VOLUME 10, ISSUE 6, JUNE 2021

Abstract: The Technology Assisted Science, Engineering and Mathematics (TASEM) learning, with major focus on innovations in the use of technology to explain new and complicated concepts rather than on education research, goes far beyond the conventional demos of van de Graaf (VDG) generators to introduce programmable Lego-based VDG (PLVDG) for the first time. The PLVDG modules explain underlying concepts of micro- and nano-systems in a fun and fascinating way as evident from the level of interest seen in over 2000 learners at K-12, undergraduate and graduate levels during 2000-2010. The interest in PLVDG seems to be strongly related to the fact that the learners can design, build, program and explore PLVDG using different pulley & belt materials and a palm-size robot. The generated voltages are in the range of 5 – 35 kV depending upon humidity and pulley speed. Sensors of positive and negative charges have also been developed using NMOS and PMOS switches embedded in LEGO-like bricks. Several new experiments are reported in this paper focusing on learning of a number of areas including materials, engineering (EE & ME), computers, and microsystems.

Abstract: The innovation Smart home is a home where appliances can be remotely controlled and monitored with the help of a network connection. Despite the numerous advantages of smart home, the security of smart homes has been a concern to home users also, smart home can improve in predicting user activities in the home. In this research work, we were able to predict home user activities in a secured smart home. A software interface was provided for One Time Password (OTP) authentication and for controlling home appliances. The use of deep learning model enables us to predict accurately, when appliances homes should be ON or OFF. The prediction was made from previous appliances historical dataset. The home security was enhanced with one time password and decision tree to detect dictionary attacks. The result gotten from the prediction system showed series of predictions made by the system at different time interval. The security result shows how effective the smart home security system is in mitigating attacks in the home.

Keywords: Smart home, Security, One Time Password, Internet of Things, Machine Learning.

Abstract: Breast Cancer is the most common malignancy in women and is the second most common leading cause of cancer deaths among them. At present, there are no effective ways to prevent and cure breast cancer, because its cause is not yet fully known. Early detection is an effective way to diagnose and manage breast cancer and can give a better chance of full recovery. Several domains and concepts are used in the detection of breast cancer. The main domains used in this detection technique include different types of Region algorithm and Directional feature method. Their region-based algorithm was especially adapted to tumors that extend over a relatively large area.

Keywords: Breast Cancer, Region algorithm and Directional feature method.

Abstract: All around the world, domestic birds are a major threat in the field of agriculture causing damage to economic field crops, storage houses and also dirtying human life areas. Such most common pest birds in many countries are House crows (Corvus), Common myna, Jungle myna, Brahminy starling, White-cheeked bulbul, Acridotterestritis etc. In order to distract these birds away, many traditional methods such as Scarecrow models, Hawk kites, Colored lights, Flashes, Chemicals etc. are used which nowadays do not seem very effective. In addition to this some of these methods can be harmful to the birds. In this paper an effective bird deterrent technique i.e., Bird Scarer has been developed. Different sounds and visuals due to which different species of birds get deterred were also noticed and studied. Unlike other projects, our project includes a variety of techniques suitable for small as well as large areas.

Keywords: Pest Bird repeller, infrasound, flash, moving wand, laser.

Abstract: To deal with the unpredictability of real time challenges, many tools and techniques has been proposed. One of the tools in dealing with imprecision is neutrosophic sets and its combinations. These sets generalize fuzzy sets, intuitionistic fuzzy sets and their extensions with a wider scope of application and thus a motivation for developing various theories. In this paper, the new concept of Fermatean Neutrosophic Sets (FNS) is defined. Further the algebraic properties and set theoretical of the Fermatean Neutrosophic Set is studied.

Keywords: Fermatean fuzzy set, neutrosophic set, Fermatean neutrosophic set.

Abstract: The ultimate purpose of Customer Relationship Management (CRM), like any organizational initiative, is to increase profit. In CRM it is achieved by providing a good service to the customers than your competitors. CRM not only improves the service to customers though; a good CRM capability will also reduce costs, wastage, and complaints, The CRM also reduces staff stress, because pressure -which is the main cause of stress reduces as services and relationships improve. CRM helps in instant market research and open the lines of communications with customers gives direct constant market reaction to the products, services and performance, far better than any market survey.

Keywords: CRM, stress, Market Research

Abstract: Alexa usually responds to voice commands but what about the people who cannot hear and speak. Everyone should adapt new technologies which will ease their life. So to overcome this problem we are Making Amazon Echo to Respond to sign language. This device will help the deaf mute to interact with Alexa by showing gestures and actions. Here camera will be used to interpret signs from the user then the signs will be converted to text and speech and then Alexa's response will be transcribed. For developing this device there is need of A neutral network to interpret the signs, A text to speech system to speak the interpreted sign to Alexa by using Web Speech API for speech synthesis to speak out the detected label, A speech to text system to transcribe the response from Alexa for the user again by using Web Speech API for transcribing the Echo’s response which responds to the query clueless to the fact that it came from another machine. And then an interface for which we have to design a browser which connects the network and web Speech API which can be opened in laptop with webcam this interface will combine all together and make Alexa to respond sign language.

Keywords: Alexa, Amazon Echo , CNN, RNN, LRCN.

Abstract: Long response time required for emergency services to arrive is a primary reason behind increased fatalities in serious accidents case. One way to reduce this response time is to reduce the amount of time it takes to report an accident. Smart phones are ubiquitous and with network connectivity are perfect devices to quickly inform authorities about the accident. We are designing an Android application “LIFEGUARD: HELP IN ACCIDENT” which will be beneficial for people to help other people who are suffering from incident like accident. It will help us to save the accidental person. Project is design for an accident detection system. The application suggests nearby hospitals and police stations list in application. FIR is generating by police station and sends copy to the respected hospital system. Respected hospital scan user QR Code and provide treatment according to information. Also send emergency SMS to users preregister mobile number.

Keywords: QR Code generator and scanner (QR Code is a machine-readable optical label that contains information).

Abstract: A snapshot of retinal image is used to analyse the disease called familial exudative vitreoretinopathy (FEVR). FEVR disease mostly affects the retinal nerve parts and it leads to vision loss, retinal detachment, strabismus, and a visible whiteness (leukocoria) in the normally black pupil. The symptoms may vary even within the same family. This disease is incurable when it reaches its severe stage. So it is very important to diagnose it in previous stage of infection. Along with FEVR we also diagnose the disease like glaucoma, refractive power and cataract. Mostly diabetes patients are affected with such type of retinal disease. Automatic retinal segmentation is complicated by the fact that retinal images are often noisy, poorly contrasted, and the vessel widths can vary from very large to very small. So in this project, we implement automate segmentation approach based on graph theoretical method to provide regional information using measure. We represent the segmented vascular structure of retina as a vessel segment graph and make problem of identify the vessels as one of finding the blood vessels to have good correlation. We plan a method of image processing with some insisted algorithms to diagnose and evaluate the retinal disease.

Keywords: Image Processing, SVM algorithm, IPACHI Model, MATLAB.

Abstract: The infection spreads in the lungs area of a human body. The chest x-ray is performed to diagnose this infection. Physicians use this X-ray image to diagnose or monitor treatment for conditions of pneumonia. This type of chest X-ray is also used in the diagnosis of diseases like emphysema, lung cancer, line and tube placement and tuberculosis. Feature extraction methods like DWT, WFT, and WPT can also be used. In this paper, detection of pneumonia infection by unsupervised fuzzy c-means classification learning algorithm is used. This approach gives better result than the rest of the methods. In fuzzy c-means, each resultant pixel gives accurate value since it has a weight associated with it.

Keywords: Deep learning · Chest CT scan · X-Ray Image · Cough analysis, radiomics, medical imaging, CNN, chest X-ray, neural networks,

Abstract: Depression is a mental illness that affects an individual negatively. It is considered as a serious disease by mental health care professionals. Depression detection is important to avoid unwanted consequences of not acknowledging the disease. A research was carried out in 2012 and an estimate was found out. It was observed that there were roughly 258000 suicides. Further, it was observed that the age group that was mostly affected was between 15-49 years of age [1]. This estimate informs us that the aforesaid age group is prone to depression. This age bracket spends maximum time on social media and shares their view on it. It reflects their mental condition. This fact encourages us to develop a system to detect the depression level of the users and provide necessary information to the guardians to enable the guardian to take appropriate actions. The system is beneficial in informing the user and their guardian to prevent self-harming or worsening of the condition. The death rate will significantly reduce if the user and the guardian are aware of the mental state of a user. The system is expected to be beneficial to reduce the percentage of death due to depression. It'll provide awareness to users and their guardians by automatically detecting depression [3]. This approach will utilize the emotions of the user detected from videos watched by the user. The title of the video indicates the content or category of the video. This enables us to get an insight to the user’s inclination towards negative polarity.

Keywords: Depression detection, NLP.

Abstract: Crowd With the popularity of mobile devices we know many peoples are using mobile to read the news instead of newspaper, because they are interested to read the news as per their geographical area. So, for that we are introduce SLR triangulate method called as Section based, location based and ranking based news recommendation system with the help of fake user detection.

Keywords: Topic ranking, inverted pyramid, location aware news recommendation, spammer identification.

Abstract: In this project, we will introduce an affordable IoT-based solution aiming to increase COVID-19 indoor safety, covering several relevant aspects: 1) Contactless Temperature Sensing. 2) Mask Detection. Contactless temperature sensing subsystem relies on Arduino Uno using infrared sensor or thermal camera, while mask detection and social distancing check are performed by leveraging computer vision techniques on camera-equipped computer.

Keywords: COVID-19, Mask Detection, Temperature Detection, Contactless.

Abstract: COVID-19 pandemic has tremendously affected our day-to-day life affecting the world trade and movements. Wearing a protective face mask has become mandatory. In the near future, many public service providers will ask the customers to wear masks to avail of their services. Therefore, face mask detection has become a essential task to help global society. This paper presents a simplified approach to achieve this purpose using some basic deep Learning packages like TensorFlow, Keras, OpenCV. The proposed methodology detects the face from the image/video stream correctly and then identifies if it has a mask on it or not. As a surveillance task performer, it can also detect a face along with a mask in motion. The method obtains accuracy up to 95.55% and 94.23% respectively on two different datasets. We explore optimized values of parameters using the Convolutional Neural Network model to detect the presence of masks correctly without causing over-fitting.

Keywords: Convolutional Neural detection, TensorFlow, Deep Learning, Keras.

Abstract: In the last decade, moving computing, control, data storage, and processing to the cloud has been a major trend. But due to the rapidly increasing number of Internet of Things IoT devices/sensors over the world, the cloud was encountered many troubles and limitations, such as high latency, poor quality of service, and location awareness, especially for real-time applications that needs interactivity and fast response. To support this computational demand of real-time latency-sensitive applications of largely geo-distributed IoT devices/sensors, a new computing paradigm named Fog Computing has been introduced [1]. Fog computing is a novel technology that extends and supports cloud computing to reach the optimal performance in the network. Fog computing is acting by pushing the computing and services to the edge of the network. In this paper, we will introduce the Fog Computing term, its architecture is explained, the characteristics are discussed, a comparison with Cloud Computing is examined, and future research directions are mentioned.

Keywords: Fog, Cloud, Computing, Internet-of-Things, IoT, Latency, Bandwidth, Real-Time Application

Abstract: In the recent days, online social networks (OSNs) are widely known as one of the largest platforms for the source of information and content that can be shared among people. As a socially oriented learning-based model has been proposed with a view to provide quality of experience (QoE) for social media services. This is for media content prefetching in order to improve the access delay reduction and to enhance OSN user’s satisfaction. With a wide spread of data-driven analysis during a period of fourteen months, over the Twitter traces on real-life from over 2,800 users, it is revealed that the social relationship has a wide impact on user’s social media behaviour. In order to represent this scenario, a social relationship of clusters for a large group of friends has been conducted, and further to expand a cluster-based machine learning model for socially-oriented learning based prefetch prediction. And then to predict users influence on the social media app, a usage-adaptive prefetch scheduling mechanism has been used by considering different users which might possess heterogeneous user’s app usage way. A framework has been proposed that can be evaluated using a trace-driven analysis on the social media. The data can be dumped onto a cloud for further analysis by using different machine learning approaches.

Keywords: Online Social Networks, Prefetching, Quality of Experience, Spice, Twidere, Usage Adaptive prefetching scheduling.

Abstract: Front-end web development is the practice of converting data to a graphical interface, Through the use of HTML, CSS, and JavaScript, so that users can view and interact with that data. React.Js is JavaScript library used for building reusable UI components. According to React official documentation, following is the definition React is a library for building compostable user interfaces. It encourages the creation of reusable UI components, which present data those changes over time. Many people use React as the V in MVC. React abstracts away the DOM from you, offering a simpler programming model and better performance. React can also render on the server using Node, and it can power native apps using React Native. React implements one-way reactive data flow, which reduces the boilerplate and is easier to reason about than traditional data binding. Music has been a way for people to reduce their stress and since we all have a variety of emotions, music comes in all type of styles. For music system, you need one app for sound equalizing another for video streaming of songs and many others. Our idea is to integrate all these into a single one, which would be a boon to the music lovers.

Keywords: Music, Web-development, React.js

Abstract: This paper discusses the automation of the greenhouse by monitoring the temperature level, maintaining the soil moisture, keeping track of fertilizer level in the fertilizer tank and monitoring the light intensity. It also incorporates the intrusion detection using the pir sensor and the buzzer is turned on if the intrusion is detected, thus providing security to the greenhouse. All of this is done by integrating sensor data with arduino uno. The plant disease detection is also incorporated which predicts if the leaf of the plant is diseased or healthy. If the plant is diseased it also provides the possible solution. The sensor data from the sensors is sent to the hive mq cloud using node mcu wifi module. The user interface displays the sensor data along with the actions taken if the sensor's value increases or decreases with the set threshold. And the user interface is also provided with the plant disease detection where users can upload the leaf of the plant and check for the health of the plant and can also get the possible solution if the leaf is diseased.

Keywords: Greenhouse, Automation, IOT, Arduino uno, Temperature, soil moisture, fertilizer level, Light intensity, Intrusion detection, Node mcu, hive mq, Plant Disease Detection.

Abstract: Security may be a critical and tall issue for each sort of orchestrate. Various organize circumstances exceptionally those where computers are utilized as center points are powerless to an extending number of security threats interior the sort of Trojan worm attacks and diseases that can hurt the pc systems, servers and communication channels. In show disdain toward of the reality that Firewalls are utilized as a crucial security degree in the midst of a organize environment but still differentiating sorts of security issues keep it up developing. In organize to energize strengthen the organize from intruders, the concept of intrusion disclosure system (IDS) and interference expectation system (IPS) is picking up reputation. IDS may be a handle of watching the events happening in the midst of a computing system or organize and analyzing them for sign of conceivable event which are encroachment or up and coming threats of encroachment of computer security courses of action or standard security approaches. Intrusion shirking system (IPS) might be a handle of performing intrusion disclosure and endeavoring. This paper presents a rundown of the advancements and hence the methods utilized in Organize Intrusion Revelation and Shirking Systems (NIDPS). Interference Area and Expectation System (IDPS) advancements are isolated by sorts of events that IDPSs can recognize, by sorts of contraptions that IDPSs screen and by activity. NIDPSs screen and analyze the streams of organize packages so on distinguish security scenes. The foremost methodology utilized by NIDPSs is tradition examination. Convention examination requires extraordinary data of the thought of the preeminent traditions, their definition, how each tradition works.

Keywords: Cybersecurity, Intrusion Detection, Intrusion Prevention, Snort.

Abstract: Intrusion detection system (IDS) has recently become one of the fundamental parts of the security field. It is mainly comprised of two methods, namely anomaly detection and misuse detection. The focus of this paper is on a Network IDS (NIDS) based on feature selection by combining Support Vector Machine (SVM) and Gradient Boosted Trees algorithms. Different approaches have been used for increasing the accuracy to detect the intrusion. The first approach is the filter method using Fisher score and ReliefF score, the second one is the wrapper method and the third approach which brings novelty to this research is the combination of Fisher score and ReliefF score. However, the analysis of the technique is done using SVM with RBF-Kernel and Gradient Boosted Trees. This paper also includes Cross-Validation folds to perform a 10-flods Cross-Validation method for training and validation.

Keywords: Intrusion Detection System, Support Vector Machine, Gradient Boosted Trees, Feature ranking and selection.

Abstract: Health care sensors are playing a vital role in hospitality. Patient monitoring system, a major improvement in hospitality because of its advanced technology. In the present busy days constant monitoring of the patient’s body parameters such as temperature and heartbeat rate etc. becomes difficult. Hence to remove the burden of monitoring patient’s health from doctor’s head, we present the methodology for monitoring patients remotely using embedded technology which can provide medical feedback to the patients through mobile devices based on theinstalled sensors. The deployed embedded technology provides easy and continuous monitoring of patient and is available at a reasonable price. Keyword : Mobile Health monitoring ,IOT, Aurdino ,sensor

Abstract: Predicting academic performance is an important task for the students in university, college, and school, etc. The factors, which affect the student’s academic performance, are class quizzes, assignments, lab exams, mid, and final exams. The student’s academic performance should be informed to the class teacher in advance that will decrease the student’s dropout and increase the performance. In this paper, machine learning classification algorithms such as decision tree, Support Vector Machine (SVM), and Naive Bayes are implemented to predict the student’s academic performance. The performance of an algorithm has been evaluated based on confusion matrix, accuracy, precision, recall, and F1 score. The obtained result shows that the Naive Bayes classification algorithm performs better Record Terms – Prediction using SVM, Machine Learning.

Abstract: As the giant market demand has been pushing for its growth for a long time, Human Machine Interfaces are about to become an integral part of the future society, offering a low-cost self-powered human machine interface to many different applications. The inability to vision things around exerts psychological and social impacts on the affected person due to the lack of proper communication. Multiple research articles have been published with new inventions and research to overcome the disability and communication in the field of hand gesture recognition using technology, combining those ideas and innovating something new is the main outcome of this paper, which would be thoroughly discussed in this research study, a device is developed which is represented by a glove powered by micro controller and various sensors, these sensors help in recording the movements of hand in a desired direction which ultimately controls RC car, and many more of these sensors are used for the Blind man application and for Mouse cursor control. Thus, a system is proposed namely, Multi-Purpose Sensory glove which aims to control multiple applications just through gestures and an Android App. This paper would help new researchers to know the benefits of the device and will also get provided with valuable insights to understand and contribute to this field of technology. The working and need of the system are briefly described in this paper.

Keywords: glove; microcontroller; sensor; gesture recognition; pattern recognition; Human machine interface (HMI); classification etc.

Abstract: Corona is the new ailment that has not been identified in humans before. It is a contagious disease which makes it spread rapidly. Since the virus outbreak, thermal screening using IR thermometers are used to check human body temperature to identify infected person at public places. This method is not effective as it consumes lot of time and also close contact of infected person might lead to fast spreading of the virus. Smart Corona Protector is equipped with the facial mask detection, which will display person wearing mask or not. It also detects the person’s temperature, oxygen level and pulse rate. This project also helps to maintain social distance to reduce the spread of corona virus.

Keywords: Arduino Uno, Temperature Sensor, Oximeter, Infrared Sensor, LCD, etc.

Abstract: - In the face of the global Covid-19 scenario, the process of softening the curve of the corona virus will be difficult if citizens do not take steps to prevent the spread of the virus. With no vaccine available, social distancing is the only possible way to combat the epidemic. The proposed framework uses the YOLO v3 object detection model to identify people in the background and in-depth tracking of identified people with the help of binding boxes and assigned IDs. The model results of YOLO v3 are compared to other popular modern models, e.g. CNN-based regional speed (convolution neural network) and single-shot detector (SSD) in terms of average accuracy (mAP), frames per second (FPS) and loss values are defined by object classification and location. Later, the L2 line shown in pairwise is calculated based on the three-dimensional feature space obtained using links and the size of the binding box. The name of the infringement index is proposed to reduce the inconsistency of the public deviation process. From the experimental analysis, it is evident that YOLO v3 with an in-depth tracking scheme shows good results with moderate mAP and FPS score to monitor community deviations in real time. We are using the YOLO v3 object acquisition model and the OpenCV image processing library to run this project. The project will play an important role in an area where large numbers of people can be expected such as a shopping mall or movie theater or airport. With the help of this project we can ensure that people follow the process of socialization.

Keywords: YOLO v3, Covid-19, Social Distancing, Pretrained Model, Webcam, CNN.

Abstract: Due to the COVID-19 pandemic caused by the novel corona virus, it becomes necessary to wear facemasks every time we go out. This leads to the need of a system which can detect whether a person is wearing a face mask or not. The proposed system uses Machine Learning as the technology. It uses CNN along with OpenCV. Convolutional Neural Networks (CNN) algorithm is used to train the dataset that consists of images of people with or without face masks. The proposed system is a real time system which is able to capture the image of face in a live video stream and determine whether it is wearing a facemask or not. It is designed to increase the safety of people against COVID-19. The main advantage of the proposed system is that it helps in reducing human interaction which leads to decrease in the risk of getting infected by COVID- 19. The key concept of this system is to use Machine Learning algorithm to determine whether detected face is ‘Masked’ or ‘Unmasked’. Key Words: : Face Mask Detection, Convolutional Neural Network, OpenCV, COVID-19, Corona virus, Machine learning.

Abstract: Several people are suffering from temporary or eternal incapacities due to diseases or fates. For cases of hard or impossible walking, the use of a wheelchair is becoming essential. Manual or electrical wheelchairs are sufficient for most low and medium-level disability cases where patients can use the wheelchair helplessly. However, in simple cases, it is hard or incredible to use wheelchairs autonomously. However, in simple cases, it is hard or unbelievable to use wheelchairs independently. In such cases, wheelchair users often absent independent flexibility and rely on an important person else to switch the wheelchair. Researchers involved in a wheelchair are marking at designing smart wheelchairs to solve such problems. This paper is to review the new studies on smart wheelchair systems. It aims to evaluate the currently available technologies and to converse new coming directions for our current research plan. Key Words: Smart Wheelchair, Health Monitoring System, IoT, Android App, Physically Disabled, Temperature & Humidity Sensors, Arduino

Abstract: Automated Teller Machine (ATM) security is the field of study that aims the solutions that provides multiple points of protection against physical and electronic theft from ATMs and protecting their installations. The implementation is achieved with IOT technology. It provides real-time monitoring and control without the need for human interference. This project deals with the design and application of an ATM security system using a vibration sensor and GSM Modem. Key Words: Smart Wheelchair, Health Monitoring System, IOT, Android App, Physically Disabled, Temperature & Humidity Sensors, Arduino

Abstract: Reviews act as a valuable source of information for decision making. Online e-commerce sites has provided their users to make their opinion about products and services. Huge amount of such opinions are publicly available in the form of reviews. Manufacturers, retailer as well as customers have great interest in customer reviews. Due to large number of reviews available on internet for analysis, it is not cost worthy to read these manually. To optimize this time consuming task there is a need of an automated system which provides summarized result of user sentiments. Opinion Mining (OM) is the field of study that analyzes people's sentiments or opinion from reviews or opinionated text.Opinion Mining can be viewed as a natural language processing task, the task is to develop a system that understands the people's language. Opinion Mining is a difficult task due to ambiguous nature of human languages( like English).

Keywords: Django, API, tweepy, NLP, heroku, textblob

Abstract: In the present study, a vehicle driver drowsiness warning or alertness system using image processing technique with fuzzy logic inference is developed ,but the processing speed on hardware is main constrained of this technique. The principle of the proposed system in this paper using OpenCV (Open Source Computer Vision) library is based on the real time facial images analysis for warning the driver of drowsiness or in attention to prevent traffic accidents. The facial images of driver are taken by a camera which is installed on the dashboard in front of the driver. An algorithm and an inference are proposed to determine the level of fatigue by measuring the eyelid blinking duration and face detection to track the eyes, and warn the driver accordingly. If the eyes are found closed for 5 or 8 consecutive frames, the system draws the conclusion that the driver is falling asleep and issues a warning signal. The system is also able to detect when the eyes cannot be found. Present paper gives the overview of the different techniques for detecting drowsy driver and significance of the problem, face detection techniques, drowsiness detection system structure, system flowchart, introduction to OpenCV. The proposed system may be evaluated for the effect of drowsiness warning under various operation conditions. We are trying to obtain the experimental results, which will propose the expert system, to work out effectively for increasing safety in driving. The detail of image processing technique and the characteristic also been studied.

Abstract: In the earlier ways, the doctors need to be present physically or in several cases SMS will be sent using GSM. And the old data of the patient is displayed and also current data is displayed. In this project, we are using android application for monitoring of a patient's health conditions and displaying reports.The health care is focus on the measurement and Monitoring various biological parameters of patient's body like heart rate, oxygen saturation level in blood and temperature using a android application where patient monitor their own health condition on his smartphone using an Android application and also the patient history will be stored on the firebase authentication, that’s why doctor and patient can access the information whenever needed from anywhere and need not physically present. Health monitoring system plays a role in the overall development of the physiological as well as social well being of the society. Observance of prevention in the area of health has a significant impact on economic productivity . This project will be advantageous to traditional file and paper work of report,by using this method this will be helpful to patients to collect reports by just sitting at home.

Keywords: Monitoring System, Hospitals, Android Mobile Application, Bluetooth.

Abstract: COVID-19 has brought global crisis with its deadly spread. In the fight against the coronavirus, social distancing has proven to be a very effective measure to slow down the spread of the disease. India's government is promising to vaccinate the whole of the adult population by the end of 2021, although it’s biggest vaccine maker has been struggling to meet demand as there is shortage of raw materials therefore, social distancing is thought to be an adequate precaution (norm) against the spread of the pandemic virus. This deep learning based framework is used for automating the task of monitoring social distancing. The framework uses the YOLOv3 object recognition paradigm to identify humans in video sequences.

Keywords: COVID, social distancing, YOLO.

Abstract: COVID-19 caused many damages in all sectors such as health, economics, sports, transportation, business, etc. It affected different people in different ways. So to overcome this pandemic the most useful remedy is to follow social distancing rules. It is not possible to monitor all the places such as parks, markets, shops, malls, schools, colleges, etc. manually. It is necessary to invent tool which will automate the process of monitoring. The concept of person detection algorithm is used to accurately detect a person’s presence in areas of interest and is then followed by measuring the distance between the detected persons. Record Terms – Monitoring, distance.

Abstract: In this paper, we have proposed to transform the traditional architectural trading into an electronic exchange between the consumers and farmers in the agricultural supply chain. It is an electronic vegetable market i.e. E-Mandi making the vegetable market more accessible for the use of everyday user and even to keep the clarity in the whole system from retailer to the dealer. Also collects the current market price of the product and notify the civilian. The project contains all the details of farmers and consumer who registered in portal, this web application increases their communication of consumers for farmers, they get their price for their commodities, at same time consumer also gets good products from farmers and producers. The project will authenticate farmer using on 7/12 while sign up. The project, include farmers product details, market information, services provided, key functions, operations done, producer and consumer collaboration activities such as daily transactions, quantity available, stock, product details for future reference. All those details are provided in single portal and all those details are maintained by administrator and they give alert for any updates in portal activities for others. In this way the proposed application gives solution to one of the most important Digitization of India in the category of Farmers.

Keywords: E-Mandi, web application,7/12 Authentication, supply chain

Abstract: In this paper, we have proposed to transform the traditional architectural trading into an electronic exchange between the consumers and farmers in the agricultural supply chain. It is an electronic vegetable market i.e. E-Mandi making the vegetable market more accessible for the use of everyday user and even to keep the clarity in the whole system from retailer to the dealer. Also collects the current market price of the product and notify the civilian. The project contains all the details of farmers and consumer who registered in portal, this web application increases their communication of consumers for farmers, they get their price for their commodities, at same time consumer also gets good products from farmers and producers. The project will authenticate farmer using on 7/12 while sign up. The project, include farmers product details, market information, services provided, key functions, operations done, producer and consumer collaboration activities such as daily transactions, quantity available, stock, product details for future reference. All those details are provided in single portal and all those details are maintained by administrator and they give alert for any updates in portal activities for others. In this way the proposed application gives solution to one of the most important Digitization of India in the category of Farmers.

Keywords: E-Mandi, web application,7/12 Authentication, supply chain.

Abstract: The aim of developing attendance system is to computerized the tradition way of taking attendance. Another purpose for developing this software is to get the report automatically at the end of the session or in the between of the session.To overcome the drawbacks of the prevailing system, the proposed system has been evolved.

Keywords: Attendance Management, Report Generation, Profile Maintenance, Android App

Abstract: Data mining (DM) is an instrument of pattern detection and retrieval of knowledge from a large quantity of data. Many robust early detection services and other health-related technologies have developed from clinical and diagnostic evidence in both the DM and healthcare sectors. Artificial Intelligence (AI) is commonly used in the research and health care sectors. Classification or predictive analytics is a key part of AI in machine learning (ML). Present analyses of new predictive models founded on ML methods demonstrate promise in the area of scientific research. Healthcare professionals need accurate predictions of the outcomes of various illnesses that patients suffer from. Present statistical models of healthcare remedies have been scientifically reviewed. The uncertainty between statistical methods and ML has now been clarified. The study of related research reveals that the prediction of existing forecasting models differs even if the same dataset is used. Predictive models are also essential, and new approaches need to be improved. Here we predict the disease by using the algorithms.

Abstract: Predicting academic performance is an important task for the students in university, college, and school, etc. The factors, which affect the student’s academic performance, are class quizzes, assignments, lab exams, mid, and final exams. The student’s academic performance should be informed to the class teacher in advance that will decrease the student’s dropout and increase the performance. In this paper, machine learning classification algorithms such as decision tree, Support Vector Machine (SVM), and Naive Bayes are implemented to predict the student’s academic performance. The performance of an algorithm has been evaluated based on confusion matrix, accuracy, precision, recall, and F1 score. The obtained result shows that the Naive Bayes classification algorithm performs better Record Terms – Prediction using SVM, Machine Learning.

Abstract: The e-marketplace has emerged as an efficient and important vehicle for transactions in the e-commerce industry,academia and industry alike have recognized trust as a central factor enabling e-commerce. We need to design and implement a system that will check both buyers and sellers so that both parties will have trust in one another when transacting. Our project operates an online marketplace for consumer-to-consumer sales, particularly targeting users in emerging markets, with a view to providing a safe, reliable and efficient way for consumers to buy and sell goods. The agricultural application provides its users with information about the nearby available products like plants, seeds and agricultural machinery. Sometimes, these products may get abide due to surplus purchase. Collaterally, there are some people who may require the same quantity of products. The main features of this application includes information retrieval facilities and marketing from anywhere in the form of obtaining statistical information about fertilizers, pesticides, seeds, and plants.

Keywords: Online customer, customer behaviour, Purchase intention, Online shopping

Keywords: Project, Intranet based application, online approval of project, project reviews, tracking status,Head of Department,Project Guide, Project Coordinator,Student.  

Abstract: Doctors follow a definite procedure of collecting data of various symptoms or anomalies that a patient experiences in order to analyse the situation and treat the condition. More often than not the patient has vague memories of what and when these anomalies have occurred. We aim to make accurate records of these ailments along with when it occurred to help doctors better understand the circumstance in as little time as possible. With the help of machine learning to classify the client inputs into certain pre-recorded categories and the database functionalities to store and serve the data, the medic aid app is a user-friendly experience which is compatible across various platforms.

Keywords: Personality prediction, unsupervised learning, textblob, vader sentiment analysis

Abstract: In our routine life internet plays an important role. We use web day by day nearly for each and every work. Before e-commerce purchasing and selling were managed without internet physically in the business sectors however after the appearance of web-based business in our life has become increasingly helpful on account of its number of points of interest. The motivation behind this examination is to discover the impact and development of e-commerce and its effect on national and worldwide market. this exploration is for to see how E-Commerce as a part blasted and acquired a change the inclinations of the shopper along these lines contacting every one of their lives.

Keywords: e-commerce, internet, global market, consumer

Abstract: Facial Emotion, Age and Gender are important factors in Human Computer Interaction. According to different surveys, non-verbal components convey two thirds of human communication. Among non-verbal components, facial features are one of the main information channels. Hence, we are proposing a CNN Model to recognize the facial Emotions, Age and Gender to recognize Customer Satisfaction. The technology used is Convolutional Neural Networks from Machine Learning. The dataset consisting of pixel sets of images of people with different Emotions, Age and Gender is used to train the model. The proposed model is a real time model used to detect the face using live video stream and determine the Emotion, Age and Gender and hence in turn determine if the customer is satisfied or not. The main advantage of the proposed system is that it uses real time live video stream through webcam. The key concept of this system is to use Machine Learning algorithm to determine Emotion, Age and Gender of Customer. Key Words: Customer Satisfaction Recognition, Convolutional Neural Network, OpenCV, Emotion, Age ,Gender, Machine learning.

Abstract: In the banking domain, a high level of security must be considered and achieved to prevent a core-banking system from vulnerabilities and attackers. This is especially true when implementing Service Oriented Architecture Middleware (SOAM), which enables all banking e-services to be connected in a unified way and then allows banking e-services to transmit and share information using simple Object Access Protocol (SOAP). The main challenge in this research is that SOAP is designed without security in mind and there are no security testing tools that guarantee a secure SOAM solution in all its layers. Thus, this paper studies and analyses the importance of implementing secure banking SOAM design architecture and of having an automated security testing framework. Therefore, Secure SOAM (SSOAM) is proposed, which works in parallel with the banking production environment. SSOAM contains a group of integrated security plugins that are responsible for scanning, finding, analysing and fixing vulnerabilities and also forecasting new vulnerabilities and attacks in all banking SOAM layers.

Keywords: SOA Middleware, BPEL, Automation Security Testing Framework, Orchestrated Business Process, SOAP Protocol, Secure Banking Architecture

Abstract: The advanced technology used for the Transportation (Traffic) Crime Control System is the subject of this article. It is not possible for traffic cops to keep the radar gun at all times. Various developers and researchers have come up with a variety of techniques. The main goal is to research and classify the various types of (apparatuses), applications, and hardware that are used in the technological field. In recent years, automatic vehicle control has become a very pressing problem. It's been crucial, and various systems have been employed so far. However, as technology advances, various government agencies are challenging any kind of computerised technology to address the issue of excessive speeding. In this case, we propose a method to track vehicles that are travelling faster than the posted legal speed limit on the streets or highways. Much of this can be accomplished by the use of Internet of Things technologies (IOT).

Keywords: - IoT, Smart vehicle over speeding sensor Radar gun, Image Processing, Gaining and Transferring

Abstract: The primary purpose of this project is to reduce the time taken to solve by a specific person or group of people which may create ambiguity and chaos.To have a specific set of problems and their solutions. To increase transparency among the coding community.Reduce time consumption.Reduce cost of hiring people to solve the problem.

Abstract: In this paper the automated attendance system was introduced that reduced staff members' paperwork for attendance and also introduced classroom monitoring without visiting all departments using biometric technology. Traditionally, faculties collect student attendance using roll call on the muster. The faculties are responsible for monitoring student attendance during the semester. They must calculate the attendance % of all students for each semester. They must also warn students who are less in attendance to achieve a minimum attendance of 80% as per university regulations. This whole process is still done manually, which takes a lot of time. This issue may require a system to more accurately record student attendance and eliminate the need for manual faculty checking. The system saves the class schedule and when the class is ongoing it will be visible on the web page and semester, log in/out time, subject etc. will be visible on the screen. It will be accessible from the staff and higher authorities. The database stores the fingerprint data of all students and teachers. Whenever a student marks attendance for a particular semester, the system checks against the system's database and therefore marks that particular student's attendance for that respective semester. It will be displayed on the web page using the IOT to the respective higher authorities.

Keywords: Fingerprint, identification, Attendance database, Biometric, dashboard.

Abstract: Farming is the Prime Occupation in India and today people involved in farming belongs to the lower class and is in deep poverty. In this advanced techniques the farmers have lack of knowledge about the new technologies. The Advanced techniques and the Automated machines which are leading the world to new heights, is been lagging when it is concerned to Farming, either the lack of awareness of the advanced facilities or the unavailability leads to the poverty in Farming. After the hard work and the production done by the farmers, in today’s market the farmers are cheated by the Agents, leading to the poverty. So our solution of this problem is to provide a bridge of communication between the farmers and customers through a mobile application as F2C (Farmer to consumer). So that it can be beneficial for both ends. The farmer will be dealing with the customer directly. In our mobile application user can register as either a seller or buyer using a necessary credentials. If user register as a farmer choose seller, they can upload a product and it’s details like price quantity and life time if product life time expire then automatically product disappear at selling products. If user register as a customer choose buyer they can see whatever the products uploaded by seller and if the buyer want to buy a particular product so buyer can directly call to concerned seller through this app. So this project will provide its fruitful benefits for both farmer and customer. Keywords--- farming, deep poverty, automated machines ,cheated by the agents, fruitful, uploaded ,disappear.

Abstract: Skin disorders are common in children. Children can experience many of the same skin conditions as adults. Infants and toddlers are also at risk for diaper-related skin problems. Since children have more frequent exposure to other children and germs, they may also develop skin disorders that rarely occur in adults. Many childhood skin problems disappear with age, but children can also inherit permanent skin disorders. In most cases, doctors can treat childhood skin disorders with topical creams, medicated lotions, or condition-specific drugs. So it is very necessary to detect skin disease in early stage. Skin disorders vary greatly in symptoms and severity. They can be temporary or permanent, and may be painless or painful. Some have situational causes, while others may be genetic. Some skin conditions are minor, and others can be life-threatening.While most skin disorders are minor, others can indicate a more serious issue.

Keywords: skin disease, image processing, segmentation, etc.

Keywords: skin disease, python, web, etc

Abstract: The existing traffic light controller used almost in every city, towns, or villages utilizes a basic fixed-time method in which the time allotted to the traffic signal lights are fixed irrespective of the traffic density in that path (i.e., whether low or high). This method is inefficient and almost always leads to traffic congestion during peak hours while drivers are given unnecessary waiting time during off-peak hours. The proposed design is a more universal and intelligent approach to the situation and has been implemented using FPGA. In this project, we have proposed a design of FPGA-based Traffic Light Control (TLC) System to manage the road traffic. The approach is by controlling the access to areas shared among multiple intersections and allocating effective time between various users, during peak and off-peak hours. Theoretically the waiting time for drivers during off-peak hours has been reduced further, therefore making the system better than the one being used at the moment. Future improvements include addition of other functions to the proposed design to suit various traffic conditions at different locations.

Keywords: FPGA (Field Programmable Gate Array), Infrared Sensor, FSM (Finite State Machine), VHDL, Xilinx ISE.

Abstract: The whole world is reeling under the COVID-19 pandemic that has occurred for once in the last century. Every country including India has been fighting with this pandemic. The most effective weapon in this fight against COVID-19 is its vaccine. We need to strengthen our vaccination system with the help of technology in order to tactically face and reduce the mortality of this pandemic. So, we are presenting a vaccine distribution management system application which is, both, Android and iOS supported. In addition to this our application also asserts for door-to-door delivery of vaccines which increases the standard of immunization in various aspects. Our application vouches for “Centralized distribution and decentralized execution which is bottom-up policy of vaccine distribution. As a result of this policy, we are strengthening the reach of vaccine to those who want to travel and can get different dosages of vaccine in different part India. By enabling technology, we are also plugging the loopholes, present in our current vaccination system. Finally, our application also provides communication channel between the vaccinator and the beneficiary combat myths and misconceptions.

Keywords: COVID-19, pandemic, vaccine, Distribution Management System

Abstract: The primary goal of this project is to discuss measures to prevent occurring of accidents on rail systems, to outline an approach for death prevention on rail systems. Based on existing literature and analysis of data obtained from the Indian railway research, it was found that most deaths occur near station platforms and near access points to the track. Most of the incidents occurred most frequently when relatively more trains were in operation and in areas of high population density. Moreover, prevention measures, such as surveillance in this pamphlet surveillance system using Analog camera are described. The surveillance system using IP camera will be used. We put forward an approach, first of its kind, to collectively address conservation of living beings by preventing their death being overrun by trains and monitoring the integrity on the rail track. It utilizes a unique method for deterring the animals and the humans using cameras on turns of the rail track. Here we use the IP camera technology for detecting them, and Web socketing, open source APIs.

Keywords: Video Surveillance System, accidents & causes, Ip camera technology, living beings, esp32 AI thinker board, Web socketing, Live streaming.

Abstract: Cloud computing is a technology encompassing a set of resources and services that are offered over the internet or a network. Cloud Service Providers (CSP) provides virtual resources over the internet to its users. It is absolute necessity to have secure architecture to provide services through the cloud in safe manner. The cloud infrastructure uses virtualization extensively. Extensive usage of virtualization causes security concerns for customers of public cloud service. Virtualization alters the relationship between the OS and hardware in all the three areas namely computing, storage and networking. The data is stored in the cloud by the users for accessing whenever they need. Any compromise in the security of the data in the cloud causes loss of trust in the cloud service provider (CSP). We will discuss, in this paper, few cloud security issues in certain aspects like multi-tenancy, elasticity, availability etc. and various methods on how to overcome these security issues of the cloud. We will also discuss the techniques and approaches for security of the data in the cloud.

Keywords: Cloud Security Standards, Cloud Computing , Cloud Security, Cloud Security Standards, Security Techniques, Security Threats

Abstract: The Introduction of smart phones and tablets, we will enjoy online shopping anytime and while sitting in any a portion of the planet. Online shopping has certainly replaced the normal way of buying daily goods and clothing. When we choose online shopping, we get the advantage of credibility. Today, almost every online store offers cash on delivery, free shipping and reduced prices. These online shopping stores eliminate the hassles of parking, getting stuck in traffic jams and standing in long queues for billing. They have also benefited those people that always complain of shortage of your time. This is the rationale; majority of the people have turned to online shopping. Here, they enjoy quick access to a beautiful price range, prompt customer support, and free home delivery. There is little question that these are a number of the attractive features that catches the eye of the consumers. Although there's one small issue that would make people lose interest in online shopping; it'd not be possible to try-on clothes in such cases. Our motive here is to extend the time efficiency and improve the accessibility of garments try by creating a virtual room environment. Our proposed approach is especially supported extraction of the user image from the video stream, alignment of models and complexion detection. Extraction of user allows us to make an augmented reality environment by isolating the user area from the video stream and superimposing it onto a virtual environment within the interface. We use the 3D locations of the joints for positioning, scaling and rotation so as to align the 2D cloth models with the user. Then, we apply complexion detection on video to handle the unwanted occlusions of the user and therefore the model. Lastly, the model is covered on the user in real time.

Keywords: Virtual Dresser (VD), OpenCV

Abstract: Blockchain technology is the most trusted all-in-one cryptosystem that provides a framework for securing transactions over networks due to its irreversibility and immutability characteristics. Blockchain network, as a decentralized infrastructure, has drawn the attention of various startups, administrators, and developers. This system preserves transactions from tampering and provides a tracking tool for tracing past network operations. A personal health record (PHR) system permits patients to control and share data concerning their health conditions by particular peoples. In the case of an emergency, the patient is unable to approve the emergency staff access to the PHR. Furthermore, a history record management system of the patient's PHR is required, which exhibits hugely private personal data (e.g., modification date, name of user, last health condition, etc.). In this paper, we suggest a healthcare management framework that employs blockchain technology to provide a tamper protection application by considering safe policies. These policies involve identifying extensible access control, auditing, and tamper resistance in an emergency scenario. Our experiments demonstrated that the proposed framework affords superior performance compared to the state-of-the-art healthcare systems concerning accessibility, privacy, emergency access control, and data auditing.

Keywords: access control; auditability; blockchain; emergency access; hyperledger composer; hyperledger fabric; personal health record; privacy & security.

Keywords: Artificial Intelligence, Chat-bot, Health service, Virtual assistants.

Abstract: Depression is a mental illness that affects an individual negatively. It is considered as a serious disease by mental health care professionals. Depression detection is important to avoid unwanted consequences of not acknowledging the disease. A research was carried out in 2012 and an estimate was found. It was observed that there were roughly 258000 suicides. Further, it was observed that the age group that was mostly affected was between 15-49 years of age [1]. This estimate informs us that the aforesaid age group is prone to depression. This age bracket spends maximum time on social media and shares their view on it. It reflects their mental condition. This fact encourages us to develop a system to detect the depression level of the users and provide necessary information to the guardians to enable the guardian to take appropriate actions. The system is beneficial in informing the user and their guardian to prevent self harming or worsening of the condition. The death rate will significantly reduce if the user and the guardian are aware of the mental state of a user. The system is expected to be beneficial to reduce the percentage of death due to depression. It'll provide awareness to users and their guardians by automatically detecting depression [3]. This approach will utilize the emotions of the user detected from videos watched by the user. The title of the video indicates the content or category of the video. This enables us to get an insight to the user’s inclination towards negative polarity.

Keywords: Depression detection, NLP.

Abstract: Technological development, including machine learning, has a huge impact on health through an effective analysis of various chronic diseases for more accurate diagnosis and successful treatment. In the field of biomedical and healthcare communities the accurate prediction plays the major role to find out the risk of the disease in the patient. The only way to overcome with the mortality due to chronic diseases is to predict it earlier so that the disease prevention can be done. Such model is a Patient’s need in which Machine Learning is highly recommendable. But the precise prediction on the basis of symptoms becomes too difficult for doctor. The correct prediction of disease is the most stretching task. To overcome this problem data mining plays an important role to predict the disease. This study analyzes chronic diseases using machine learning techniques based on a chronic diseases dataset from the UCI machine learning data warehouse. We use Heart disease, Kidney disease, Cancer disease and Diabetes disease datasets, In order to build reliable prediction models for these chronic diseases using data mining techniques. The most relevant features are selected from the dataset for improved accuracy and reduced training time. The system analyzes the symptoms provided by the user as input and gives the probability of the disease as an output Disease Prediction is done by implementing the Logistic Regression. By using logistic regression, random forest and decision tree we are predicting diseases like Diabetes, Heart, Cancer and Kidney. For each chronic disease, diverse models, techniques, and algorithms are used for predicting and analyzing. The paper comprises a conceptual model that integrates the prediction of most common chronic diseases.

Keywords: Logistic Regression, Chronic Diseases, Machine Learning, Diseases Prediction and Accuracy.

Abstract: IOT is extensively used in everyday objects and its popularity is increasing day by day and Fuel reminder is a which keeps track of the fuel level and the location of a vehicle taking the assistance of GPS tracking system. It notifies the driver of the vehicle when the fuel in the petrol tank of the vehicle reaches a certain level reminding him to refill the tank. It also shows the nearby petrol filling stations with the price.

Keywords: fuel level, ultrasonic sensor, nodemcu,fuel tank.

Abstract: Basically, recommendation system generates based on profiles of users news benefits based on their past historical browsing behavior for such users who connected with the system recently as well as explicitly allowed web history. To produce personalized news recommendations, combine the information filtering mechanism with the user profiles experienced with the current collaborative filtering mechanism. To build a customized news recommendation system, use the popular micro blogging service using Facebook. The proposed research provides online news recommendation using hybrid machine learning algorithm. System initially deals with Natural language Processing (NLP) to extract the features and train the module respectively. The system can recommend the news based on user personalized history, vaious dataset have been evaluate to measure the performance analysis of system which provides better prediction accuracy accuracy than other recommendation systems. Keyword: Facebook and Twitter, Recommendation for Personalized Data, Recommendation Programs, User Profile

Abstract: each Country’s biggest plus is individuals and their contribution towards nation. This Contribution helps the country to grow the long run as we tend to referred to as it as GDP of nation. Gross domestic product (GDP) is a financial live of the value of all the ultimate merchandise and services created in a very specific fundamental quantity. GDP definitions ar maintained by variety of national and international economic organizations. This Organization collects the big variety of hands and contribute equally to nation. Any growing of Organization should have labor-intensive peoples United Nations agency puts best to figure for betterment of organization. and therefore the best Organization is taken into account to be best on condition that they lookout of worker health and supports them. For a business to reach its endeavors, its workers should be match and healthy. for excellent geographical point productivity, the health of your workers is that the determinant issue. Having physiological state within the geographical point motivates employees. It additionally reduces absence. Chronic sicknesses scale back productivity, ar chargeable for rising healthcare prices, and will be managed by the leader to cut back attention expenditures. this could be done through worker health and well-being programs, and well-designed health management initiatives. additionally, new info and communication technologies build it doable to watch worker health with wearable devices and tele-health power-assisted police investigation techniques. This paper introduces a singular new approach to Real time knowledge winning and health prediction system itself a monitor to predict the health conditions. The main benefits are: reduction within the variety of visits to the doctor throughout workplace hours; reduced dependency on institutionalized health setting like hospitals for check-ups; and previous data of worsening symptoms, thereby resulting in timely cure instead of moment hospital visits, rest home admissions, all of that result in lesser sick leaves, and a lot of productivity per worker.rather than last minute hospital visits, nursing home admissions, all of which result in lesser sick leaves, and more productivity per employee.

Abstract: Digital systems are the most important part of VLSI industry. To ensure fast computation fast circuits are required. Adders are the key component of digital design. This paper refers to the comparative analysis of various Adder circuits based on the parameters like propagation delay, no. of Look up tables utilized, no. of Input Output Blocks required and total memory utilization of adder circuit. The adder circuits like Carry Save Adder, Ripple Carry Adder and Carry Look ahead Adders are designed & simulated for 4 inputs each of 4 bit addition operation using XILINX ISE 9.2i.

Keywords: Carry Save Adder, Carry Look ahead Adder, VHDL Simulation.

Abstract: The present invention relates to a system for maintaining and controlling earth resistance. The earth resistance is maintained by controlling moisture of earth using moisture sensor. The main component of the proposed earthing system is smart earthing kit which limits the leakage current. Soil moisture sensor senses the moisture of the soil and gives data to the micro-controller. If moisture decreases microcontroller operates solenoid valve through opto-isolator and water supplied to soil. If the fault current is excessive than the conventional earthing capacity then controller circuit sense this excessive current and divert this leakage current into Smart earthing kit.

Keywords: Earthing, smart earthing system, excess current, dry earthing surface.

Abstract: Now a days, to extend popularity, the various people give the assistance of social media and various mobile applications. due to rapid development and trends of short videos, many folks use them. However, we study or take a survey on short video applications like TikTok, Roposo, Moj, Mx TakaTak, etc. These applications are easy to use, low-cost or free and also easy to forward and share to others. This application meets the present lifetime of people’s desire and demands of social media interaction. due to those applications, we will share various knowledge, technology, various activities which supplies us entertainment. We are studying those applications to boost and improve the educational experience.

Keywords: social media, Application’s Features, Short Video App .

Abstract: This article explores the potential for improved communication and allows for similar meetings to be held in the cloud in a very safe, efficient and unconventional way. The collection’s signature and key parameters are used to propose new, easy-to-understand solutions to exchange collection information so that the public can ignore many mysterious customers. From one perspective, anonymous people can discuss a brand, and if this is a basic issue, they can trace the identity of a real person. On the other hand, the nature of regular meetings is based on the basic permissions that allow multiple people to safely share and store information. The symmetrically adjusted rectangular false plane is used throughout the life cycle of the lock. It significantly reduces a person's weight and determines general temporary gain. Both hypothetical and test studies have shown that the proposed conspiracy is safe and productive for most information related to distributed computers.

Keywords: Remote Data Integrity Checking(RDIC), Message Authentication Code (MAC), Admittance, Contraption, Forestalling, Versatile.

Abstract: The corona virus COVID-19 pandemic is causing a worldwide fitness disaster so the powerful safety techniques is wearing a face masks in public regions according to the arena Health Organization The COVID-19 pandemic forced governments internationally to impose lockdowns to prevent virus transmissions. reports indicate that carrying face mask whilst at work simply reduces the hazard of transmission. An efficient and economic technique of using AI to make a secure surroundings in the course of a production setup. using this newly released technique we are able to assist many to hit upon and convey safety precautions, by means of the usage of this method many fitness and social employees will be able to discover the COVID-19 affected patients. in order that they may be privy to this and hold a distance from the individual to reduce the unfold of coronavirus disease. This machine now not only works at web sites however this approach can also be helpful for the home enterprise to discover the affected customers. A hybrid version using deep and classical system studying for mask detection are going to be provided. A mask detection dataset consists of with masks and without masks pictures, We have become to apply OpenCV to try to to real-time face detection from a stay circulate thru our webcam. we will use the dataset to create a COVID-19 masks detector with pc vision the use of Python, OpenCV, and Tensor flow and Keras. Our intention is to identify whether the character on photograph/video movement is sporting a masks or no longer with the help of computer vision and deep gaining knowledge of.

Keywords: Deep Learning, Computer Vision, OpenCV, Tensorflow, Keras.

Abstract: The corona virus COVID-19 pandemic is causing a worldwide fitness disaster so the powerful safety techniques is wearing a face masks in public regions according to the arena HealthOrganization The COVID-19 pandemic forced governments internationally to impose lockdowns to prevent virus transmissions. Reports indicate that carrying face mask whilst at work simply reduces the hazard of transmission. An efficient and economic technique of using AI to make a secure surroundings in the course of a production setup. Using this newly released technique we are able to assist many to hit upon and convey safety precautions , by means of the usage of this method many fitness and social employees will be able to discover the COVID-19 affected patients . In order that they may be privy to this and hold a distance from the individual to reduce the unfold of coronavirus disease. This machine now not only works at web sites however this approach can also be helpful for the home enterprise to discover the affected customers. A hybrid version using deep and classical system studying for mask detection are going to be provided. A mask detection dataset consists of with masks and without masks pictures, We have become to apply OpenCV to try to to real-time face detection from a stay circulate thru our webcam. we will use the dataset to create a COVID-19 masks detector with pc vision the use of Python, OpenCV, and Tensor flow and Keras. Our intention is to identify whether the character on photograph/video movement is sporting a masks or no longer with the help of computer vision and deep gaining knowledge of.

Keywords: Deep Learning, Computer Vision, OpenCV, Tensorflow, Keras.

Abstract: In order to improve the economy of India, agricultural growth is very important. This demands small and marginal scale agriculture farmers to become efficient and self-sustaining. A mobile application that the farmers can use to hire tractors as well as other mechanizations at a nominal amount all using their mobile phones. This would not only help them avoid manual labor but can also be considered as an important step to encourage this profession. Using this software for farmers to hire farming equipment like tractors and other machines. We proposed a system to make the farmers aware of the current market rate of the product. This type of system is very beneficial for the young generation to adapt to the traditional farming technique. It will increase the easy access to farm mechanization solutions through rental of tractors and farm equipment for small and marginal farmers. The benefits of our project is Avoid bidding problems and Cost is not the issue because of the mobile based application.

Abstract: A Hotel management system is a computerized management system. This system keeps the records of hardware assets besides software of this organization. The proposed system will keep a track of Workers, Residents, Accounts and generation of report regarding the present status. This project has GUI based software that will help in storing, updating and retrieving the information through various user-friendly menu-driven modules. The project “Hotel Management System” is aimed to develop to maintain the day-to-day state of admission/Vacation of Residents, List of Workers, payment details etc. Main objective of this project is to provide solution for hotel to manage most of their work using computerized process. This software application will help admin to handle customer’s information, room allocation details, payment details, billing information, etc.

Keywords: Customer’s Information, Room Allocation Details, Payment Details, Billing Information.

Abstract: Now-a-days saline level monitoring is done manually by hospital staff. They usually have to check the level of the bottle in regular intervals and to identify problems while electrolyte entering into the body. But it sometimes causes risks of blood reverse flow. So, there is a need for a design which automates the saline monitoring system. So, our aim is to design a ready-made portable system for such bottles. Ready-made wearable sensors on the sides of the bottle can detect the level/weight of fluid inside the bottle and stop the flow of saline when there is a need to stop fluid flow like high pulse rate or saline bottle becomes empty.

Keywords: Saline, level monitoring, ready-made portable system, abnormal pulse rates.

Abstract: License, Insurance Certificate, RC Book, Pollution Certificate all these things are required for every individual so that we need to submit these documents when it is needed. So, we decided to create the QR-Code and dump all these in QR code so that whenever we need to access these, we can do it in an easier way. We are living in a world where everything is digitalized to keep the human effort to minimum. In such a world we are still using the hard copies of RC book, Pollution certificate etc. By carrying these there may be a possibility of damage to the certificate and we may not carry them with us sometimes. Authenticating these proofs by a traffic police may take some time and sometimes we may be in a hurry. In order to simplify this problem, we are proposing a solution which is to store the soft copies of all the required documents in a QR. By providing a QR which contains all the required documents we can easily carry them and it is to use them when it is needed.

Keywords: QR code, Documents, Website, Traffic Police, Citizens.

Abstract: In today’s world communication has become so easy due to integration of communication technologies with internet. However, the visually challenged people find it very difficult to utilize this technology because of the fact that using them requires visual perception. Even though many new advancements have been implemented to help them use the computers efficiently no naive user who is visually challenged can use this technology as efficiently as a normal naive user can do that is unlike normal users, they require some practice for using the available technologies. This paper aims at developing an email system that will help even a naive visually impaired person to use the services for communication without previous training. With the help of this tool the voice can be transformed into text and from text to voice. This project will completely eliminate the use of keyboards and we would be able to access the things only by using our voice and mouse click. The normal person can also be used this system for read purpose. The system will not let the user make use of keyboard instead will work only on mouse operation and speech conversion to text. Also, this system can be used by any normal person also for example the one who is not able to read. The system is completely based on Interactive Voice Response (IVR) which will make it user friendly and efficient to use.

Keywords: Speech to Text, Text to Speech, IVR, Speech Recognition.

Abstract: In our country, the economy is mainly based on agriculture and agriculture are depends on the monsoons which is not sufficient source of water. So the irrigation is used in agriculture field. In Irrigation system, depending upon the soil type, water is provided to plant. India has a major problem for daily changes in the weather conditions and soil moistures. Our aim is to provide information about the soil moisture, humidity, temperature of the soil and irrigate the field incorporating weather condition. Primary focus is to save water and reduce human intervention in the agriculture field. In this technology, the humidity and temperature of plants are precisely controlled. The main objective of our irrigation system is to make the system more innovative, user friendly, time saving and efficient system using IOT.

Keywords: Agriculture, Irrigation, Soil moisture, Humidity, Temperature

Abstract: In this project we are providing a smart solution for contractor and worker by providing an interface between workers and contractors. The contractor update the information of work in this application along with the location. Worker can select the work based on location and type of work, Then worker can directly contact with the contractor if he is willing to work. For this we are developing a android based mobile application, So that Contractor can upload work details. Workers based on location and type of work he can directly contact with the contractor.

Keywords: QR code, Documents, Website, Traffic Police, Citizens.

Abstract: Now a days roads are getting over crowded, especially in cities.Themain goal of our projection build a traffic regulation system which is able to detect the vehicles in traffic.Based on the count of the vehicles the signal shift to the next traffic signal. A webcam isused in each stage of the traffic light in order to take pictures of the roads. Count of vehicles in these images are calculated by using opencv with python and shifts the signal by using aurdino based micro controller.

Keywords: Open CV, Image Processing,Aurdino,Micro controller.

Abstract: The human face is an important organ of an individual‘s body and it especially plays an important role in extraction of an individual ‘s behaviour and emotional state. Manually segregating the list of songs and generating an appropriate playlist based on an individual‘s emotional features is a very tedious, time consuming, labour intensive and upheld task. Various algorithms have been proposed and developed for automating the playlist generation process. However, the proposed existing algorithms in use are computationally slow, less accurate. This proposed system based on facial expression extracted will generate a playlist automatically thereby reducing the effort and time involved in rendering the process manually. Thus, the proposed system tends to reduce the computational time involved in obtaining the results and the overall cost of the designed system, thereby increasing the overall accuracy of the system. Facial expressions are captured using an inbuilt camera. The accuracy of the emotion detection algorithm used in the system for real time images is around 85-90%, while for static images it is around 98- 100%. Thus, it yields better accuracy in terms of performance and computational time and reduces the designing cost, compared to the algorithms used in the literature survey. Based on the obtained emotion, playlist is created.

Keywords: Music suggestion, Facial Recognition, SVM, OpenCV, Python.

Abstract: India is mainly an agricultural country. Agriculture is the most important occupation for the most of the Indian families. It plays vital role in the development of an agricultural country. In India, agriculture contributes about 16% of total GDP and 10% of total exports. Water is main resource for Agriculture. Irrigation is one method to supply water but in some cases there will be lot of water wastage. So, in this regard to save water and time we have proposed project titled automatic irrigation system using IoT. In this proposed system we are using various sensors like temperature, humidity, soil moisture sensors which senses the various parameters of the soil and based on soil moisture value land gets automatically irrigated by ON/OFF of the motor. These sensed parameters and motor status will be displayed on user android application

Keywords: Arduino control unit, Moisture Sensor, Temperature Sensor, Water Pump, Plant.

Abstract: One of the most common forms of online advertising, particularly for second-hand goods, is classified advertising. The variables and qualities of online classified ads, such as structured data and free text that may affect the advertising's performance in terms of closing sales are explored in this study. Buyers are hesitant to buy second-hand products (whether used or not) from strangers on the internet, which is one of the biggest issues in the resale of second-hand products. Its goal is to use an online platform to connect potential buyers with sellers in a hyper local community, where buyers may see the sellers' products and make offline contact with them.

Keywords: Classified Ads, Optimization, Hyper local Community, investigation.

Abstract: Traffic sign detection and recognition plays an important role in expert systems, such as traffic assistance driving systems and automatic driving systems. It instantly assists drivers or automatic driving systems in detecting and recognizing traffic signs effectively. In this paper, a novel approach for real-time traffic sign detection and recognition in a real traffic situation was proposed. First, the images of the road scene were converted to grayscale images, and then we filtered the grayscale images with simplified Gabor wavelets (SGW), where the parameters were optimized. The edges of the traffic signs were strengthened, which was helpful for the next stage of the process. Second, we extracted the region of interest using the maximally stable extremal regions algorithm and classified the superclass of traffic signs using the support vector machine (SVM). Finally, we used convolution neural networks with input by simplified Gabor feature maps, where the parameters were the same as the detection stage, to classify the traffic signs into their subclasses. The experimental results based on Chinese and German traffic sign databases showed that the proposed method obtained a comparable performance with the state-of-the-art method, and furthermore, the processing efficiency of the whole process of detection and classification was improved and met the real-time processing demands.

Abstract: The agricultural application provides a good pesticide to the farmers . If a user searches the details about the disease of the crop then it directly shows the pesticide which is related to that disease . Then farmers or the end users directly look into the details of the pesticide and finally user gives a feedback. Generally , farmers do the farming but actually they don’t know which pesticide to use for the each and every crop , they may confuse and keep wrong pesticides which effect their crop. So for this , we will create an application and in that if they searches the disease of the crop it automatically suggests the pesticide related to that.

Keywords: Farmer , Application , Pesticide , Crop Disease , Feedback

Abstract: Social networks have been developed as a great point for its users to communicate with their interested friends and share their opinions, photos, and videos reflecting their moods, feelings and sentiments. This creates an opportunity to analyse social network data for user’s feelings and sentiments to investigate their moods and attitudes when they are communicating via these online tools. Mental health issues are widely accepted as one of the most prominent health challenges in the world, with over 300 million people currently suffering from depression alone. With massive volumes of user-generated data on social networking platforms, researchers are increasingly using machine learning to determine whether this content can be used to detect mental health problems in users. This study aims to develop a model to classify users with depression via machine learning techniques, which can learn from user-level labels to identify post-level labels .By combining every possibility of posts label category, it can generate temporal data which can then be used to classify users with depression. This project shows that there are clear differences in posting patterns between users with depression and non-depression, which is represented through the combined likelihood of posts label category.

Keywords: Depression, Social Network, Feelings, Analyse, Detection.

Abstract: This project is an attempt to provide the advantages of online shopping to customers of a real shop. It helps buying the products in the shop anywhere through the internet by using this website. Thus, the customer will get the service of online shopping and home delivery from his favorite shop

Abstract: Logistics is a global supply chain network, it involves many stakeholders such as brokers, raw materials providers and so on, complicating the end-to-end visibility. In the present system, Security is the biggest challenge faced by Internet of Things. In logistics system, when the parcels are delivered from one warehouse to another warehouse the code is entered manually by the data entry operators, it is time consuming and it may lead to any fraud activities. And if there is any delay in the delivery of parcels by the truck due to breakdown both the company and the client will not have any knowledge about the delay. Inorder to overcome this, in the proposed system, Blockchain and IoT are combined together which help to enhance the reliability and traceability of the network. This helps the customers and the logistics company to get the exact information of the product. As Block Chain is decentralized, it helps in reducing the bottlenecks as we don’t need any certification from the third parties . The concept of IOT is used whose components are applications, gateways, processors and sensors. From the collected data, application block is utilized and for sending processed data to appropriate location gateways are used. And sensors are used to share data to its nearby actuators. Integrating block chain or distributed ledger provides security for the Internet of Things. The major elements of this project are the QR code or barcode scanner Arduino board, Impact sensor, and the GPS module. All this information is stored on cloud database and is retrieved as and when required from the admin monitoring application. This project presents an attempt to implement Blockchain, Iot and Cloud computing technology to reduce the risk in regard to fraud or to deliver right products by live Monitoring of products by using QR code or Barcode details on products in carrier to ensure security of the products.

Keywords: IoT, Cloud Computing, Blockchain, Decentralization, Immutable data.

Abstract: Nowadays journey is most important, however to make it more convenient it is important to do some preliminary checks before beginning your journey. A pet could get under the car, alert the owner honk the horn before starting the engine. Every year when the weather gets colder, pets take the rest under the cars and are killed accidentally. many pets die due to this way every year“ so in order to save pets our software observes if any pet animal is present under the car. If at all any pet animal is present it instructs the owner by giving an alert message. For example, image classification is straightforward, but the differences between object localization and object detection can be confusing, especially when all three tasks may be just as equally referred to as object recognition.

Abstract: License, In the forest near rural areas, there are so many losses of lives because of wild animal attacks. At night human can’t see the animals but animals can see the human and attack them, so it may lead to life loss. For this problem government provides cameras to monitor that type of places and it is not possible to monitor for every time. To overcome that problem, we upgrade that cameras by using Artificial Intelligence. Our camera detects and monitor animals 24/7 by using some AI algorithms, we detect the animals which are harm to the humans and gives a buzzer sound to make people alert and also to interrupt animals from there thinking. At the same time it send notification to the forest department as picture and warning message .In this proposed system, animal data set training and testing is processed and we make them easy to capture the visuals of the wild animals .We capture and analyse these pictures of the wild animals and store them in our database for future use.

Keywords: Wild Animals, Capture, Alert, People, Forest Department.

Abstract: In this paper we propose a Go-Kart Management 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 Chabot, Go Kart.

Abstract: The kidneys in the human body attached to the cleaning and filtering of the blood and other body fluids and removing the toxins and other waste by-products from the body. This is an essential function as the accumulation of these impurities can hinder the functioning of other organs and lead to a toxic level of these chemicals in the body. This inefficient function of the kidneys can lead to a lot of different problems and can also cause death. Chronic kidney disease is highly difficult to predict before time and the earliest stages are very difficult to analyze retrospectively. Therefore, a number of researchers for the identification of chronic kidney diseases have been effectively analyzed in this survey paper. The methodology achieved through this analysis utilizes machine learning protocols for the purpose of chronic kidney disease identification which will be further expanded in future research.

Keywords: K-Mean Clustering, Pearson Correlation, ANN, Decision Tree

Abstract: The improvement in various medical facilities has allowed the improvement in the life of a lot of individuals. This has also exposed people that are susceptible to certain illnesses that affect one of the core organs of the human body. This has been one of the most serious medical issues that have put a pressure on the health-care system in recent years. This is a troubling development that has resulted in more complications and deaths as a result of kidney disease. Due to the fundamental nature of these diseases, which necessitates comprehensive testing and diagnosis, these kidney disorders are particularly difficult to detect. The delay in receiving the results causes a delay in delivering prompt treatment to the patient, which is critical for kidney illnesses, as failure to do so can end in a lot of pain for the patient or even death. Therefore, an automatic approach for the diagnosis is needed to achieve prompt kidney disease detection through the use of machine learning methodologies. This research article describes a precise kidney disease detection mechanism that utilizes K Nearest Neighbor and Pearson Correlation along with Artificial Neural Network and Decision Tree. The experimental results indicate a positive performance for the detection that is highly satisfactory. Keywords— Kidney Disease Detection, K-Nearest Neighbors, Artificial Neural Network, Decision Tree.

Abstract: Heart arrhythmia may be a heart state during which the heartbeat is irregular. The heartbeat possibly is excessively quick, excessively slow, or unstable. Electrocardiography (ECG) is utilized for the detection of heart arrhythmia. Since ECG signals reflect the physiological states of the heart, specialists use ECG signs to analyze heart arrhythmia. Thus, the advancement of programmed procedures for recognizing strange states of ECG signals from the everyday recorded ECG information is of crucial significance. Additionally, ideal medical aid measures can be successfully applied if such unusual heart conditions can be distinguished naturally utilizing the wellbeing observing gear which will inside utilize the Machine Learning algorithms.

Keywords: Electrocardiography, ECG, Machine Learning, cardiac arrhythmia

Abstract: Traffic obstruct is one of the huge issues in India and it is especially common in the metropolitan cities. Packed roads and traffic jams can result in a dreadful situation. Some of these mainstream traffic problems include- Poor road quality due to excessive traffic. The extreme congestion of urban roads due to heavily used private vehicles leads to the degradation of the quality of the roads. This leads to traffic problems most of the times. The sheer magnitude of traffic problems also gives rise to other health problems. In today's scenario the traditional approach works efficiently only if the count is sparse, as the density of vehicles on a particular side of road increases or if the traffic is comparatively larger on one side than other side in such case the approach fails. So, in the proposed solution the switching time of signal will be decided based on real time data with good accuracy in dense traffic. This solution can prove its most effectiveness in releasing the congested traffic at an efficient and faster rate by controlling the signal using HERE guides API.

Keywords: Traffic control, traffic clog, congestion, API, traffic signal algorithm, machine learning.

Abstract: The threat because of fire has become increasingly serious to people’s lives and property. To overcome the problem of traditional fire detection i.e., false alarm rate, we proposed an innovative detection method based on multi feature fusion of flame. First, it is considered as fire pre-processing stage where we combined the motion detection and colour detection of the flame. Second, flame has a certain similarity in the sequence of the image, even though it is irregular. Then, we included some features extraction to improve the accuracy of recognition. The new features are of spatial variability, shape variability, and area variability of the flame. At the end, we used a support vector machine for training and completed the analysis of candidate fire image. Thus, achieved automatic fire monitoring. The method can also be applied to real-time camera monitoring systems, like home security, forest fire alarms, and commercial monitoring.

Keywords: flame, camera, fire detection, alarm, monitor, SVM, fusion.

Abstract: Malaria is caused by “female Anopheles” mosquito. Mosquito transmits the Plasmodium Parasite to the blood which causes Malaria. The conventional method to diagnosis malaria is to examination of blood cell of patient in the microscope. The blood cell to be tested is kept in a slide then, observe the infected RBC under the microscope. This process consumes more time and expensive. Here we construct the image processing system detection and later we develop a machine learning code to detect the infected cells. We find out the accuracy using Keras-Sequential Model. In our project we will get the fast and accurate result. We try the keras model using SVM classifier. SVM have a positive rate of 99.8% in the detection of the plasmodium infected. Below average people living in village areas who lack of access to health care are at the greater risk for the disease. World Health Organization estimates that the India has a 15 million cases of the malaria with 19,500-20,000 deaths annually.

Keywords: Plasmodium, Machine Learning, Female Anopheles, Parasite

Abstract: Leukemia (blood cancer) begins in the bone marrow and causes the formation of a large number of abnormal cells. The most common types of leukemia known are Acute lymphoblastic leukemia (ALL), Acute myeloid leukemia (AML), Chronic lymphocytic leukemia (CLL) and Chronic myeloid leukemia (CML). This thesis makes an effort to devise a methodology for the detection of Leukemia using image processing techniques, thus automating the detection process. Our project consists of development of a machine learning algorithm to detect cancer using microscopy image. Keywords—LeukemiaDiagnosis,convolutional neural networks, Leukemia types

Abstract: According to a search, we found the statistics of the disability population in our country is very high. So, we came to know that the count of physically disabled people is increasing day by day. Across hospitals and NGOs serving disabled people. These people are not capable of full-body movement as compared to a normal person and also, they need a caretaker always along with them to do activities. In such a situation we propose a system that helps disable person display a message by just simple motion of any part of his/her body. The main aim of the proposed system is to implement a low-cost reliable system that will help to establish communication between disabled patients and family caretakers. We are using an accelerometer device which is used to detect the motion. It is the device that is used to detect the motion. Our system provides a reliable and important solution to various issues faced by caretakers in traditionally communicating with disabled people and helps them to be in independent mode.

Keywords: Quadriplegia, Disability, Motion, Accelerometer.

Abstract: In the era of smart life, wearable devices are revolutionalizing health care. Estimating the heart rate of a person to monitor their health and fitness is an integral part of using wearable devices that contain Photoplethysmography (PPG) sensors. Though the PPG sensor gives an easier estimation of heart rate when compared to electrocardiography (ECG), the motion artefacts can act as an impediment affecting the accuracy and thus 3D accelerometer sensor is also used to combat this. This paper proposes a novel approach in order to classify and estimate heart rate while performing activities using machine learning models. The results of which show that an accuracy of 96.67% is obtained when the Random Forest classifier is used followed by other ensemble classifiers like Bagging and AdaBoost classifiers.

Keywords: Wearable devices, PPG sensor, 3D Accelerometer, heart rate estimation, activities.

Abstract: In the recent world, as we all know the covid-19 this pandemic has arisen all over the world. This pandemic has affected our day-to-day life-disrupting our movements and also world trade. This pandemic has not only affected our movements but also results in the death of many people all around the world. And so to soothe the condition main contri-bution which is asked nowadays from all the citizens is to follow all the safety norms that are to wear facemask all the time immediately whenever they are stepping out of their home then to use hand sanitizer and maintain social distancing whenever they come in contact to any other person. This paper proposes one of the systems to ensure that at least all peo-ple who are coming under Webcam/phone’s camera or any video stream wears masks and that too in a proper way. In this system, we are using a basic Convolutional Neural Network(CNN) model using TensorFlow with Keras library and OpenCV to detect if people are wearing a facemask to protect themselves. And we created a dataset of various images to train a neural network. This method attains training accuracy and validation accuracy which is nearly up to 99.87% and 94.41% respectively. This system is also designed in such a way that if it found out a person with no mask or not wearing the mask in a proper way then alarm buzz outs to alter. In this paper, we propose a system that restricts the growth of coronavirus by finding out those people who are not wearing any facemask by monitoring with cameras.

Abstract: Predicting the student’s emotional engagements using Computer vision techniques are a challenging task. There are several works on computer vision based affective state recognition of students in the e-learning environment, there are limited works on affective state recognition of students in the classroom environment where more than one Student are present in a single image frame. Face recognition has become an attractive field in computer-based application development in the last few decades. The learning process has also evolved a lot. However, the emotion of students is usually neglected in the learning process. This project is mainly concerned about using facial expression to detect emotion in the learning environment. There are many algorithms for facial recognition and emotion capturing out of which we have used Convolutional neural network (CNN).The captured facial expression will be used in the Learning Environment for analyzing the learner mood. The proposed architecture uses the students’ facial expressions for analyzing their affective states. The experimental results will predict the probability of affective states of the faces detected in learning environment for understanding of emotions during learning process in order to enhance the learning and feedback achieving process.

Keywords: Face Detection, Face emotion recognition, Convolution neural network, OpenCV, Machine learning.

Abstract: This study primarily focused on detecting credit card fraud in the real world. For the qualified data set, we must first collect credit card data sets. Then, based on the user's responses, deliver inquiries to test the data set, use a credit card. Following the random forest algorithm employing a classification approach with a data set that has previously been examined and supplying a current data set. Finally, the data accuracy of the outcomes is improved. After then, a number of attributes will be processed so that fraud detection can be noticed when looking at the graphical model's depiction. Credit Card Fraud Detection is a typical sample of classification. In this process, we have focused on analyzing and pre-processing data sets as well as the deployment of multiple anomaly detection algorithms such as Local Outlier Factor and Isolation Forest algorithm on the PCA transformed Credit Card Transaction data.

Abstract: In changing times, working parents have become quite common in today's developing world. This has led to an increase in the demand for products that help parents care for their children. This paper aims to show the Infant Care Assistant who uses the IoT sensor network and the Raspberry Pi to collect information on the baby's current state and its surrounding and changing ways to soften a troubled baby's. The facilitator also includes a cry detection unit based on the vector classifier support, a cry analysis unit according to the random forest layout and an emotional awareness unit according to the mini Exception convolution neural network model. In addition, it saves data using phpMyAdmin and private servers and installs graphical interface built using HTML5 and CSS. The results of the proposed tests show that this helper can reduce the burden on parents and make them more able to care for their children.

Keywords: Audio processing , IOT sensor Network.

Keywords: Renasas Controller, YOLOv3, RFID, Emergency Vehicle, Accident

Abstract: Refrigerator is the most frequently used domiciliary/kitchen electrical appliance all over the world for food storage. Kitchen is one of the most prominent zones of intelligent appliances, one of those devices is refrigerator. The Internet of Things (IoT) refers to the set of devices and systems that interconnect real world sensors and actuators to Internet. Principally this appliance is used for various tenacities like storing vegetables, fruits etc. Smart refrigeration module is designed to transfigure any existing refrigerator into a smart cost-effective machine using sensors. Smart refrigerator compares the status of the food for e.g., Weight, quantity etc. Significance of this work will be removable of food spoilage, reduce illness and make healthier lifestyle of modern age human being. The provision of recipe suggestion based on the vegetables present in the basket is carried out through a basic machine learning algorithm which classifies the vegetables based on the colors which in turn suggests a particular recipe. It will be smart enough to notify the current status of food items through an android app on our mobile phone. Key Words Smart refrigerator, android application, internet of things

Abstract: The road accident data analysis use data processing techniques, focusing on identifying factors that affect for accidents. However, any damage resulting from road accidents. Some of them are internal to the driving force but many are external. For example, adverse weather like fog, rainfall or snowfall causes partial visibility and it may become difficult as well as risky to driver on such roads.

Abstract: Our paper is to focus on the implementation of an effective health monitoring system and as we know security plays an important role in every industry which also has fingerprint sensor for authentication of right person. Portable devices become an interesting topic in the field of technological research and gain lot of attraction due to its small size. It allows us to take it to any location where we want with each other over the internet. The proposed system monitors the vital health parameters and transmits the data through a wireless communication through Wi-Fi module. The data can be accessed any time using mobile app.

Keywords: Microcontroller STM32F103, Finger print sensor, Pulse oximeter, Temperature sensor, GPS module, Wi-Fi module.

Abstract: The automatic classification of animal images is an onerous task due to the challenging image conditions, especially when it comes to animal breeds. Checking of wild animal in their common environment is crucial. This proposed work develops an algorithm to detect the animals in wild life. Since there are many different animals manually identifying them can be a difficult task. This algorithm classifies animals based on their images so we can monitor them more efficiently. Animal detection and classification can help to prevent animal-vehicle accidents, trace animals and prevent theft. This can be achieved by applying effective deep learning algorithms. Key word: Animal Detection, Deep Learning Algorithm

Abstract: The sudden increase in COVID-19 patients is overwhelming healthcare systems across the world. It is difficult to test every patient with COVID -19 symptoms due to limited testing kits (RT-PCR) available. The tests take long time, and they have limited sensitivity. Detecting COVID-19 infections using Chest X-Ray will help quarantine high risk patients while test results are awaited. In this work we use the chest X-Ray to prioritize the selection of patients for further process. It will also be useful where the to decide whether to keep the patient in the ward along with other patients or isolate them in COVID-19 areas. It is also useful in identifying patients with high likelihood of COVID with a false negative RT-PCR who would need to undergo repeat testing again.

Keywords: COVID-19, RT-PCR, severe acute respiratory syndrome coronavirus 2 (SARS-CoV- 2)

Abstract: Food wastage is based on python application whose point is to improve the quality in the administration of dispersing the food which is waste at wherever of mass food. Now it will be distributors are challenge with numerous difficulties to do the procedure. The Major issue is correspondence among the convince strain to shelter. It strains well to correspondence among the wholesalers. The point of the venture is to digitalize the social event of food and also to convey it to halfway of houses that are generally close by. The Analysis of the weight of food and all-out individuals who are living in the shelter has appeared as changing styles of the chart.

Keywords: Wastage, Orphanage, Go no waste, Food for Needy, Wastage of food.

Abstract: Traffic accidents on city streets are the consequence of coordinated activities by numerous elements, including humans, vehicles, roadways, and the environment. It is important to mine the connection rules between significant risk factors from the statistics on these incidents in order to determine the primary causes of these accidents. This method enhances the Apriori algorithm to mine the association rules between risk factors and probes deep into the causes of traffic accidents on urban roads, taking into account the many layers and dimensions of accident data. The parameters like support, confidence, and lift were modified according to the layer and dimension of certain characteristics in order to find qualifying association rules between risk factors. The findings were then filtered to provide a set of useful association rules. The system's data allow the traffic department to develop appropriate accident-prevention strategies and improve traffic safety on city streets. The major goal of the system is to discover the link between traffic accident risk variables and accident kinds. By analysing the key accident variables, the system was built as an automation to decrease road accidents

Abstract: According to incidence statistics, colon cancer is one of the most common types of cancer in the world. The correct diagnosis of this lesion will provide cancer patients with the most appropriate treatment. Diagnosis is made through visual analysis of tissue samples by a pathologist. This analysis is affected by intra-pathological and inter-pathological variation, and is also a complex and time-consuming task. In order to solve these problems, imaging techniques have been developed to be applied to histological images obtained by digitizing tissue samples. To this end, characterization and classification techniques are being explored to help pathologists and achieve faster and more objective diagnostic determinations. Therefore, this paper proposes a method that combines multi-dimensional fractal technology, curvature transformation and Haralik descriptors for research and captains. Detect colon cancer that has not been studied in the literature. The proposed method considers feature selection methods and various classification methods.

Keywords: colorectal cancer, feature associations, multiresolution features, fractal techniques, curvelet transforms, haralick descriptors.

Abstract: A countless number of people drive on the highway day and night. Taxi drivers, bus drivers, truck drivers and people traveling long-distance suffer from lack of sleep. Due to which it becomes very dangerous to drive when feeling sleepy.Drowsiness detecting device is solution for avoiding accidents. Key word: Drowsiness Detecting, Machine Learning.

Abstract: Oral cancer is a major global health issue accounting for 177,384 deaths in 2018 and it is most prevalent in low- and middle-income countries. Enabling automation in the identification of potentially malignant and malignant lesions in the oral cavity would potentially lead to low-cost and early diagnosis of the disease. Building a large library of well annotated oral lesions is key. As part of the MoMoSA (MobileMouth Screening Anywhere) project, images are currently in the process of being gathered from clinical experts from across the world, who have been provided with an annotation tool to produce rich labels. A novel strategy to combine bounding box annotations from multiple clinicians is provided in this project. Further to this, deep neutral networks were used to build automated systems, in which complex patterns were derived for tackling this difficult task. Using the initial data gathered in this study, two deep learning-based computer vision approaches were assessed for the automated detection and classification with ResNet-101 and object detection with the Faster R-CNN. We create a methodology to extract features from image and implement genetic algorithm and apriori algorithm for association mining to get accuracy more in results. Key Words: Malignant lesion, Machine Learning

Abstract: The importance of online news articles has evolved with the advancement of information and technology. How people gather information, shape their views, and engage with topics of relevance has been increased by the internet. Thus news articles become important sources and play a significant role in shaping personal and public opinion. Predicting polarity in news articles becomes crucial to have a well-balanced understanding of any event. Using aspect-based sentiment analysis, the application predicts sentiments attached to various aspects of a particular Hindi news article. Our approach consists of sentence identification using POS tagging techniques followed by aspect extraction using unsupervised learning algorithms and finally predicting the sentiments of the aspects using sentiment analysis. The predicted sentiments would be displayed in a user-friendly format so that the users can easily understand them. Existing systems work on the English language unlike our approach for sentiment analysis

Keywords: News Articles, Polarity, Sentiment Analysis, Topic Modeling, RNN

Abstract: Images obtain in poor environmental circumstances has poor visibility. These images limit the performance of many imaging systems. Many techniques have been implemented in the literature to handle this issue. However, designing an efficient channel prior to restore hazy images is still an open area of research. The comprehensive review of the existing techniques has shown following gaps in the literature: The hyper-parameter tuning of Gradient channel prior has been ignored in the literature. An efficient tuning has an ability to improve the results further. Most of existing techniques still suffer from texture distortion issue. Therefore, a suitable gradient aware channel prior is proposed to handle these issues. Extensive experimental results show that the proposed technique has an ability to remove the limitations of existing techniques.

Keywords: Dehazing, Hazy images, Gradient, Channel prior.

Abstract: The voice is a prominent tool allowing people to communicate and to change information in their daily activities. However, any slight alteration in the voice production system may affect the voice quality. Over the last years, researchers in biomedical engineering field worked to develop a robust automatic system that may help clinicians to perform a preventive diagnosis in order to detect the voice pathologies in an early stage.

Keywords: Block chain, RFID, cloud computing, edge computing livestock, monitoring.

Keywords: blockchain technology, digital invoices, graphic image processing, artificial intelligence, OCR

Abstract: Lately, wearable gadgets have been an arising pattern available. However, late investigations show that individuals desert their wearable gadgets two or three months. One of the fundamental reasons assumed is the specialized look and feel of the gadgetry gadgets and accordingly, an insufficient appropriateness for everyday use. Computerized adornments, the idea of disguising innovation behind chic gems, is a promising approach to resolve this issue. In any case, little exploration has been done to unmistakably define the necessities for computerizes adornments. In this paper we present the plan and aftereffects of an online study, in which we explored, which prerequisites are significant for computerized adornments, and how significant specific necessities are seen by possible clients. By and large, members thought about usefulness, structure factor, and between activity and show plan as vital, while they discovered body area, setting mindfulness and customizability less significant. We additionally found non-similarities in the significant appraisals, which are identified with gender and age. Our outcomes will help fashioners of advanced Jewellery to zero in on the right, yet additionally on the more significant necessities first.

Keywords: Digital, Wearable, Jewellery, Smart, Wireless.

Abstract: Nowadays, implemented different software applications, increasing user engagement. Social influence plays an important role in product marketing. Our Social Media creates an online user group and shares their experiences, interests and views with each other. To provide better service to users and grow a business, there is a need to analyze user interest, need, preferences, and habits. The social circle and influence of people in contact also matters to the user's purchase. Sequential actions of friends and temporal autocorrelation influences user point of interest. Design and development of proposed work includes recommendation generation based on deep learning. Recommender systems which can utilize information in social media, newspaper, TVs, internet, including user preferences, item's general acceptance, and influence from social friends. This paper includes the study of various sequential modelling techniques. Based on the study of existing system, a new system is proposed for sequential modelling.

Keywords: Recommender Systems, Social Media, Machine Learning.

Abstract: Lung cancer is cancer that start in the lungs. Cancer is a disease where cancerous cells grow out of manage, taking over normal cells and organs in the body. The early detection of lung cancer is the most useful way to decrease the mortality rate. In this document we contrast two methods, a modified Hopfield Neural Network (HNN) and a Fuzzy C-Mean (FCM) Clustering Algorithm, used in segmenting sputum color metaphors. The segmentation grades will be used as a base for a Computer Aided Diagnosis (CAD) system for early detection of lung cancer. The manual analysis of the sputum samples is time overriding, inaccurate and requires intensive qualified person to avoid diagnostic errors. Both methods are designed to classify the image of N pixels along with M classes or regions. Due to intensity variations in the background of the raw images, a pre-segmentation process is developed to normalize the segmentation process. In this learn, we used 1000sputum color metaphors to test both methods, and HNN has shown a better classification result than FCM; though the latter was quicker in converging.

Keywords: Lung Cancer recognition, Sputum Cells, Thresholding Technique, Image Segmentation, Hopfield Neural Network, Fuzzy C-Mean Clustering

Abstract: Today’s world is a digital world, where decisions are taken on the internet and the internet forms a very integral and important part of the society and the economy. Naturally, the internet’s security, essentially the security of the World Wide Web (www) is very important and groundbreaking. The internet is often vulnerable to attacks from possible hackers who try to compromise the system in order to illegally poach the resources of the system under question. These attacks are famously called web attacks and are a very common problem amongst the computer fraternity. Though there are several existing systems to counter the problem of attacks on the web, most of these systems have their own drawbacks, as in they do not provide classification on any other grounds except frequency, thus causing many web attacking http requests to fall out of the bracket. The objective of our project is to detect these web attacks from the http requests based on many parameters, and classify them as web attacks or not. We also plan to further classify the attacks as HTML, JavaScript or SQL attacks, thus providing a novelty. Thus, the system solves the problem of undetected web attacks through http requests and thus increases the security of the system manifold.

Keywords: Supply World Wide Web (www), web attacks, web attacking http requests, HTML, JavaScript or SQL attacks.

Abstract: An automated irrigation system was developed to enhance production of crops. The system consists of sensors placed within the root zone of the plants. Additionally, sensor information is handled by a gateway unit, which transmits data to a mobile application. An algorithm was developed which can predict threshold values of temperature and soil moisture into a micro controller-based gateway. The system was supported by a cellular-Internet interface that allows data inspection and irrigation scheduling through a mobile application. The automated system was tested, and overall efficiency increased up to 90% compared with traditional irrigation practices of the agricultural zone. The system has the potential to be useful in geographically isolated areas.

Abstract: Stock Market Prediction is a platform where an enormous amount of data exists and constantly needs to be scrutinized. Traditional stock market prediction models are based on analysis of historical market data. Stock Market Prediction on the basis of public sentiments based on social media – an intriguing field of research. Positive tweets and news in social media encourage people to invest in the stocks of the company, thereby increasing the stock price of the company. Data sets are so large that it is difficult to analyze them using traditional data processing applications. We can extract the useful information to an understandable structure using machine learning algorithms, and Sentiment Analysis as the approaches, we implement and simulate a brokerage system and analyze the stock market. Key Words: Stock Market, Sentimental analysis, TextBlob, Machine Learning Algorithms, Natural language Processing, WebScraping

Abstract: The term phishing reminds us of the malpractice that targets the end-user, making him or her a victim unknowingly. The term phishing came into the limelight in the year 1987. It is a fraudulent practice where in the attacker traps the victim to navigate to an illegal website that resembles the legitimate website. The victim’s most sensitive information related to their login data and the card details is tampered with. Hence, phishing is the best illustration for social engineering attack to trap the end-users. Hackers use the internet as a medium to deceive people.

Keywords: DNN, Phishing attack and LSTM

Abstract: Today, autism spectrum disorder (ASD) is developing faster than ever. Screening tests to detect the characteristics of autism is very expensive and time-consuming. with Advances in artificial intelligence and machine learning (ML), autism can It was predicted very early. Although a lot of research has been done to use Different technologies, these studies did not provide any clear conclusions about the prediction The characteristics of autism in different age groups. The proposed model is evaluated using the AQ 10 data set and 1000 real data sets collected from people with and without autism characteristics.In light of this, we are developing a model in machine learning algorithms namely SVM ,Adaboost and Random forest. IndexTerms - SVM ,Adaboost and Random forest.

Abstract: Cloud computing is the rising technology. Cloud computing presents convenient get admission to and excessive overall performance computing on the records .Another primary task that these days software program agencies face, are storage of information at low-cost price and make handy all the time. The important offerings present in Cloud computing is the Cloud storage. With the cloud storage, statistics can be saved on a servers which is now not cared by means of the consumer and no one is aware of the place precisely information saved. Data storage is a very vital and treasured lookup discipline in cloud computing. This paper introduces the notion of cloud computing and cloud storage as nicely as the structure of cloud storage firstly. This paper gives the learn about on introduction to cloud storage and digital storage architecture.

Keywords: Cloud computing, Cloud Storage, Cloud Storage Models ,Cloud Services , Emerging Technology