewer. It is also capable of live stream of surrounding using camera placed on robot for effective operation of robotic system. The present disclosure highlight System which is contact free and as no human energy is wasted in sanitization of particular compact area. In the present the research proposed an efficient way of sanitization system as the ultraviolet light of type C is able to kill different types of bacteria, viruses and germs. Thus, present disclosure will impact a traditional sanitization method thus giving a new perspective with ultra violet sanitization method, the innovative non invasive blood glucose sensor system place on the robot is placed to check the blood glucose of the user the present disclosure with interactive artificial intelligent problem-solving tool will also help the user to brainstorm the day to today activities.

Keywords: AI based sanitization robot, UV based sanitization, wirelessly controlled robot, and Machine learning based human detection.

Abstract: As data sharing has become one of the most popular services offered by cloud storage, designing public auditing mechanisms for integrity of shared data become more important. Two problems which arise In shared data auditing include preserving users identity and collusion resistant revocation of users. To ensure the security of data sharing within group and outsourced data in group manner are formable challenges. The key protocols have played a very important role in secure and efficient group in cloud computing. To solve this problem, Symmetric balanced incomplete block design (SBIBD) are used for key Security and un-authorized user can’t access the Data from different group. SBIBD is used the general formula for generating the common conferences key K for multiple Participants. General formula (v,K+1,1) block design is used to data are stored. As Result of storing datafrom dynamic group and Data are divided Block and System Performances are a better as compared to Exiting Scheme with help of algorithm Blows fish and DES and Encryption used as fully Homomorphism encryption.

Keywords: Cloud storage auditing, cloud storage, outsourcing computing, key update, encryption.

Abstract: Among worldwide, agriculture has the major responsibility for improving the economic contribution of the nation. However, still the most agricultural fields are under developed due to the lack of deployment of ecosystem control technologies. Due to these problems, the crop production is not improved which affects the agriculture economy. Hence a development of agricultural productivity is enhanced based on the plant yield prediction. To prevent this problem, Agricultural sectors have to predict the crop from given dataset using machine learning techniques. The analysis of dataset by supervised machine learning technique(SMLT) to capture several information’s like, variable identification, uni-variate analysis, bi-variate and multi-variate analysis, missing value treatments etc. A comparative study between machine learning algorithms had been carried out in order to determine which algorithm is the most accurate in predicting the best crop. The results show that the effectiveness of the proposed machine learning algorithm technique can be compared with best accuracy with entropy calculation, precision, Recall, F1 Score, Sensitivity, Specificity.

Keywords: Machine Learning-Classification Method,Dataset,Customer Satisfaction,User-Interface

Abstract: Organ is an important aspect for a living things. Organ donation is a lifesaving process in case of emergency requirement. In this system users can view all the information provided. The main aim of developing this system is to reduce the time to a great extent that is spent in searching for a right donor required. As well as user can register himself for his/her organ donation after his or her death to the needed ones.

Keywords: Organ,Website,Management,Donation

Abstract: A grievance is a discontent or dispute that may arise at any level in any organization. In many circumstances, people of an organization fail to state their issues and cannot seek support for the issues they are facing in an organization. Surveying the already implemented grievance redressal systems, it can be said that the people want to remain anonymous, however there is no provision as such for now. The management of the institutions and organizations are constantly on the lookout for various issues its people are facing, track them down, work on them and update their status, however no current systems address this. Also, these systems are not autonomous and need human intervention for classifying the issues into various categories. Thus, we have come up with a novel approach that keeps all these factors in mind and developed a grievances tracker and redressal system. The end users can post their issues on the portal completely anonymously and the authorities at their various levels can provide solutions to those. Others facing the same issue can upvote the issue for higher visibility. The management can easily track the issues that are currently ongoing, completed, or invalid and can have statistics and reports on one click. The system having natural language processing capabilities can easily and autonomously categorize the various issues based on the content. Also, NSFW content that might be uploaded by the rogue end users can be hampered by using a deep neural network for classifying images before uploading.d. You can use this document as both an instruction set and as a template into which you can type your own text.

Keywords: Grievances Tracking, Issues Tracking, Neural Network, Portal, Management

Abstract: Nowadays the number of cases in the context of farmers committing suicide is increasing day by day. The reason for the same will surely vary from the family to the family of the farmers. Some causes include scarcity of water/ improper water supply, lack of knowledge of the fertility of the soil and the soil content, no prior analysis of past failure, and lack of direct communication between farmers and authorized personals to maintain the demand and supply ratio. All these factors lead to inflation where the cost of the product/pulses reduced due to high supply but lack of demand. As a result, the expected price recovery of the farmer was not satisfied this leads to heavy debts and manipulates the mind of farmers to commit suicide.

Keywords: Farmer Suicide, Water Theft, Soil Moisture, Crop Prediction, Demand And Supply, Water Management System.

Abstract: The main objective of this project to develop an Website which calculates the presents a Handwritten Equation Solver trained by handwritten digits and mathematical symbol using Convolutional Neural Network with some image processing techniques to achieve a decent accuracy of 98.46%.

Keywords: Machine learning, Python, Handwritten Equation, Simplification, Preprocessing, Segmentation, Implementation, Recognition, CNN, Polynomial expressions, Image processing.

Abstract: With the recent outbreak and rapid transmission of the COVID-19 pandemic, the need for the public to follow social distancing norms and wear masks in public is only increasing. According to the World Health Organization, to follow proper social distancing, people in public places must maintain at least 3ft or 1m distance between each other. This project focuses on a solution to help enforce proper social distancing in public using YOLO object detection on video footage and images in real time. The experimental results shown in this paper infer that the detection of human subjects based on YOLO has stronger robustness and faster detection speed as compared to its competitors. Our proposed object detection model achieved a mean average precision score of 94.75%. The network ensures inference speed capable of delivering real-time results without compromising on accuracy, even in complex setups. The social distancing method proposed also yields promising results in several variable scenarios. The proposed system also successfully demonstrated people and crowd detection with varying degrees of the crowd. The system obtained crowd detection accuracy is around 90% and expected to be readily implemented on real hardware drones and tested in real environments.

Keywords: Human Object Detection, Feature Extraction, Distance Tracking, Machine Learning.

Abstract: The main purpose behind the creating this application was to spread awareness among the people of this COVID-19 pandemic. All the correct and a particular application related to the COVID-19 are obtained by the systematic search technique in the popular application store. All the COVID-19 tracking applications or the contacting tracing applications are getting developed at a rapid pace by different government in their respective countries. And one of the best Indian COVID-19 application is Aarogya Setu Mobile Application developed by the Government of India. This application was developed by the Government of India to trace or track the COVID-19 spread and aware people about the pandemic situation. The study aims to understand the various useful features of this application or tool. In our application we have lot of the similar features available in the Aarogya Setu application. Not only from Aarogya Setu application we have also included other features from other applications. All the features are based on the correct sources and studied before implementation. This study would be useful for mobile technology professionals, data science professionals, medical practitioners, health-related frontline workers, public administrators, and government officials. Some of the features are all the confirmed cases, recovered cases, total deaths all over the world are shown. Not only about the world, this application contains the information of Indian states and other countries all over the world. All the information included in this application is from trusted and correct sources, so anyone can completely rely on the data provided in the application. Along with that COVID-19 symptoms, majors to take against coronavirus and to stay safe, all the helpline numbers of Indian states, all the containments zone of India, etc and lot more other features included in this application.

Keywords: COVID-19, coronavirus, mobile health application, pandemic.

Abstract: The main purpose behind the creating this application was to spread awareness among the people of this COVID-19 pandemic. All the correct and a particular application related to the COVID-19 are obtained by the systematic search technique in the popular application store. All the COVID-19 tracking applications or the contacting tracing applications are getting developed at a rapid pace by different government in their respective countries. And one of the best Indian COVID-19 application is Aarogya Setu Mobile Application developed by the Government of India. This application was developed by the Government of India to trace or track the COVID-19 spread and aware people about the pandemic situation. The study aims to understand the various useful features of this application or tool. In our application we have lot of the similar features available in the Aarogya Setu application. Not only from Aarogya Setu application we have also included other features from other applications. All the features are based on the correct sources and studied before implementation. This study would be useful for mobile technology professionals, data science professionals, medical practitioners, health-related frontline workers, public administrators, and government officials. Some of the features are all the confirmed cases, recovered cases, total deaths all over the world are shown. Not only about the world, this application contains the information of Indian states and other countries all over the world. All the information included in this application is from trusted and correct sources, so anyone can completely rely on the data provided in the application. Along with that COVID-19 symptoms, majors to take against coronavirus and to stay safe, all the helpline numbers of Indian states, all the containments zone of India, etc and lot more other features included in this application.

Keywords: COVID-19, coronavirus, mobile health application, pandemic.

Abstract: People communicate through a few shapes of dialect either by content or discourse. Presently to form intelligence between computers and people, computers have to understand natural dialects utilized by people. Common dialect preparing is all approximately making computers memorize, handle and control characteristic languages. With a consistent advancement in innovation, voice command frameworks such as Amazon Alexa and Apple's Siri are getting to be a more normal portion of standard living. This ppt explores voice command of specialized capacities in a savvy phone. Then we present bland information almost the hypothesis and ideas of voice acknowledgment, current voice colleagues, and savvy phone recognized through a writing examination. Using a subjective approach, we explore the impacts of voice command when actualized in smartphone

Keywords: Voice, Commands, Smartphones, Communication.

Abstract: In the past decade cloud computing has been used extensively in industry, personal storage, military, government, etc. Even though storing and accessing data has become a lot easier due to significant development in cloud computing in the last two decades, and there are some issues with increasing dependency on cloud, the biggest issue among many is how secure is data and information in the cloud. So, considering security as priority this paper presents a study on file security using hybrid cryptographic methods. Two of the main constituents of cloud data are text file and multimedia files and here two methods are discussed one each for text file and multimedia file These security issues can be solved using both cryptography and steganography. It can still be improved by using multiple steganography and cryptography techniques.

Keywords: Cryptography, steganography, security, computing, hybrid.

Abstract: Cloud computing is a properly-defined paradigm for computing offerings wherein information and assets are amassed from cloud carrier companies through the internet by the use of well-designed internet-primarily based equipment and packages.. Cloud Computing is simply a combination of computer resources and services and is supplied to people at a cost-effective rate. The sharing of resources might lead to an issue with the availability of such resources, which causes a stalemate scenario. The technique of dispersing network traffic over many servers is known as load balancing. This guarantees that no single server is overburdened. Load balancing increases application responsiveness by distributing tasks equally. It also makes programmes and websites more accessible to users. The purpose of this paper is to understand load balancing.

Keywords: Cloud Computing, Load Balancing, Static Load Balancing, Dynamic Load Balancing.

Abstract: Cloud computing is becoming popular in the field of IT industry these days. It’s a model that allows people all over the world to connect to shared pools of programmable resources over the internet. That is, it can execute many apps or programs on many computers at the same time. Cloud computing's nature and applications are continually evolving, both virtually and in reality.The deployment of cloud models is explored in this study.The main cloud deployment types are public,private,community and hybrid clouds. Each of these models has its own set of benefits and drawbacks.Cloud computing is successful in providing a cost effective strategy for most of the companies to manage IT. The major thing that is limiting the cloud’s expansion is security.In this paper different deployment approaches are proposed depending on various security concerns.. Each model adds to the security measures offered by the preceding ones. The last model alleviates security problems.It can be used as a template for future models.

Keywords: Cloud Security, Cloud Deployment,Separation of Duties,Data migration,Data Confidentiality,Data Integrity,Data Privacy

Abstract: The enormously enhancing the evolution of forthcoming generations, the fifth-generation wireless technology continuously developed and extent to more progressive. The field of mobile technology provides improved network capacity, low latency, great availability, more reliability with intense speed. This paper introduces an overview of fifth-generation wireless technology accompanied by five other major technologies of 5G namely millimeter wave, small cells, Massive MIMO, Beamforming, and Full-duplex respectively. In addition, Energy Efficiency (EE) is an enormous strategy that immensely declines the circuit power consumption in fifth-generation cellular networks. This consequence is enhanced due to the rising number of antennas in massive multiple-input multiple-output (MIMO) systems. Energy efficiency has now become a fundamental aspect in the framework of communication networks. With the arrival of the fifth generation of wireless networks, with millions of additional base stations and billions of connected devices, the demand for energy-efficient system design and operation will be even more fascinating. Further, this paper outlines the various research work related to energy efficiency including the papers published in this special issue, and considers the most compelling research challenges to be discussed in the upcoming generation.

Keywords: 5G,Massive MIMO, Millimeter wave, small cells, Beamforming, Full duplex, heterogeneous networks, Energy Efficiency (EE).

Abstract: COVID-19, a new virus, was discovered in Wuhan, China, in December 2019. Due to its infectious features and lack of medically established therapy, the COVID-19 virus spread around the planet in early 2020, causing widespread infections and deaths on all continents except Antarctica. The COVID-19 epidemic has been dubbed the most significant worldwide calamity since World Wars I and II. The initial line of defence in the fight against Non-pharmaceutical techniques such as social separation and personal isolation are used to disseminate COVID-19. The global epidemic, which is hurting billions of people economically and socially, has reached a tipping point. spurred the scientific community to develop computer-assisted solutions COVID-19 diagnosis, prevention, and estimation using digital technologies. Several of these Efforts are centred on statistical and Artificial Intelligence-based data analysis. COVID19 is a virus. All of these scientific endeavours required that the data collected be made public.To encourage expansion, validation, and improvement, the analysis service should be open source.In the fight against the global pandemic, team. Keywords COVID-19, coronavirus, pandemic, machine learning,artificial intelligence, open source, data sets

Abstract: With recent advance in web technology, many online shopping websites have been emerged. Despite its advantages, however, online shopping presents certain drawbacks. One drawback is that it may be difficult for a person to visualize how a given article would look if worn by that person-owing to the rich variation in body size and shape, hair and skin color, etc., in the human population. Testing the fitness of clothes is highly important for both customer and trader. Our approach concentrate on how the selected garment fitted the user’s body and how it will be appear as if he/she in real world. Trying clothes in clothing stores is usually a time-consuming activity. Besides, it might not even be possible to try-on clothes in such cases as online shopping. Our motivation here is to increase the time efficiency and improve the accessibility of clothes try on by creating a virtual dressing room environment. The implemented system introduced an advanced methodology which is presented for the purchase of clothing through a virtual fit on platform, which consumes far more less time than the normal process, making it easier for the both seller and customer. This provides a realistic behaviour for the suitability of the garment’s details. The whole process starts from an image of the user which is captured from the webcam which then and there provides an environment of a virtual dressing room. Customers are able to select clothing designs from a range of different garments as they prefer and those can be tried onto the image which allows them to experience a live view of the outfit as if it worn on their own body. The primary aim of this project was to build up a compelling, interactive and highly realistic shopping experience via a desktop application providing the user a reliable and accurate service to access an environment of a virtual try on system.

Keywords: Virtual dressing room, Virtual TryOn, Visualization, Virtual fitting, trial, augmented reality, room.

Abstract: Now days, Complaint any Civic or day to day life problems is a difficult process for the citizens. They have to do a long procedure and formalities to register their problems or to report such problems like street damages, garbage management problems, Electricity problem etc. in short citizens can Upload their problems which come under the surveillance of munici-pal. Usually because peoples are very busy with their day to day work and they don’t have time to register the complaints and to follow the time consuming process. To make an easy reporting system for complaining procedure, we are going to implement an machine learning online web application that will provide a platform for citizens report their problems with infrastructure in their city to relevant municipal department.

Keywords: CNN, Transfer Learning and Image processing.

Abstract: With recent advance in web technology, many online shopping websites have been emerged. Despite its advantages, however, online shopping presents certain drawbacks. One drawback is that it may be difficult for a person to visualize how a given article would look if worn by that person-owing to the rich variation in body size and shape, hair and skin color, etc., in the human population. Testing the fitness of clothes is highly important for both customer and trader. Our approach concentrate on how the selected garment fitted the user’s body and how it will be appear as if he/she in real world. Trying clothes in clothing stores is usually a time-consuming activity. Besides, it might not even be possible to try-on clothes in such cases as online shopping. Our motivation here is to increase the time efficiency and improve the accessibility of clothes try on by creating a virtual dressing room environment. The implemented system introduced an advanced methodology which is presented for the purchase of clothing through a virtual fit on platform, which consumes far more less time than the normal process, making it easier for the both seller and customer. This provides a realistic behaviour for the suitability of the garment’s details. The whole process starts from an image of the user which is captured from the webcam which then and there provides an environment of a virtual dressing room. Customers are able to select clothing designs from a range of different garments as they prefer and those can be tried onto the image which allows them to experience a live view of the outfit as if it worn on their own body. The primary aim of this project was to build up a compelling, interactive and highly realistic shopping experience via a desktop application providing the user a reliable and accurate service to access an environment of a virtual try on system.

Keywords: Virtual dressing room, Virtual TryOn, Visualization, Virtual fitting, trial, augmented reality, room

Abstract: Real-time quality inspection of capsules manufacturing in pharmaceutical applications is an important issue from the point of view of industry productivity, competitiveness and quality aspect of the product. Pharmaceutical products are susceptible to several common flows like incorrect size or colour, surface defect, missing, broken capsules. To guarantee every capsule is free of defects, each capsule must be inspected individually. We proposed system which we have compared different approaches of image processing for detection of defective capsule and presence of category of defects.

Keywords: Deep Learning, ResNet50, CNN, Python, Feature Extraction.

Abstract: The majority of people today depend heavily on their mobile devices. The smartphone is a flexible platform that can appeal to a variety of our needs, from making phone calls to keeping track of our fitness. Despite the growing popularity of flexible manufacturing, due to issues such as asset scarcity, frequent separations, and versatility, maximising its potential is difficult. Cloud registering has consequently empowered dispersed organizations that help in figuring assets in an online way. This has additionally formed into ideas, for example, mobile distributed computing frameworks which give cell phones resources to help limit registration constraints. Mobile devices, too, have certain flaws. The amount of memory available, computing speed, and battery life have always been the main drawbacks of mobile devices. Mobile cloud computing can overcome these issues by performing versatile applications on asset suppliers outside the cell phone. The basic architecture and details of its methodologies are discussed in this paper. The report will close with the needs of mobile cloud computing, and feature headings for future work.

Keywords: Mobile computing, Cloud computing, Mobile Cloud Computing(MCC),Application programming interface, Distributed computing, Offloading

Abstract: Using empirical analysis, conventional air automatic monitoring system has high precision, but large bulk, high cost, and single datum class make it impossible for large-scale installation. Based on introducing embedded system into the field of environmental protection, this project puts forward a kind of real-time air pollution monitoring and forecasting system. By using embedded, this system can reduce the hardware cost into 1/10 as before. The system can be laid out in a large number in monitoring area to form monitoring sensor network. Besides the functions of conventional air automatic monitoring system, it also exhibits the function of forecasting development trend of air pollution within a certain time range by analysing the data obtained by front-end perception system according to neural network technology. Targeted emergency disposal measures can be taken to minimize losses in practical application. Keywords — nodeMCU, MQ135, DHT11, MQ5

Abstract: Virtual Smart Assistant is customizing programs/structures which are expected for dying the human undertakings. The Most commended utilization of iPhone is "SIRI" which helps the top customer to offer end customer flexible with voice and it similarly responds to the voice requests of the customer. Same quite use is moreover advanced by the Google that's "Google Voice Search" which is employed for in Android Phones. Nonetheless, this Application by and enormous works with Internet Connections. Nevertheless, our Proposed System has ability to figure with and without Internet Connectivity. It is named as Personal Assistant with Voice Recognition Intelligence (Alexa), which takes the customer commitment to kind of voice or text and cycle it and returns the yield in various constructions like movement to be performed or the question yield is coordinated to the end customer. Also, this proposed structure can change the strategy for relationship between end customer and the Computer System. The system is being arranged with the goal that all of the organizations given by the PC's or Laptops is open by the end customer on the customer's voice orders.

Keywords: SIRI, Google Voice Search, Alexa, PC, Laptop, Internet, Cortana, Google Assistant.

Abstract: Imagining the world without any use of electricity is very difficult these days. Small things like study lamp to big things like a plane requires electricity to operate. Human civilization has become very modern, and electricity is needed everywhere.In Today’s modern era new forth thing is added in the basic need i.e. food, Shelter,cloths and Electricity. So the keeping that though in mind and a little contribution to humanity we have proposed electricity generation mechanism with the help of steps of Human being.This project is to develop a new source of renewable energy with low-cost budget with the help of Arduino Uno as the microcontroller. The footstep power generation system is to capture the typically wasted energy surrounding a system and transforming it into electrical energy. Here force energy is produced by human footsteps and the force energy is converted into mechanical energy by rack and pinion mechanism, electricity is produced by generator. This power source has many applications as in home, agriculture application and street lighting and as energy source for sensors in remote locations. This paper is mainly all about generating electricity when people walk on the Floor.

Keywords: . Arduino Uno, rack and pinion mechanism, Generator, Rectifier, Voltage Sensor

Keywords: Arduino(ATMEGA328), measuring instrument, DC motors, RF Transmitter&  Receiver.  

Abstract: Music is a limitless form of art. Accessibility is an essential part of its emergence. Traditional musical instruments like piano, drum, etc., are expensive and arduous which reduces its accessibility and portability. To make it universally available and efficient, this is an attempt to demonstrate the use of an alternate medium for creating music using gestures. use of colored gloves/fingertip covers/nail paints/drumsticks, etc., making it more user-friendly and autonomous.This makes it available to a large number of music enthusiasts. Devices, nowadays, use touch-based and key-array-based controls, limiting the interface to two dimensions. For this purpose, object detection has been used to demonstrate a gesture-controlled piano, giving it another dimension. Existing image processing systems use shadow detection methods, IR detection methods, etc., whereas here, object detection method for gesture recognition has been used to identify the gesture and simulate the playing of piano notes. The object detection method eliminates the use of colored gloves/fingertip cover/nail paints/drum sticks, etc, making it more user friendly and autonomous.

Keywords: CNN, API, OpenCV, GPU, CPU

Abstract: Globalized producing and horticultural assembling dissemination give a recharged center to the food handling, food quality, and the approval of a few critical rules in farming and food supply chains. Expanding quantities of sanitation and food corruption dangers have made a gigantic requirement for an effective recognizability arrangement that goes about as a significant quality administration instrument guaranteeing proper item wellbeing in the farming inventory network. Blockchain is a problematic innovation that in horticulture and food supply chains can give an imaginative and option in contrast to item detectability. The present horticultural inventory chains are muddled biological systems including a few giver manufacturing it hard to approve a few critical necessities like country of beginning, crop development stages, quality principles consistence, and yield checking. In this task, we recommend a technique that influences the blockchain and productively leads organization activities across the horticulture's inventory network for crop value checking and discernibility. Our answer kills the requirement for a confided in brought together power, middle people and offers records of exchanges, improving proficient science and security with high respectability, dependability. All exchanges are recorded and put away in the unchangeable record of the blockchain with connections to a decentralized le framework and along these lines guarantee an undeniable degree of straightforwardness and detectability in the inventory network biological system in a dependable, solid, secure and proficient way

Keywords: Blockchain, Smart Contracts, traceability, agricultural supply chain, food safety.

Abstract: Return on Investment is a Level Five training evaluation model that compares costs to benefits and expresses the return as a percent. It is a useful model to communicate the benefits of training to program stakeholders. ROI (return on investment) calculators are becoming especially powerful tools for marketers today. This type of interactive content helps your customer project their ROI should they buy your product or service. With this personalized information in hand, they can make an educated decision about whether or not to buy. Using an ROI formula, an investor can separate low-performing investments from high-performing investments. With this approach, investors and portfolio managers can attempt to optimize their investments.

Keywords: Investment calculator for Return of Investment.

Abstract: The use of private vehicles intensifies the existing unbearable traffic jam and majority of the parents consider school buses to be largely unsafe for their kids. However, safe and user friendly school buses can reduce the use of private vehicles and will eventually cut back the traffic jam in cities especially in school hours. All buses can be tracked by the guardians using the proposed intelligent and secured tracking system for school buses. This proposed system includes an Android application that can be employed to send notifications during entry and exit of the students using Fingerprint scanner, ensuring arrival confirmation of the student by dual authentication. The system will also notify parents when the bus is a 15-min distance away from the home. The focus of the research is to display the feasibility of a safe and intelligent school bus using secured tracking system based on authentication procedures. It is expected that the offshoot of this research initiative will regain the confidence and reliability of parents in school bus and reduce the use of individual transport. A smart school bus will keep the student safe, easing the tension for parents and the city will have a smooth traffic system.

Keywords: School Bus; Safety System; GPS; Fingerprint; Iota.

Abstract: There is an expectation that the blood will always be there when it is really needed. Blood donor volunteers constitute the main supply source in an effective blood supply chain management. They feed blood stocks through their donation. In an emergency situation, if the stocks are insufficient, the only source of blood supply will be the people who come to the health centre and donate the blood on a voluntary basis. It is certain that time is a very important component in such situation. For this reason, the health care centre should call the nearest available donor in order to ensure to get the service as quickly as possible. A smart phone application is developed to facilitate the identification of the nearest available blood donor volunteer and the communication with him/her in the emergency situations where the blood can’t be supplied through the blood banks’ stocks.

Keywords: Smart phone application, Plasma donation information system, optimization, distance calculation, java development platforms.

Abstract: A new secure picture transmission technique that changes naturally a given enormous volume secret picture into a secret-fragment-visible picture is called a mosaic picture of an exactly similar size. The mosaic picture, which looks to be like a discretionarily choose target picture and may be used as a disguise of the secret picture, is yielded by separating the secret picture into sections and changing their shading attributes to those of the comparing pieces of the target picture. Skillful techniques are invented to lead the shading change process so that recovered secret pictures may be almost losslessly. A scheme for handling overflows/underflows in the converted pixels shading values by recording the shading contrast in the untransformed shading space is proposed in addition. The data needed for improving the secret picture is embedded in the created mosaic picture by a lossless information concealing plan using a key.

Keywords: mosaic picture,picture encryption, data hiding , secure picture transmission.

Abstract: The ability to analyse facial expressions plays a major role in non-verbal communication. If a someone only analyses what a person's mouth says and ignores what the person's face says, then we can only have a part of the story. Humans were the only ones who could distinguish between expressions but not anymore, with advancing technology our computers can learn how to detect emotions as well. This report is a guide to facial expression recognition software using OpenCV, Keras, Tensorflow and CNN, by implementing a program in Python it has become possible to build an algorithm that performs detection, extraction, and evaluation of these facial expressions for automatic recognition of human emotion in real-time. The main features of the face are considered for the detection of facial expressions. To determine the different emotions, the variations in each of the main features are used. To detect and classify different classes of emotions, machine learning algorithms are used by training different sets of images. This paper discusses a real-time emotion classification of a facial expression into one among the seven universal human expressions: Anger, Disgust, Fear, Happy, Neutral, Sad, Surprise by the implementation of a real-time vision system that can classify emotions.

Keywords: CNN, Facial Emotion Recognition, FACS, EMA.

Abstract: A novel coronavirus spill over event has emerged as a pandemic affecting public health globally. Screening of large numbers of individuals is the need of the hour to curb the spread of disease in the community. Real ‐ time PCR is a standard diagnostic tool being used for pathological testing. But the increasing number of false test results has opened the path for exploration of alternative testing tools. Chest X-Rays of COVID-19 patients have proved to be an important alternative indicator in COVID-19 screening. But again, accuracy depends upon radiological expertise. A diagnosis recommender system that can assist the doctor to examine the lung images of the patients will reduce the diagnostic burden of the doctor. Deep Learning techniques specifically Convolutional Neural Networks (CNN) have proven successful in medical imaging classification. Four different deep CNN architectures were investigated on images of chest X-Rays for diagnosis of COVID-19. These models have been pre-trained on the ImageNet database thereby reducing the need for large training sets as they have pre-trained weights. It was observed that CNN based architectures have the potential for diagnosis of COVID-19 disease.

Keywords: Covid-19, CNN, Corona Virus, X-Ray.

Abstract: The outbreak of COVID- 19 has created a social and psychological problem including mental health that has had a deep impact on students of Higher education. The all universities (993 universities In India ,and colleges ( 39931 Colleges) with other higher education Institutions decided to temporary suspended the classes , conferences, seminars. Examination and sports activities due to badly hit of COVID-19.The closure of university and colleges with institution of higher education may create the situation of frustration, stressors, worry and fear towards the students.The Covid-19 outbreak brought not only the risk of death from the viral infection but also unbearable psychological pressure to students in higher education. The entrance examination conducted by the regularity body universities , colleges and institute of Higher education suspended or postponed due to spreading of coronavirus -2019, this attributed to anxiety, fear and other psychological impact of the students. Key words: Students, Higher education, Stress, Anxiety, Mental Health, Covid-19

Abstract: Text conversion and categorization are fundamental machine learning operations in which an object is assigned to a subset of unnamed candidates. We propose a novel text classification approach based on Deep Learning in this research (DL). Our suggested method has a lot of appealing features: it gathers certain metadata from each item and builds the training set train first. The weight achieved under each class mark was used to classify each object. The Recurrent Neural Network (RNN) was employed in the proposed classification model. For training and testing, the streaming text was dispersed using cross-fold validation. The 70-30% of the data was used for training and research purposes, respectively. The consequences of the strategy in the chapter on outcomes are revealed through a partial implementation. The proposed method outperforms traditional approaches to text classification, according to the results of the experimental study.

Keywords: Text processing, Machine learning, deep learning, natural language processing, data analysis, artificial intelligence

Abstract: In today’s busy world , these autonomous bots can save both time and energy by helping in industries where instead of employing a human operator we can set our desired tasks to the robot which can easily follow the repetitive path from source to destination and vice versa. Kepping the need of industry in mind we have praposed the line follwer robot with the help of aurdino sytem which helps to overcome the problem of labour.It is microcontroller based autonomous robot which detects and follows a path that can be invisible magnetic field or a visible path indicated by black line on a white surface(or vice versa). The system senses the line. This work is done by sensors – IR sensors. The IR sensors are mounted at the front end of the robot. The data from these sensors will be given to the microcontroller (Arduino board) which in turn sends the signal to the motor driver that in turn drives the motor of the robot based upon the information of IR sensors. This system hence can be used in a safe, efficient, time-saving way in industries as well as for daily purposes.

Keywords: IR Sensor,Aurdino UNO, Robot, Motor

Abstract: This paper discusses recovering old or damaged images using generative adversarial networks. Researchers are using generative adversarial networks as a general-purpose solution to image to image translation problems. We demonstrate that this approach is effective in restoring lost parts in an image and colorizing images, but these networks can be used to solve a wide range of image to image translation problems.

Keywords: Restoration, Colorization, Generative Adversarial Network, Generator, Discriminator, Deep learning.

Abstract: The paper is about advocating usefulness of the social media as educational too at the same time warns against the dangers of unguided and unsupervised access of learners to the social networking sites. Social media can’t be ignored as it has become part of daily routine of more than ninety percent young students. These sites have some unique characteristics like quick, economic, secure, creative, social and multimedia besides huge capacity of data uploading and sharing. The impact is such that no teacher affords to ignore, rather it would be better to accommodate in the teaching-learning process. Author includes number of references to demonstrate integration of semen’s like Facebook, Twitter, LinkedIn, YouTube etc. At the same time author cautions about some concerns like privacy, wastage of time, distractions and mechanical nature of these SNS’s. In the final lines, author referrer some implications for teacher in context of SNS’s which also hints future direction for teacher education program.

Keywords: Social Media, College, Android, Application,

Abstract: Government is allocating many expenses made in the field of military and army forces in adopting primitive security measures taken to protect the borders from the unknowns and tresspassers. And some military/army organizations taking the help of robotics and technology and in the risk pronezone areas which are not that effective when its done by miltary mens. These Army robotics are comfine with the camera module, sensors, bomb detector and video streaming. The main agenda of our system is to get chameleons or camouflaged including some additional parameters like bluetooth model for real time data processed by the camera at the video screen and passive infrared sensor to identify the intruders.. Thus the proposed method using blue-tooth reduces errors at defense and keeps the nation secure from the foe.

Keywords: controller, wifi module, motors, chassis, camera module,wifi night vision camera module, etc.

Abstract: Cloud computing can be described as an on-demand availability of computer resources to perform large-scale and complex computing which helps maintain dedicated space, computer hardware and software in an efficient manner. Big data cannot be easily handled and processed using traditional methods but can be utilized and controlled better with the help of the cloud. In this paper, we will see why big data handling and processing is better in a cloud environment in a sequence starting with simple illustration of how big data can be uploaded and linked to the cloud and on-premises applications using IPaaS, hybrid cloud solutions for encapsulation and data security and finally multi-cloud solutions for improving the overall performance of big data processing in the cloud environment with their advantages and disadvantages, respectively.

Keywords: Cloud computing, Big Data, Big data analytics, Hybrid cloud, multi cloud.

Keywords: -Vision Systems, Fire Detection, Smart Cameras, Computer Vision, Object Detection

Abstract: In India electricity generation is less and demand is more. In industrial, rural, agriculture areas the available electricity is less. So that electricity thefts are increasing every year across domestic as well as industrial domains which increases cost paid by customer and can have serious safety consequences. So that, the project’s aim is to design a system which overcome these problem which means design a system to monitor the power consumed by the load to detect and notify the electricity board about electricity theft through IOT (Internet of Things). In this project hall sensor detect power theft and send command to GSM module which sends the theft information message to electricity board. The implementation of this system save large amount of electricity and also prevent theft of electricity

Keywords: Internet of things, GSM module, Microcontroller, Hall sensor, electricity theft detection, electricity board.

Abstract: Face recognition technology is a biometric development, which relies upon the of facial components of a person. individuals assemble the face pictures, and the recognition gear subsequently processes the photos. The report presents the related explores of face recognition as indicated by substitute perspectives. We present the investigation of face recognition for certifiable conditions, and we present the general evaluation standards and the by and large data bases of face recognition. We give a forward-looking point of view on face recognition. Face recognition has transformed into the future progression heading and has various potential application prospects.

Keywords: Open CV, Image Processing, Deep Learning, Numpy, PyCharm