VOLUME 11, ISSUE 7, JULY 2022

Abstract: Diabetes is a chronic health disorder due to the failure of the pancreas to give the necessary level of insulin or to protect the body that isn't consumable. Diabetic patient health observation is a systematic strategy that furnishes us with detailed health data about diabetic patients. Diabetic patient health observation systems play a critical part in observing the patient's health condition, particularly with the utilization of Internet of Things (IoT) connected devices. Diabetic patient observation frameworks are capable essentially to screen diabetic patients and saving certain health information about blood glucose level, blood pressure, and body temperature. Prescient analysis for diabetic patients is needed because of its capability to help diabetic patients, their families, health specialists, and clinical analysts to pursue decisions on diabetic patient treatment in view of the patient's health condition. This paper depicts a new framework for observing diabetic patients' health and examines prescient investigation utilizing Artificial Intelligence algorithms.

Keywords: Diabetes, Internet of Things (IoT), Remote Health Monitoring, and Artificial Intelligence (AI)

Abstract: This research work involves the design and development of an energy management system to be used in monitoring and control of energy usage in the school hostel. The developed system uses the smart energy measuring module PZEM-004T for capturing the real-time energy consumption in each of the rooms in the school hostel. The system measures these data and then incorporates the data with the internet of things (IoT) for data logging and reporting to a web-based online server using the GSM module. The system will also be able to detect bypass current as a result of illegal meter bypass in each of the rooms. Each of the room’s maximum loads is set at 200watts. Every piece of information captured from the hostel is sent to the server that is continuously being monitored by an Administrative officer, who responds to reports from the system. This developed system is able to reduce the energy wastage in the school hostel, based on the operational function of the system to cut off the power supply to any room in the hostel with a load above 200watts.

Keywords: IoT, GSM module, Energy meter, Wi-Fi module, Multithreading.

Abstract: Blockchain systems rely on classical cryptography of public key encryption and hash functions for its security. These security mechanisms of the distributed technology is made possible by complex mathematical computations, integer factorization and discrete logarithm problems. The emergence of quantum technology is expected to reduce the security of current cryptographic systems. As a result, companies adopting blockchain-based solutions, becomes prone to quantum attack in long-term strategic planning. Grover’s and Shor’s quantum algorithms, which attack the cryptographic principles on which the blockchain is built, currently pose the biggest threat to the blockchain. To counter these threats, the post-quantum cryptography was proposed. The main aim of this study is to critically analyzed the security of classical blockchain and present some post-quantum implementation algorithms in developing a quantum-based blockchain system that would be able to withstand any attacks using quantum technology.

Keywords: Blockchain system, Classical computers, Quantum Technology, Post-Quantum Cryptography.

Abstract: Cloud computing is evolving daily for securing large data in diverse industries and organizations. The two major challenges about cloud storage are reliability and security. Clients cannot entrust their data to another company without any assurance that they can access their information anytime and no third party will be granted access to it. Data can also be requested from the cloud by the users. However, uploading data in the cloud faces some security issues due to cyber threats and prevalent fraudulent activities. With advancement in technology and research, different solutions have evolved to protect cloud data. Cryptographic techniques utilizing different encryption mechanisms are used to protect the data and ensure its integrity. The existing cryptographic techniques are classical and vulnerable to attacks by quantum computers. In addition, the classical computers utilizes multiple algorithms for encryption and decryption which takes time to encrypt and decrypt a file. In this paper, we presented an optimized new security mechanism using post-quantum cryptography to provide block-wise security to cloud data storage irrespective of the size of the file uploaded or downloaded.

Keywords: Cloud computing, Quantum Cryptography, Cryptographic algorithms, Cloud storage.

Abstract: Emancipation of the computers from the limited in space data entry tools (such as keyboards) and its possession of the ability of hearing and reading, remains an area of active research in computer science for more than four decades. During this period, the researchers have provided a considerable number of methods and algorithms for the computerization of hearing and reading in what is known as Pattern Recognition in computer science. One of these methods is the Holistic Approach, which has proved its efficiency in the fast recognition. The usage of neural networks with the holistic method has special importance, as it helps to determine the transition to the analytical method very easy. This paper presents successful recognition experiments of probabilistic neural networks to recognize holistically the most common Arabic names. This network was succeeded in recognizing a high proportion of Arabic names very quickly because it does not segment the words.

Keywords: Holistic approach, Probabilistic Neural networks, Arabic names recognition

Abstract: k Nearest Neighbour Classifier (kNN) is a widely used non parametric machine learning model. This classifier can model complex data distributions and can achieve generalization. kNN algorithm coherently groups data into subsets and labels the test instance based on the similar or nearest training instances. The optimal selection of the nearest neighbours has to be done for accurate classification. Our work implements kNN algorithm with a similarity measure in identifying the optimal nearest neighbours for test instances and deciding their class label as the majority class label among the nearest neighbours. The proposed similarity measure considers the data distribution and thus helps in selecting the optimal nearest neighbours. The effectiveness of the proposed work is evaluated on several datasets with different classifiers like J48, Naive Bayes (NB) classifier. The proposed method outperforms in comparison with other ensemble learning techniques like Multilayer Perceptron (MLP) and Random Forest (RF) with high classification accuracy.

Keywords: similarity measure, nearest neighbour, k fold cross validation, classification, accuracy.

Abstract: This project is installed in the SSCET building which will provide an uninterrupted power through solar energy in the day hours for the requirement of load of SSCET. existing electrical appliances viz., Indoor lights, Corridor lights, Fans, EPBX, Computers, Printers etc. Today, PV systems have an important use in areas remote from an electricity grid where they provide power for water pumping, lighting, vaccine refrigeration, electrified livestock fencing ,telecommunications and many other applications. However, with the global demand to reduce carbon -dioxide emissions, PV technology is also gaining popularity as a mainstream form of electricity generation. Photovoltaic modules provide an independent, reliable electrical power source at the point of use, making it particularly suited to remote locations. However, solar PV is increasingly being used by homes and offices to provide electricity to replace or supplement grid power, often in the form of solar PV roof tiles. The daylight needed is free, but the cost of equipment can take many years before receiving any payback. However, in remote areas where grid connection is expensive, PV can be the most cost-effective power source.

Abstract: Phishing is a type of cyber-attack in which attackers open deceptive websites that look similar to renowned and legitimate websites in order to steal the user's sensitive information. Numerous ordinary human life activities, including electronic banking, social networks, ecommerce, and so on, have been transferred to cyberspace as a result of the fast growth of communication technologies and worldwide networking. The internet's anonymous, accessible, and unmanaged architecture provides an ideal platform for cyber-attacks. The world has seen an increase in the number of Phishing attacks in the past years. It poses a serious threat to the privacy of individuals and can be used to cause financial theft, and identity theft, and can also cause disruption of an organization. It is of prime importance to detect such attacks and eliminate the risk of being a victim of a phishing attack.

Keywords: AWPG, Hybrid Learning, Link Guard Algorithm, Phishing attack, Website

Abstract: Due to the recent rapid expansion in the number of digitised historical files, this is vital. It provides efficient methods for information extraction and statistics retrieval to allow access to data. It makes use of optical character recognition to convert document images into textual representations (OCR). OCR techniques today frequently do not belong in the historical domain. Additionally, they typically need a substantial volume of annotated documents. This paper will therefore show you a few ways to allow OCR on past data. Authentic, hand-labeled coaching information should be added to the image. OCR with all features OCR and page structure analysis, which comprises text blocking and line segmentation, are the device's two primary functions. While the OCR approach is based on a convolution neural network, our delineation method uses on recurrent neural network. Both approaches are state-of-the-art in the concerned field. developed a novel authentic dataset for the Protonium Portal for OCR. This information, which is openly available on this corpus, will be used to evaluate all suggested strategies. We illustrate it using some actual examples of annotated data so that both categorization and OCR tasks may be carried out. The experiment seeks to achieve this. If your information is limited, decide how to accomplish it properly in a satisfactory manner. We also demonstrate that the rating we conducted is on par with or superior to the results of certain modern systems. The study's findings demonstrate how to create a successful OCR engine for historical documents even in the lack of substantial training data.

Abstract: BACKGROUND: The general hospital psychiatric care is most important since 30-50% of the patients attending primary care levels or general hospitals suffer from various forms of psychosomatic disorders, but they complain only vague symptoms which cannot be diagnosed medically. So, nurses working in general hospitals setting can help these clients by assessing and proper psychosocial care should be given for a permanent relief.

Abstract: The aim is to build a solar-based pesticide sprayer used to spray the pesticide in the field and can also be used as a multipurpose sprayer. Solar energy is converted to electrical energy by the photovoltaic effect and stored in batteries for various uses. The sprayer's actual field capacity was determined to be 0.14 hectares per hour, giving an average coverage of 1 hectare per day when operating for 8 hours. Other than solar energy, the machine doesn't use any other external sources of power. This model increase spraying capacity by semi-automation process and becomes more economical and eco-friendly.

Keywords: Solar Energy, Agricultural pesticide sprayer, Eco-friendly technology, Multi-purpose system, Charging battery, solar panel, photovoltaic effect.

Abstract: With increasing cases of crimes against women it has become the need of this hour for women to protect themselves. According to statistics, there were over 28,000 rape cases reported in India in the year 2020 alone. This project work proposes a solution in helping women find support and defend themselves from any threat using a wearable wristband. Using this device in crisis cases, women can taze the aggressor using a non-lethal taser so that she can distract the aggressor and sneak off to a safer location. The device also enables women to send a message with GPS location along with a captured image of the aggressor to their emergency contacts, which helps track the woman in need of support. It also includes a buzzer that can be used to alert people around them of their situation. The device includes a pulse sensor and temperature sensor which records the current temperature and pulse rate of the individual.

Keywords: electric shock, face recognition, GPS, GSM, IoT based device, women safety device

Abstract: Artificial Intelligence is extensively used to detect the movement of lips. It is observed that there is a high Correlation between the visual motion of mouth and corresponding audio data. This fact has been utilized for lip reading and for improving speech recognition. A Convoluted Neural Network would detect the movement of lips and determine the words spoken. The words that are spoken in the video would be detected by the Trained CNN and displayed in the text format. The CNN relies on information provided by the context, knowledge of the language, and any residual hearing. The aim is to verify whether the use of artificial intelligence methods, namely Deep Neural Network, is a suitable candidate for solving this problem. Practically, the focus is on presenting the results in terms of the accuracy of the trained neural network on test data.

Keywords: Artificial Intelligence, Lip Reading, Deep Neural Network, CNN, Machine learning.

Abstract: Coronavirus disease is an infectious disease caused by SARS-CoV-2 virus it can spread through touch or by sneezing in front of someone and leads to death of an individual and Pneumonia is caused by virus, bacteria and fungi Pneumonia is an infection that inflames the air sacs in one or both lungs. To detect these two we proposed a model it will detect the kind of disease whether the person is normal or he is suffering from viral pneumonia or bacterial pneumonia or Covid-19 by collecting X-ray copy of the Patient.

Keywords: Covid-19 Detection, Pneumonia Detection, vgg16, Convolution Neural Network, Deep Learning.

Abstract: The aim of this paper is to develop home automation system based on IOT using Bluetooth based microcontroller. As scope of technology is widening every day, we are making our tech advance in mobile, robotics, Machine Learning, then why an exception for our home. Today's houses are gradually transferring from ordinary/human's input-based appliances to smart/IOT enabled appliances to be controlled remotely. At Present, existing home automation systems use technology that is limited to only that device. So, in a nutshell, we are making our devices IOT enabled not our homes. As far as this paper is concerned, NodeMCU (ESP8266) microcontroller along with Relays is used to control electrical switches remotely from the server which is built on java. User can control switches using a Web Application after authenticating

Keywords: bluetooth module for connecting device, NodeMCU(ESP8266) ,Relay board for connecting wires

Abstract: Extracting each word from a new post or remark in order to detect the feelings expressed therein, followed by matching those words with dictionaries in order to classify the post using a classification model. Use ML approaches to later determine whether it is FAKE or REAL NEWS. Project is the web-based programme that the program's administrator and users access. Accessing the project in real time requires an internet connection. The project relies on outdated information (training data-set). Users of the application should have knowledge in accessing the application . The project was created with the aid of effective tools like SQL Server and Visual Studio.

Keywords: SQL Server, Visual Studio, classification model, ML

Abstract: Hand gestures are an effective form of communication, particularly when we are speaking to others who cannot comprehend our signing. It's also a crucial component of human-computer interaction. To ensure that listeners comprehend what speakers are attempting to say, understanding hand gesture is crucial. Speaking will be helpful for the deaf and the dumb, and the speaking mouth will be helpful for the stupid. Convolutional Neutral Networks (CNN) are frequently used to categorise photographs of hand gestures. Voice recognition is complemented by the conversion of hand movements into text picture manipulation. It offers more accuracy.

Keywords: CNN, Image Processing, Deep Learning, Feature extraction, Vision based system.

Abstract: The drinking water crisis in India is reaching alarming proportions. It might very soon attain the nature of global crisis. Hence, it is of utmost importance to preserve water. In many houses there is unnecessary wastage of water due to overflow in Overhead Tanks. Automatic Water Level Controller can provide a solution to this problem. The operation of water level controller works upon the fact that water conducts electricity. So water can be used to open or close a circuit. As the water level rises or falls, different circuits in the controller send different signals. These signals are used to switch ON or switch OFF the motor pump as per our requirements.

Keywords: System Analysis,Fluid Level Detector Sensors,Step Down transformer,Diodes, Types of Diodes,Light Emitting Diodes or LEDs,Resistors, Relays, Hardware Subsystem,Power Supply Unit,Display Unit

Abstract: Most students throughout the world are always perplexed after completing high school and reaching the point where they must choose a job route. Students under the age of 18 lack the maturity to understand what steps must be taken to pursue a rewarding professional path. As we progress through the phases, we find that every student has questions or thoughts about what to do after 12th grade, which is the single most difficult question. Then there's the question of whether they have the necessary talents for the career path they've selected. Based on an objective test of an individual's skills, our computerized career counselling system predicts the best department for them. If a person completes the online evaluation that we have established in our system, they will automatically end up choosing an acceptable job, which will reduce the number of people who fail because they choose the wrong career path.

Abstract: The multi-label emotion classification task aims to identify all possible emotions in a written text that best represent the author’s mental state. In recent years, multi-label emotion classification attracted the attention of researchers due to its potential applications in e-learning, health care, marketing, etc. There is a need for standard benchmark corpora to develop and evaluate multi-label emotion classification methods. The majority of benchmark corpora were developed for the English language (monolingual corpora) using tweets. The proposed work focused on English language. A multilabel emotion datasets are collected from the go emotions library. To build this project we have used both machine learning and deep learning techniques to predict the result, but compared to machine learning algorithms deep learning MLP has provided better result accuracy.

Keywords: Emotion, MLP, Multilabel, Corpora, Classification

Abstract: Infectious disease Coronavirus disease (COVID-19) has turned into a global pandemic as per the announcement by World Health Organization (WHO) on 30th Jan 2020. A portion of the areas the sicknesses become broadly fanned out due to ill-advised wearing of facial cover. So, WHO pronounced wearing the mask in swarmed regions as an anticipation technique and thus we are forced to use a protective face mask checking framework. The advancement of AI and picture handling examination present strategies for the detection of the presence of face masks. Utilizing image processing and AI strategy are utilized to figure out face mask detection. Face mask recognition can be done through different strategies, this technique can be helpful for surveillance purposes may be at the entrance of Cinema halls, airports, institutions, organizations, etc. Here we examined different profound learning methods utilized for sensing the presence of face masks.

Keywords: Face Mask, Face Mask Detector, Covid-19, Convolutional Neural Network.

Abstract: Technology is going very fast day by day; digital recognitions are getting more popular and providing more scope to perform research in ML (Machine Learning) and AI (Artificial Intelligence). Recognition of sign languages has been done by many researchers. Few researchers also tried recognizing Kannada sign languages with static images. Still real time Kannada sign language recognition is one of the least touched techniques. This project is trying to use Machine Learning techniques to do this job of Kannada sign language recognition with reasonable accuracy.

Keywords: ML, Python, Kannada, Sign Language

Keywords: Microcontroller;Zigbee ; Weight Sensor ; 1x4 Keypad ; Lcd Display ; Motor Drive; Gps Application;Ldr Sensor;Relay

Abstract: Deep Learning methodologies offer great potential for applications that automatically attempt to generate captions or descriptions for images and video frames. With the recent advancements in neural networks, there has been progress in implementing object detection or generating description for images and captions for videos. Our work aims to automatically generate list of objects in the image when image is given and generate caption to video when video is given by reading their content. At present images and videos are annotated with Human intervention and it is difficult or almost an impossible task for a large commercial database to manually caption every photo and video. Image Object Detection and Video Captioning is basically very much useful in many applications like for generating captions or description during real-time and theyare also being used in advance machine and deep learning applications.

Keywords: Deep learning, Object detection, Neural networks, Video captioning.

Abstract: In highly populated Countries, speed is one of the basic reasons, everyday people lose their lives because of accidents and poor emergency facilities. Many lives could have been saved if emergency services could get accident information and reach in time.. This project implies a system which is a solution to this drawback, when a vehicle meets with an accident and deals with accident detection system when the accident occurs it uses various components and alerts the Rescue team for help. Vibration sensor detects the sudden change in the vibration of vehicle and GSM module sends the alert message on your Mobile Phone with the location of the accident. Location of accident is sent in the form of Google Map link, derived from the latitude and longitude from GPS module . It reads the exact latitude and longitude of the vehicle involved in the accident and sends this information to nearest emergency service provider. The goal of the project is to detect accidents and alert the rescue team in time. Due to real-time tracking facility, vehicle tracking systems are becoming increasingly popular among owners of expensive vehicles Keywords Vibration sensor, GPS module, GSM module, vehicle tracking systems

Abstract: Phishing has been a constant issue across the global community. The approach has primarily been related to most attackers gaining access to sensitive information about users. Lack of awareness is among the main factors that result in successful phishing attacks. There are different types of phishing attacks available. However, cybersecurity specialists have developed algorithms that have effectively prevented phishing attacks. The report below includes information on anti-phishing algorithms that can detect phishing attacks. The algorithms include different technologies and capabilities that promote safety for most individuals. The paper focuses on describing each of these concepts and how they promote cybersecurity across the globe.

Keywords: Anti-phishing, sensitive information, phishing, social engineering, cybersecurity, cyberattacks

Abstract: Humans have a proclivity for looking for solace. They are always looking for new ways to diversify their everyday routines and jobs. self-contained. Pick-and-place concept and- place, as well as a robot that clears obstacles will be carried out in accordance with a certain set of instructions line, might be able to assist a business in reducing the amount of pollution it produces. cost of labour or possible substitutes hard work The industries are always changing. Industries are increasingly adopting the concept of automation, and robots are the best option for this In most cases, one sort of robot is used industry is a manipulator robot or just an arm made of metal It can be either open or closed. linked kinematic network of stiff links Through means of moveable joints. We have a mechanical arm with a line follower robot that will be able to choose an article from a container then transport it to the specified location by following a predetermined path along Servos can be used to clear the obstacle a vehicle approaching the line's lane.

Keywords: Raspberry pico pi, Ultrasonic sensor, IR sensor, Servo motor, Robot Mechanical arm claw.

Abstract: Neural networks are simply known as the biological nervous system. An Artificial Network (ANN) is an information processing system that is inspired by the way biological Nervous System, such as the brain, process information. The key element of ANN is the novel structure of the information processing system. It is composed of a large number of highly interconnected processing elements (neurons) working in unison to solve specific problems. ANNs, like people learn by example. They can be trained with a known example of a problem. Once trained, the network can be put to use in solving unknown and untrained problems. An ANN is configured for a specific application , such as pattern recognition or data classification, through a learning process. Learning in biological system involves adjustment to the synaptic connection that exist between the neurons. This examines the efficiency of neural networks. Taking into consideration type of ANNs such as Generalized Regression (GR) neural network. Radial Basis Function (RBF) neural networks, Linear Layer (LL) neural network efficiency of ANNs is checked in the design of trusses. The neural networking tool available in MATLAB is used. To train ANNs, various input and output data are provided using an analysis and design package STAAD PRO. The ANNs are trained with some values and are tested for both interpolation and extrapolation Then percentage error is calculated in all three ANN. Based on percentage error, the efficiency of each ANNs is compared in the design of trusses. The study is made by increasing the number of training, by increasing the number of input and output variables, by training in the matrix form, etc. From these results the suitability of each ANN is studied and conclusions are drawn.

Keywords: Neural networks, Truss, General Regression Neural Network, Generalized Regression

Abstract: One of the major obstacles that an agriculturist may experience in their cultivation is plant stress, which can result in severe economic crop loss. Nitrogen deficiency is one of the most common causes of plant stress. Nitrogen deficiency causes stunted growth in plants, depending on the severity of the stress. To aid agriculturists, developers are investigating several approaches for measuring plant stress. To evaluate plant stress, the suggested system uses Deep Learning and convolutional neural networks, as described in this research. Deep learning-based methods are more efficient at measuring different plant traits for diverse genetic discoveries while searching for plant stress than traditional image-based phenotyping methodologies.This research takes a deep learning method to picture analysis. This suggested approach uses deep convolutional neural networks (CNNs) to detect as well as pixel-wise segment features to capture high-resolution photos without sacrificing pixel density, resulting in more accurate detection. In addition, the proposed model also outperforms traditional Machine Learning techniques like SVM, KNN, DT by achieving an average of 10% better accuracy.

Keywords: Deep learning; Convolutional neural network; Plant stress; Transfer learning;

Abstract: Image processing is a method to convert an image into digital form and perform some operations on it. With the advancements in artificial intelligence (AI), the field of human behavioral prediction and analysis, especially human emotion, has evolved significantly. The most standard methods of emotion recognition are currently being used in models deployed in remote servers. These Human facial expressions convey a lot of information visually rather than articulately. Facial expression recognition plays a crucial role in the area of human-machine interaction. Automatic facial expression recognition system has many applications including, but not limited to, human behavior understanding, detection of mental disorders, and synthetic human expressions. Recognition of facial expression by computer with high recognition rate is still a challenging task. Keywords- AI

Abstract: Most online stores allow their consumers to post reviews of their products and services. These reviews' presence can be used as a source of knowledge. Reviews are becoming a more important source of information for consumers. Unfortunately, phony reviews by certain parties that attempted to produce fake reviews in order to boost the popularity of their product or to disparage the competitor's goods have undermined the significance of the review. The goal of this paper is to identify fake reviews on e-commerce sites using the text, rating properties, and other information from a review. The project also proposes to classify the reviews as positive or negative based on the text used in the reviews, ratings given to the product so on.

Keywords: Supervised Learning, Flask, Framework, Web Application, Naïve Bayes

Abstract: The procedure of counting various blood cells from a smear image will be substantially facilitated by an automated method. Applications for object detection and picture classification are improving in accuracy thanks to the development of machine learning algorithms. the approach for detecting various blood cells based on machine learning. You only need to look once when using cutting-edge object detection techniques like regions with convolutional neural network (R-CNN) (YOLOV3). In one evaluation, YOLOV3 employs a single neural network to forecast bounding boxes and class probabilities based on the entire image. Additionally, photos are annotated with the labelling tool, and the YOLOV3 framework uses the annotated images to automatically identify and count RBCs, WBCs, and platelets.

Keywords: YOLO, Machine Learning, YOLOv3, labelImg, RBC, WBC, Blood Cells

Abstract: We attempt to detect clickbait with our design model. YouTube videos often include captivating descriptions and intriguing thumbnails designed to increase the number of views, and thereby increase the revenue for the person who posted the video. Initially, in the proposed system, we gather data like the audio transcript from YouTube along with Title, Comments, likes, views, and Statistics. we train, pre-process and evaluate the data sets. In Multi-Model Architecture, we apply the SVM algorithm for titles, Comments, likes, and Statistics. According to the output obtained by this algorithm, we classify video as clickbait or not.

Keywords: Scikit-learn (Sklearn), Regular Expression (Regex)

Abstract: Payroll is the procedure by which employers compensate employees for their labor. Payroll administration responsibilities may be burdensome for large firms but are a tremendous burden for small business owners. When payroll is performed manually, keeping accurate records, organizing information, and assuring constant accuracy may be more difficult. Because of changing needs, changing employee demands, and changing technology, many traditional payroll practices and procedures must be reviewed. As a result, an organization needs an automated payroll system to conduct payroll-related processing more efficiently. There are lots of tools for robotic process automation, however Automation Anywhere is one of the popular RPA tools that provides powerful features to automate complex business tasks. It is used to automate such processes that are repetitive, rule-based, and manually performed by humans. When using Automation Anywhere for your Robotic Process Automation technology, bots can run both attended or unattended. Automation Anywhere integrates well with a multitude of applications, so you can easily automate business repetitive tasks, allowing you to create and deploy processes end-to-end with a digital workforce of software robots that complete activities in real-time.

Keywords: Payroll processing, Employee, Robotic process Automation

Abstract: Hand gesture recognition has been a very interesting aspect in the field of Human Computer Interface due to its flexibility and user friendly. The gesture recognition technique is being used to develop different types of system to develop communication among disabled people or a system for controlling a device. Major challenges for developing a efficient hand gesture recognition techniques are non – uniform backgrounds, difference in the size and shape of user’s hand, different hand gesture types such as static and dynamic gestures. Mouse plays a very important role as an input device in the Human Computer Interaction (HCI). There have been different techniques introduced to replace the functionalities of mouse. Different methods such as using hand gloves, coloured finger tags, accelerometer, Gyroscope, Bluetooth, etc. In the system we are using different types of dynamic gestures to replace the mouse functionalities without using any type of external devices and using only the system camera with the help of mediapipe and opencv.

Keywords: Hand Gestures, keypoints, Mediapipe, OpenCV

Abstract: Security of two-wheeled vehicles in public parking lots is now of utmost importance in the current global context. With the aid of the Global Positioning System (GPS) and Global System for Mobile Communication (GSM) technologies, this system implements straightforward and less expensive two-wheeler vehicle tracking. With the use of a smartphone, it is also possible to track any moving object and pinpoint the precise location of a two-wheeled vehicle. The GPS module, GSM modem, and microcontroller are the system's primary components. The GPS technology is used to monitor the two-present wheeler's location. GSM technology is also deployed in two wheeler vehicles because GPS can only receive information about the location of two wheeler vehicles from satellites.

Keywords: Arudino nano, Ignition Key, GPS, GSM, Battery, rf tag , adxl35.

Abstract: Plants were also essential to human life because they provide us with air, food, shelter, medicine, fuel, and gums that help to preserve the environment. Many plants have valuable medicinal properties and active components that can be used in medicines. Many beneficial plant species are currently becoming extinct or being destroyed as a result of factors such as global warming, rising population, professional secrecy, a lack of government awareness for research operations, and a lack of knowledge about therapeutic plants. Because manual identification of medicinal plants takes a long time, professional help is required. The automatic identification of medicinal plants is a hot topic in image processing research right now. We created our own dataset of 4 categories of herbal plants for experimental investigation, including cinnamon, henna, marigold, and turmeric, and we also used an existing Malaysian flavia dataset. We created a leaf and flower identification technique that uses a CNN classifier and has a 95% accuracy.

Keywords: Image processing, Herbal plant, CNN, leaf and flower

Abstract: Intrusion detection plays an important role in ensuring information security, and the key technology is to accurately identify various attacks in the network. In this project we explore how to model an intrusion detection system based on deep learning and we propose a deep learning approach for intrusion detection using recurrent neural networks (RNN-IDS). Moreover, we study the performance of the proposed model in binary classification and multiclass classification and the number of neurons and different learning rate impacts on the performance of the proposed model. We compare it with those of artificial neural network, random forest, support vector machine and other machine learning methods. The experimental results show that RNN-IDS is very suitable for modelling a classification model with high accuracy and that is performance is superior to that of traditional machine learning classification methods in both binary and multiclass classification. The RNN-IDS model improves the accuracy of the intrusion detection and provides a new research method for intrusion.

Keywords: Intrusion detection, Recurrent neural networks, Deep Learning.

Abstract: A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual. is the process of capturing a high-contrast image of a person's iris using visible and near-infrared light. It is a form of biometric technology, like face recognition and fingerprinting. The proponents of iris scanning technology claim that it gives law enforcement officers the ability to compare suspects' iris scans with a database of existing pictures in order to verify or confirm a subjects identify. Since it is easier for someone to conceal or alter their fingers than it is to do the same with their eyes, they also assert that iris scans are quicker and more accurate than fingerprint scans. The iris recognition system consists of an automatic segmentation system that is based on the Hough transform, and is able to localize the circular iris and pupil region. The extracted iris region was then normalized into a rectangular block with constant dimensions to account for imaging inconsistencies. Infrared light is used by biometric iris recognition scanners to illuminate the iris and identify distinct patterns that are invisible to the human eye. Eyelashes, eyelids, and specular reflections—common obscurants of the iris—are identified and removed by iris scanners. The ultimate result is a group of pixels that only include the iris. The bit pattern that encodes the information in the iris is then determined by looking at the pattern of the lines and colours in the eye. Finally, the phase data from 1D Log-Gabor filters was extracted and quantized to four levels to encode the unique pattern of the iris into a bit-wise biometric template. And finally, iris recognition is employed for classification of iris templates, and two templates were found to match if a test of statistical independence was failed. Therefore, iris recognition is shown to be a reliable and accurate biometric technology.

Keywords: Grid Search, Principle Component Analysis (PCA)

Abstract: About 70% of the India economy depends on agriculture. Due to environmental changes such as rainfall, temperature, the crop yield gets affected severely. Phaseolus vulgaris L is an important food legume crops and provide essential diet for millions of people across the world. It is affected by various diseases out of which Anthracnose are of major importance. Anthracnose disease is caused by fungus Colletotrichum lindemuthianum. Camellia assamica is one of the most popular non-alcoholic beverage crops in the world. The leaf gets severely affected by fungus Alternaria alternata. Development of automatic detection system using advanced computer technology such as image processing help to support the farmers in the identification of diseases at an early or initial stage and provide useful information for its control. Therefore, the present study was carried out on automatic disease detection of plant leaf of Phaseolus vulgaris (Beans) and Camellia assamica (Tea) using image processing techniques. It involves image acquisition, image preprocessing, image segmentation, feature extraction and classification.

Keywords: Phaseolus vulgaris, Camellia assamica, image acquisition, image segmentation, feature extraction.

Abstract: Recommendation of music is one of the predominant things, like streaming platforms of music. Music genres are the frames used to catalogue music files. Most of the music classification is initiated by the extraction of the audio features which calls for computing processes. This scrutiny aims the analysis and tests the performance of the classification of music genre based on the functionality of two different classifiers, such as Support Vector Machine (SVM) and K Nearest Neighbors (K-NN). The music dataset of Spotify was chosen as it had the functionality of each of its musical genres. The results correspond to the audio feature extraction, hence the classification with the extortion of functionality features can be developed more if the functionality in the dataset is managed well.

Keywords: Music Genre, K-NN, Support Vector Machine, Audio Features

Abstract: In the modern world, internet has become a major part in everyone’s life. Most of businesses have now gone digital and internet is playing a major role in their success. Internet has enabled businesses to have larger market to which they can sell their products. One important component of the internet is the server. All the devices in the internet are broadly either a server or a client. Server stores the data that are then accessed by the clients. Distributed Denial-of-Service is a network attack on the servers. This attack targets the availability of the server by overwhelming them by a flood of internet traffic. This prevents the server from giving services to the legitimate users. DDoS attack causes significant losses to the organization. In this paper, we discuss a ensemble modelling based approach to mitigate this problem. Ensemble modelling is a process where multiple model which are different fundamentally are combined to make one classifier model.We try to predict the type of DDoS attack by developing a ensemble model by combining Naïve Bayes, Random Forest, Multilayer Perceptron, Stochastic Gradient Descent . The accuracy score of 98.62 percent has been achieved. It can be concluded that this system proves to be an effective deterrent for DDoS attacks.

Keywords: DDoS attack,http-flood, udp-flood, smurf , machine learning , ensemble model

Abstract: Incremental loading is a preferred data warehouse (DW) refresh technique in the modern world for being more efficient than Full loading. A special case in full loading where the entire content at the target is dropped and reloaded for the purpose of refresh is known as Truncate and Load. Incremental loading involves refreshing only the changed contents from the data source into the data warehouse. The gathering of these changed contents is known as Change Data Capture (CDC). This paper presents a study on different CDC techniques used in practice to aid the incremental loading. An example scenario which uses the truncate and load approach is presented and the suitability of the CDC techniques to implement incremental loading is discussed. The implementation for conducting a CDC based on the delta rules for migrating from a naive truncate and load to an effective incremental load in the example scenario is presented in this paper.

Keywords: Truncate and Load, Incremental Load, Data Warehouse, Change Data Capture, Delta, Log, Snapshot, Timestamp, Metadata.

Abstract: Making informed judgments and maximising the use of the available transportation resources are made easier with accurate bus passenger flow forecasting. A wide range of elements connected to the travel environment that have an impact on passenger flow can be identified using data from various sources. A decent prediction model should resolve the accompanying multicollinearity problem in addition to fully using the latent information hidden in multisource data. Based on this concept, we offer a special scaled stacking gradient boosting decision tree (SS-GBDT) model to anticipate bus passenger flow. The SS-GBDT consists of the prior feature generation module and the following GBDT prediction module. The stacking method was used in the prior module to provide a number of improved multi-source data characteristics using a few basic models with comparable performance. By using a quasi-attention-based mechanism, we explicitly develop a scaled stacking approach (precision-based scaling and time-based scaling). The prediction module improves prediction performance by using the newly developed characteristics as input to calculate the passenger flow using a GBDT model with layered data. On two actual bus routes in Guangzhou, China, the plan is tested. Considering the results, it can be concluded that SS-GBDT is superior in terms of prediction stability and accuracy. Additionally, it is better suited to handle the multicollinearity issue with multisource data. The variables that impact predicting passenger flow can also be sorted. When there are sizable amounts of data, the prediction model is flexible and scalable, enabling the integration of a number of influencing factors.

Abstract: Waste generated from many sources are disposed or buried on an open ground, which increases the soil pollution and degrades fertility. Kitchen waste can be efficiently handled to produce biogas. There is a large amount of kitchen waste that is being generated daily and there is no proper system which uses this type of waste effectively. Conventional biogas facilities are inefficient and produce little methane because they rely on low calorific inputs such municipal solid waste, distillery effluent, and animal manure. Although it has not yet been fully exploited, biogas produced from kitchen trash is regarded as a high-calorie feed. It can replace half of the LPG used in cities and works in parallel with expensive and difficult to operate cow dung-based biogas plants in rural regions. In order to generate efficient gas from kitchen waste the pH value in a digester (of plant) should be neutral (i.e., pH=7) and temperature should be around 30℃ to 40℃, so it is essential to monitor the digester and after monitoring it is essential to check the amount of gas generated using gas sensors interfacing to ESP32 microcontroller and displaying the result in LCD.

Keywords: ESP32 NODE MCU; MQ4 SENSOR; MQ135 SENSOR; LCD DISPLAY.

Abstract: The study suggests an automated way of preventing bogus job postings online that uses categorisation techniques based on machine learning. To determine the most effective model for identifying job scams, the output of multiple classifiers was compared. In order to verify false internet postings, these classifiers are used. In the midst of several other ads, it aids in identifying fraudulent job listings. The two fundamental categories of classifiers considered for the purpose.

Abstract: Certain cooking items still fall under the same classifications. The problem is that the general public has limited access to updated records. The objective of this study is to ascertain the difficulty of automatically identifying a meal in a photograph for cooking and then automatically generating the appropriate recipe. Due to significant overlaps in food dishes and the possibility that meals from various categories may simply resemble one another visually, the chosen job is more challenging than previous supervised classification difficulties (also known as high intra-class similarity). Convolutional Neural Networks (or CNNs for short) are used to distinguish objects or food courts while concurrently looking for adjacent neighbours (Next-Neighbour Classification).

Abstract: Vehicle crashs cause endless passings and weakens reliably, a particular degree of which result from grim treatment and discretionary events. Sensibly, changed car accident openness can decrease response time of rescue affiliations and vehicles around disasters to additionally develop rescue limit and traffic flourishing level. In this paper, we proposed a changed minor effect locale technique pondering Cooperative Vehicle Infrastructure Systems (CVIS) and machine vision. As an issue of some significance, an original picture dataset CAD-CVIS not entirely set in stone to besides empower precision of disaster area contemplating smart roadside contraptions in CVIS. Especially, CAD-CVIS is consolidated various kinds of event sorts, climatic conditions and setback area, which can chip away at self-versatility of disaster area procedures among different traffic conditions. Moreover, we foster a basic cerebrum network model YOLO-CA considering CAD-CVIS and colossal learning evaluations to see disaster. In the model, we use Multi-Scale Feature Fusion (MSFF) and mishap limit with dynamic loads to cultivate execution of seeing not entirely obvious subtleties moreover. Finally, our evaluation focus on outlines execution of YOLO-CA for seeing minor accidents, and the results show the way that our proposed strategy can perceive minor setback in 0.0461 seconds (21.6FPS) with 90.02% standard accuracy (AP). In moreover, we contrast YOLO-CA and other article certification models, and the results show the total show improvement for the exactness and consistent over various models.

Keywords: Cooperative Vehicle Infrastructure Systems (CVIS), Multi-Scale Feature Fusion (MSFF). Car accident detection, Machine vision.

Abstract: Medical imaging automated fault identification is an area that is expanding in various diagnostic medical applications. Automated tumour detection in MRI is essential because it provides details on aberrant tissues required for treatment formulation. Human evaluation is the common technique for identifying errors in computed tomography brain pictures. This strategy is not practical due to the volume of data. As a result, creating precise and automated classification techniques is necessary to lower the rate of human mortality. Automated cancer detection methods are thus created since they would free up radiologist time and have a proven track record of accuracy. MRI brain tumour identification is a challenging endeavour due to the complexity and variety of tumours. We recommend applying machine learning techniques in this work to detect tumours in brain MRIs in order to overcome the limitations of the present classifiers. It is feasible to precisely identify cancer central nervous system using MRI by using computer learning and image classifiers.

Abstract: E-learning is learning through the utilization of technologies. E-Learning is that the inexorable trend of the applying of recent data technology in education. It's one in all the foremost learning ways within the era of knowledge characterised by non-restriction in time and place, it's providing new prospects to teaching establishments to be ready to give versatile and price effective distance learning setting. so as to effectively use varied sorts of style data in development, it's necessary to make data management system. Developing Associate in Nursing E-learning platform will meet the necessity of progressive teaching, that may be a reasonably economical thanks to develop data technology in education and subject teaching. it's primarily the linear organization of the teaching materials and also the related data resources. this method will facilitate the scholars to check severally for his or her exams. It additionally provides the mandatory course materials, question paper, quizzes and plenty of a lot of. this method provides user friendly interface for the users and customized service whereas exploitation the system.

Keywords: E-Learning, online preparation, civil service exam, web development

Abstract: Every business or organisation regularly collects and stores large amounts of data. Two methods that are frequently utilised to do this are cloud computing and wireless network infrastructure. Customers that use these services can perform their duties more swiftly and easily while obtaining the desired results. In order to store information in a digital database, general services use a special identifier. It might, however, have some restrictions and difficulties. The unique identifier is linked to the data owner's name, address, identity card number, and other facts. Attackers can take the complete data set by altering a unique identifier. Attackers may even use eavesdropping or educated guesses to get the necessary data. The result is a lack of data privacy protection. Therefore, wherever digital data is held, data privacy concerns must be taken into account. When using current services, there is a considerable risk that data or information will be revealed to or leaked to an unidentified user during transfer. Additionally, during exchange of information, attacks against services, such as impersonating and forgery attacks, may occur. This study suggests using a palm vein-based biometric authentication method to assuage these concerns. The database record is made anonymous, and the data is adequately protected, using a pseudonym generation approach. This protects information and data from unauthorised access. The suggested remedy can stop information breaches, and a user's genuine identity is never revealed. INDEX TERMS: Data preservation, pseudonym, anonymity, unlink ability, and palm vein authentication

Abstract: Long-term research has been done on the issue of spotting fake exchanges. The existence of fraudulent exchanges in the economy discourages investors from investing in bitcoin and other blockchain-based businesses. False exchanges are regularly viewed with scepticism due to the gatherings in issue or the way they are put up. To prevent them from jeopardising the trustworthiness of the neighbourhood and the blockchain network, people endeavour to identify false exchanges wherever possible. Numerous other Machine Learning approaches have been suggested to address this issue, but none of them has clearly emerged as the best one, even though some of the results show promise. This study looks at how well a few controlled AI models and a few deep learning models do at spotting bogus transactions in a blockchain network. Such a correlation exploration will assist in identifying the most efficient method given the compromise in precision and processing execution. Our goal is to pinpoint the clients and transactions that will probably resort to extortion. A blockchain network's economics and user confidence are fundamentally damaged by fraudulent exchanges. Although it is hard to guarantee the morality of the participants or the verifiers, employing agreement methods like proof of stake or proof of work makes it possible to confirm the authenticity of an exchange. This implies that fraud in a block chain organisation is still a possible. One method to stop extortion is by using AI computations. AI facilitates both guided and independent learning. For both certified and fraudulent exchanges, we analyse managed AI solutions in this study. Additionally, we offer a full connection of several directed AI methodologies.

Abstract: Traffic surveillance may monitor and collect data about the flow of traffic on road networks, which is necessary for a number of applications in intelligent transportation systems (ITSs). One of the key issues with traffic monitoring is the accurate and quick detection and counting of vehicles. Vehicle detection and monitoring have several applications. In order to enhance the infrastructure for everyone's comfort and convenience, public and private organizations may try to comprehend the traffic that passes through a particular area. Road widening, the placement of traffic signals, and the installation of parking spaces are a few examples of projects where traffic study is crucial. In the past, manual tracking and identification were employed. Somebody will be posted there to count the vehicles and record their classifications. Sensors have been employed recently, although they only address the counting issue. Vehicle type cannot be determined via sensors

Keywords: Vehicle Detection, Deep Learning, DeepSort, YOLO, Video Processing.

Abstract: Phishing is a considerable problem differs from the other security threats such as intrusions and Malware which are based on the technical security holes of the network systems. The weakness point of any network system is its Users. Phishing attacks are targeting these users depending on the trikes of social engineering. Despite there are several ways to carry out these attacks, unfortunately the current phishing detection techniques cover some attack vectors like email and fake websites. Therefore, building a specific limited scope detection system will not provide complete protection from the wide phishing attack vectors. This paper develops detection system with a wide protection scope using URL features only which is relying on the fact that users directly deal with URLs to surf the internet and provides a good approach to detect malicious URLs as proved by previous studies. Additionally, Anti-phishing solutions can be positioned at different levels of attack flow where most researchers are focusing on client-side solutions which turn to add more processing overhead at the client side and lead to losing the trust and satisfaction of the users. Nowadays many organizations make centralized protection of spam filtering. This paper proposes a system which can be integrated into such process in order to increase the detection performance in a real time.

Keywords: Phishing, security threats, URLs, websites

Abstract: It is a well-known fact that any two persons with disability are not alike and their articulation would not be similar. In this context teaching and rendering services for children with special needs particularly those who have hearing impairment and articulation disorder is quite a challenge. To provide clinical support services to the needy population, we have used MATLAB, a multi-paradigm numerical computing environment as a tool to achieve the aim and objectives of our project. The main aim of our project is to encourage students to achieve one of the primary milestone i.e., articulations of phonemes. To provide training in articulation of phonemes by continual therapy imparted through MATLAB and to promote interactive learning method during therapy sessions are the prime objectives. This Technical intervention would be very user friendly for therapist during the therapy session as they provide visual cues and also help giving feedback on improvement towards achieving the correct articulation to the children. These visual cues will encourage articulation disordered kid to learn in an easier way, unlike the traditional practice. Whole process was divided into three phases. Initially, the reliable and efficient microphone was selected for phoneme recording purpose based on frequency response characteristics. Where, the phonemes are recorded using different set of microphones; each microphone’s frequency response characteristic was analyzed and appropriate microphone (SLM) was selected for articulation therapy. Secondly, a data base of normal was created using the recordings from the suitable microphone that was articulated by the native Kannada speaking children with the age range of 7-8 years and without any articulation disorder. Finally, Phonemes articulated by articulation disorder children of the age range of 7-9 years was recorded. Comparison of its frequency response characteristic with the reference of normal children was obtained. The Cepstrum algorithm was used for the analyzing the frequency response characteristic. Analysis of the compared phonemes are studied and scored. These scored data are provided as visual cues through MATLAB tool. This visual feedback not only helps the therapist to provide therapy in clinical sessions but also encourage the child in achieving the milestone towards correct articulation very quickly in an easier way.

Keywords: MATLAB; SLM; MICROPHONE; CEPSTRUM.

Abstract: For every individual person there personal information or data in the most important in there life. No one likes to share there personal information with the others without the reason. The health data of a person is more confidential because none likes to say that I’m suffering from this disease and so on to avoid the problem of leaking of the personal data this Electronic personal health record sharing system is developed. Where patient can upload there data into the cloud and keep there file safely, in order to secure the data the Key Generator controller and admin works. In this patient can able to perceive the important and vital of security to the private information or info(information) in recent years, the rapid expansion of the web technologies and the lot of net users black net, caused to rapid development of the IOT, which has resulted in the introduction of development of numerous unique applications. The e-health commerce system is one among them, as it can give them advantageous, excellent medical care. In the interim, a critical area of interest and consideration is safeguarding the protection and security of a user(client)'s very own well-being information.

Keywords: Cloud, Secret Keys (special key), Advanced Encryption Standard (AES), Rivest Cipher 4(RC4), Key generator controller

Abstract: As we evolve in the field of technology, the applications of the same in our day-to-day life have improved our lives. But this ease comes at a cost since, as the number of appliances used exponentially increases in our society, so does our demand for energy. This energy is usually obtained after destructive emissions are released into the environment, and the wastage of said energy can also be seen in several areas. A survey shows that a plugged-in mobile charger, when not used, consumes 0.1 to 0.5 watts per hour, costing ~15 rupees per day. Such wastage can be expected from other devices as well. Therefore, there is a scope for efficient energy management and, in recent times, it can be done more effectively using automation systems that eliminate the need for human interactions with devices or tools as much as possible. These systems may require the additional fitting of hardware such as sensors that will incur supplementary energy consumption and overhead costs for maintenance. They may also offer low-coverage for detection. Collaterally, it is worthwhile to note that the need for closed-circuit television (CCTV) installations is a basic necessity in several areas of the society and cannot be compromised to conserve energy and yet, we can utilize them to make a region of interest (ROI) energy efficient. This can be achieved through rationing the power consumption of other devices by inferring from an intelligible detection of objects and activities observed by a camera. It is made possible through a technique called Computer Vision (CV). CV, though reducing the workload of building setups for recognition, is a computationally exhaustive technique that requires hardware support to function with an accelerated performance for object detection in real-time. Thus, this work details the different methods available to detect objects and the techniques that can be employed to accelerate the performance of a low power consuming detection system. Graphics Processing Unit (GPU) acceleration and Edge computing are also discussed as a way to offer additional support to CV computation. The advantages and specific drawbacks of each method are also elaborated.

Keywords: Closed Circuit Television (CCTV), Region of Interest (ROI), Computer Vision (CV), Region Based Convolutional Neural Network (R-CNN), You Only Look Once (YOLO), Graphics Processing Unit (GPU), Edge Computing.

Abstract: The compiler often misses significant programme flaws. Finding vulnerabilities and minimizing faults in a software programme is possible through static code analysis. This paper presents an overview of static code analysis using a tool called Coverity.The Coverity Analysis package offers checkers that do runtime analysis of the code with dynamic as well as static analysis. Checkers look for problems in two areas in general: Quality problems Identify any code that, if executed, will fail in some way. Code that is vulnerable to attack is identified by security problems. For developers that want flexible, in-depth, and accurate source code analysis, coverity static analysis is the go-to solution since it yields a thorough insight of the build environment and source code.This paper will give an insight of some types of coverity defects along with examples.

Keywords: Static analysis, tools, alerts, warnings, vulnerabilities

Abstract: Regardless of age, a significant number of people die from persistent lung diseases every year. A crucial demonstration tool for accurately identifying pulmonary diseases is lung sound analysis. In the past, lung diseases were diagnosed manually, but this method was unreliable for a variety of reasons, including low perceptibility and contrast in the eyes of different clinicians for different sounds. Patients suffering from many types of lung illnesses can now receive better treatment since contemporary research yields outcomes with much higher precision. Asthma, bronchitis, emphysema, tuberculosis, and pneumonia are among these problems. Wheezing, exhaustion, rhonchi, and persistent hacking are a few of the negative symptoms. In this project, we are using respiratory sound datasets to predict a variety of diseases, including asthma, pneumonia, bronchiectasis, and others. In order to complete this task, we first took the respiratory sound dataset and the disease conclusion dataset, separated out the components from all of the sound datasets, and then created a convolution brain organisation (CNN) calculation model. We can integrate any fresh test information to the model after it has been prepared in order to foresee infection from it.

Keywords: Admin, Convolution neural network, Cough Sound, Respiratory Disorder, Feature Extraction.

Abstract: Future 5G wireless networks will aspect new contests, as well as growing claim on network capacity to support a huge number of devices running application necessitating high data rates and always-on connectivity; hugely and supportive the emerging business models in the wireless network market demanding networks to be more open. New challenges initiative new resolutions and involve changed plans in the network positioning, management, and operation of future 5G wireless networks equated to those of current wireless networks. One of the key purposes of future 5G wireless networks is to compliantly provide service customized networks to a wide variety of services using integrated cloud reserve and wireless/wired network possessions, which may be presented by several infrastructure providers and/or operators.

Keywords: Future, 5G, Wireless, Capacity

Abstract: Working-class people frequently suffer from mental health illnesses due to stress. In the past, there have been questions expressed about the same in numerous researches. According to a study conducted by the industry association Assocham, more than 42 percent of working professionals in the Indian private sector experience depression or generalized anxiety disorder as a result of their long work hours and demanding deadlines. According to a 2018 Economic Times story citing a poll by Optum [1] that found that half of working professionals in India experience stress, this number of people is growing. Up to 8 lakh employees from more than 70 significant enterprises, each employing 4,500 or more people, responded to the survey, which was taken into account. It is crucial to prioritize keeping the workplace stress-free. It will increase the likelihood that such measures are successful if employees who would require such assistance are identified early. To aid working professionals in managing stress for their mental health, a number of measures can be implemented, including counselling support, career advice, stress management exercises, and health awareness campaigns.

Keywords: Clustering, Random Forest, Decision tree, graph representation, SVM.

Abstract: The aim of this work was to create a React based interface to provide users with a seamless banking experience. It is well known that currently there are several legacy applications which run using HTML/CSS at the back end and would need to be improved upon. On a similar note, we have these banking applications which have a dull user interface and are slow to process. The purpose of this paper is to provide an insight into how the banking industry could implement and integrate a better UI experience for it’s customers.

Keywords: React, Dashboard, Develop, Reporting, User interface, Jules, Testing

Abstract: Organizations now place a high priority on data quality since it might be the key differentiator. There are already several software applications on the market that solve problems with data quality. This study examines the evaluation of data quality solutions created using open-source development practices or made available as free trial versions. The evaluation of Talend Open Studio, Data Cleaner, Informatica Data Quality, Oracle Enterprise Data Quality, and Ataccama's DQ Analyser is specifically covered in this article. Based on performance characteristics and the kinds of data quality issues they addressed, the tools were assessed. In the report, applications of practical tools in data quality programmes that support data governance and master data management activities are also briefly discussed.

Keywords: Data quality, Data Quality Tools, Data Cleansing, Data Integration

Abstract: The complexity of a supply chain makes product safety or quality issues extremely difficult to track, especially for the basic agricultural food supply chains of people’s daily diets. The existing agricultural food supply chains present several major problems, such as numerous participants, inconvenient communication caused by long supply chain cycles, data distrust between participants and the centralized system. The emergence of blockchain technology effectively solves the pain-point problem existing in the traceability system of agricultural food supply chains. This thesis proposes a framework based on the consortium and smart contracts to track and trace the workflow of agricultural food supply chains, implement traceability and share ability of supply chains, and breakdown the information is lands between enterprises as much as possible to eliminate the need for the central institutions and agencies and improve the integrity of the transaction records, reliability and security.

Keywords: Blockchain, smart contract, agricultural food supply chain, traceability, food safety.

Abstract: Interest in blockchain technologies has grown over the past few years. Even while the use case involving financial transactions has received the greatest attention, it could have an impact on other industries. Transparency is increased through blockchain, and the need for reliable middlemen is diminished. This essay examines the viability of using blockchain technology to spot fake goods. This essay covers the various anti-counterfeiting tactics, blockchain technologies, and the traits that make blockchain such an attractive application case. Three different designs have been created, and we are still working to refine an existing system concept. It is known that reducing counterfeits won't be possible by employing simply technological means. Having tamper-proof packaging, a dependable alarm system, raising awareness, and battling counterfeiters legally are important elements. These elements, when paired with blockchain technology, can result in a thorough and effective counterfeiting reduction approach. Some phrases that are similar include blockchain, encryption, and authentication.

Abstract: India, one of the top ten producers and consumers of rice worldwide, heavily relies on rice production and consumption to suit its dietary and economic needs. The early detection of any disease and the administration of the necessary remedies to the affected plants are essential for the health and the development of rice plants. It makes logical to create an automated system because manually diagnosing diseases requires a lot of time and effort. A machine learning-based technique for diagnosing rice leaf disease is presented in this study. The three most prevalent diseases affecting rice plants, according to this article, are leaf smut, bacterial leaf blight, and brown spot. Clear images of damaged rice leaves over a white background made up the input. Following the required pre-processing, the dataset was trained using a range of different machine learning approaches.

Abstract: Next word prediction using machine learning which includes Natural Language Processing (NLP) is a significant part of artificial Intelligence, which incorporates AI, which contributes to finding productive approaches to speak with people and gain from the associations with them. One such commitment is to give portable clients anticipated” next words,” as they type along within applications, with an end goal to assist message conveyance by having the client select a proposed word as opposed to composing it. As LSTM is Long short time memory it will understand the past text and predict the words which may be helpful for the user to frame sentences and this technique uses a letter-to-letter prediction means it predicts a character to create a word. As writing an essay and framing a big paragraph are time-consuming it will help end-users to frame important parts of the paragraph and help users to focus on the topic instead of wasting time on what to type next. We expect to create or mimic auto-complete features using LSTM. Most of the software uses different methods like NLP and normal neural networks to do this task we will be experimenting with this problem using LSTM by using the Default Nietzsche text file also known as our training data to train a model.

Keywords: Predection, Information

Abstract: In this work, we will focus on two development tools provided by Microsoft for creating Windows applications. Win-forms are quite old and very popular since the days of Visual Basic 6. However, Microsoft has now developed a new technology called Windows Presentation Foundation (WPF). WPF is relatively recent compared to Win-Forms and was first released as a component of the .Net Framework with .Net 3.0. Microsoft has never made it clear that WPF will replace Win-Forms or that the two technologies will coexist. Each tool has advantages and disadvantages over the other. Therefore, we will provide a comparison of the two tools in this work. This enables the developer to choose the best tool to create the aforementioned application.

Keywords: Procedural Approach, Design Options, Controls, WPF,Triggers, Layout, Win-Forms, Memory, Templates, Animation, Control Design, User Interface, Framework & Skinning Structure.

Abstract: Building sustainable smart water delivery systems is facing considerable obstacles globally due to the increasing rise of modern cities. Water quality has a variety of effects on how we live our daily lives. Traditional efforts to control urban water quality were mostly focused on conducting routine inspections of quality indicators from the physical, chemical, and biological groups. However, the unavoidable delay for biological indicators has elevated the risk to your health. In this article, we start by looking at the concerns and conducting research. Then, we provide a solution by developing a methodology for risk analysis for the urban water supply system. Indicators are required to identify threats and track changes in the quality of the water. We recommend employing an adaptive frequency analysis (Adp-FA) technique to resolve the data using the indicators' frequency domain for their internal linkages and forecasts. We also investigate how well this strategy scales across indicator, geographic, and temporal domains. For the application, we selected data sets of industrial quality from four different Norwegian urban water supply systems: Oslo, Bergen, Strommen, and Aalesund. We examine the spectrogram, rate the timeliness and precision of the predictions, and compare it to traditional ANN and Random Forest methods. The results show that our method works better in most instances. It is possible to support early alerts for concerns to industrial water quality.

Abstract: Robotic Process automation (RPA) is a new technology in automation of any routine human task which is repetitive. This technology is useful to the organizations that are ready to implement automation. The information regarding RPA is scarce as it is a new technology. RPA is getting corporate attention particularly in digital transformation which is progressing in recent times. Even though RPA is very popular in corporate world, the academic research is lagging behind. The processes which are performed by human are automated by using software robots. The companies use software robots as they are easy to use and very much adaptable. The direct effects of software robots and their indirect impacts on organizations needs to be addressed. In this paper we will discuss about RPA as well as a RPA Tool called Automation Anywhere

Keywords: RPA- Robotic Process Automation, AA- Automation Anywhere, Automation Bots

Abstract: The project presents robust palm vein recognition using hybrid texture descriptors like discriminative robust local ternary pattern and Weber’s local descriptor for improving the recognition accuracy. A Biometric system is actually a pattern recognition system that makes use of biometric traits to recognize individuals. There was a negative effect on recognition performance on fingerprint and palm print biometrics thanks to the some conditions such as oil on the fingers, moisture, and dirt. Therefore, vein patterns stand out from the host of intrinsic biometric traits for development of a recognition system which will meet all these expectations. Vein patterns are the network structure of blood vessels underneath the human skin that are almost invisible to the eye under natural lighting conditions and can be acquired in infrared illumination, which effectively protects against possible external damage, spoof attacks and impersonation. The feel of the blood vessels of different individuals has been proven to be distinctive even among identical twins. Initially the palm vein images are pre-processed to pick the region of interest for vein pattern extraction. Here, local thresholding is employed to extract the vein pattern for its texture analysis. Two textures descriptors called Weber’s local descriptors and DRLTP (Discriminative Robust Local Ternary Pattern) are proposed to extract the features about texture for recognizing with original templates. DRLTP is employed to provide the shape and contrast invariant features of an object. WLD provides details about illumination changes between the pixels. Euclidean distances are going to be used to match the features of test and original templates for making decision on person biometric. Finally the performances of proposed algorithm are going to be measured with recognition accuracy and it proves that it provides better matching rate than prior approaches.

Keywords: Palm vein, Biometric, Weber local descriptors, DRLTP, Euclidean distance.

Abstract: The project is mainly intended to manage the asynchronous requests, responses and provide the filter queries for the transactions of various tenders. The UI used here is the transactions viewer framework. The transactions viewer UI is used to render the data based on the filters provided along with authentication and authorization for the user. The transactions viewer server performs CRUD operations on the transactions using graphql. Graphql has a query operation that manages reading the data and mutations for updating, creating and deleting the data fields. The project offers huge benefits by handling the majority of client requests asynchronously for all the tenders. This saves a lot of time by not requesting the appropriate queries in an order. The platform also offers additional features to improve user-experience, like that of multiple requests management to queries.

Keywords: React, Material Design, User Interface, User Experience, Web Application.

Abstract: An accident is an unpredicted and unintentional event.This system aims at providing early detection of accidents and communicating the information immediately to the emergency responses on time to provide quick assistance for the injured person. When the rider met with an accident. IOT is a system assures to provide immediate assistance to the victim of the accident. The results give exact locations of the accident. This project implements Internet of Things using Raspberry Pi 3b embedded with Global Positioning System and Sensors. This project helps to prevent road accidents caused due to the over speed and if at all accident is inescapable because of various other reasons then providing the victims with immediate rescue and medical assistant.

Keywords: Raspberry Pi 3b, Global Positioning System and Sensors, IOT, over speed.

Abstract: In recent years, there has been a tremendous growth in online applications, especially web applications. From things like net banking or online banking, healthcare or even social media platforms with billions of people worldwide are now using web applications and mobile applications. These applications not only ease our lives but also offer business values. It also offers seamless user experience with its creative user interfaces. All our day-to-day activities become dependent on these applications. And with the development of so many technologies, it is very important to choose the best possible technology or framework. This includes choosing the front-end framework, database and back-end framework. The most trending front-end frameworks in the market are React, Angular, Vue and OJET. While in back-end frameworks Node.js is very popular which uses JavaScript and Django is also gaining popularity and its written in python. Databases can be chosen based on requirements of the project and the scope of the project and can be broadly chosen between either SQL or NoSQL. To develop the API, one can use the REST API principles or can choose GraphQL based on the complexity of the project. These complex web applications can be single page applications (SPA’s) or multi page applications (MPA’s). When we include all these technologies to build the application, it is called a full stack application. There are a lot of combinations of web stacks like MEAN, MERN etc. This paper discusses the popular web frameworks in the front-end and back-end and database environments.

Keywords: Front-end frameworks, React, Angular, OJET, Back-end frameworks, Node.js, Django, Databases, MySQL, MongoDB.

Abstract: Web development has come a long way since the start of the world wide web and it will go a long way with the development of web3, virtual reality and augmented reality. As the internet improved and its reach extended to almost every corner of the world, many new technologies have been developed to build websites and one of the most used is ReactJS. It is developed and maintained by Meta and a few developer communities. For the backend functionalities JAVA Springboot is one of the most used frameworks. Springboot has a strong connection with the database using JDBC APIs. And spring boots ability to make production grade code with minimal configuration makes it more desirable to most of the users.

Keywords: Configuration, DOM, HTML, JSX.

Abstract: Updates for the apps are frequently released nowadays. Therefore, users must have a very smooth experience of updating the app. The aim is to develop an independent SDK that can be easily integrated with any iOS applications. This paper proposes “App Upgrade SDK” that is developed for iOS applications which ensures that the user is notified if there is an update available in the app store and directs the user to the app store if he/she decides to update. In this SDK, three APIs are integrated – one is for checking updates and presenting the user with an update screen, the second is for handling the blocker logic, and the third is for presenting the new features after the app is opened for the first time after updating. These APIs are integrated with app UI using MVVM architecture. MVVM is used to ensure the scalability of the SDK. Fetching the latest version and minimum OS compatibility for the latest version is a challenge. AppUpgrade SDK provides the easiest way to fetch the latest version of the app from Appstore every 24 hours. AppUpgrade SDK is also made customizable according to the developer’s needs. This AppUpgrade SDK can be directly integrated with any iOS application as a development pod.

Keywords: AppUpgrade SDK, Software Development Kit (SDK), Protocol, Delegate, View Controller, iOS applications, Model-View-View model (MVVM) architecture.

Abstract: Due to the impact of a dynamic environment, the need for safety, smoothness, and real-time requirements, as well as the nonholonomic restrictions of vehicles, the study of path planning methods has always been a fundamental and challenging subject, especially in complex contexts. Nevertheless, due to the enhancements they represent for people's ways of life, safer and faster transit, better accessibility, comfort, convenience, efficiency, and environmental friendliness, autonomous vehicles are still popular and appealing. Motion planning needs to be carried out utilizing a variety of techniques to solve the issue of moving through complicated settings that contain numerous barriers. In our project, the ego vehicle must navigate a traffic light-controlled intersection safely, which is a difficult challenge. Using a 3D simulation environment we can successfully and safely provide a solution for the issue of using perception to identify traffic signal placements and statuses despite lighting conditions and occlusions. We simulate various traffic scenarios with various lighting conditions using simulation systems like CARLA and Automated Driving ToolboxTM.

Keywords: CARLA, Motion Planning, A*, Dijkstra's, Radar, Lidar.

Abstract: The advances in the classification of individual cooking ingredients are sparse. The problem is that there are almost no public edited records available. This work deals with the problem of automated recognition of a photographed cooking dish and the subsequent output of the appropriate recipe. The distinction between the difficulty of the chosen problem and previous supervised classification problems is that there are large overlaps in food dishes (aka high intra-class similarity), as dishes of different categories may look very similar only in terms of image information. The combination of object recognition or cooking court recognition using Convolutional Neural Networks (short CNN) and the search for the nearest neighbours (Next-Neighbour Classification).

Keywords: Inverse cooking, Image processing, Food recognition, Deep learning, Text generation

Abstract: Software processes for developing embedded devices is a challenge as devices tend to be long lasting and need regular software updates to sustain in modern world, one such electronic device is Oscilloscope which is used and precision evaluation and testing other electronic instruments. Software plays a vital role in such devices as managing large subsystems can pose a challenge, this paper focuses on software development process by taking a architecture such as SV methodology that resembles some of the existing frameworks of C which provides a better understanding for developers to design and maintain software. Database for embedded systems is less known but provides essential functionality for storage of subsystems. To design a system having a top-level design is essential to understand the instrument database and transactions happening in an oscilloscope. Understanding a product by taking Oscilloscope and focusing the software aspects which directly affects user experience is essential. Linux based systems is recommended instead of bare metal as it has existing essential features which can be used and developer need not implement all basic features from start.

Keywords: Oscilloscopes, Network file System, Instrument database, style, Transaction Manager

Abstract: Cardiovascular disease is the primary cause of death in the nation. Though the data available in the health field is vast, there is still a need to develop a supporting decision system to maintain, analyse, and knowledge evaluation. One such technique that can address such a problem is data mining. Data mining techniques can help to classify whether a patient has heart disease or not. This paper explores the different classification techniques for heart disease prediction. Logistic Regression, Support Vector Machine, Naïve Bayes, Nearest Neighbor, and Decision Tree methods are applied. Build the model to predict new data, and various measures have been taken to assess the classifiers' performance, including accuracy, recall, precision, and F1 score.

Keywords: Data Mining, Heart disease, Data pre-processing, Classification Techniques.

Abstract: Long durations of high blood sugar levels can cause fluid to build up in the focusing lens inside the eye in diabetics. This alters the lens's curvature, which affects how you see. However, the lens normally returns to its former shape and eyesight improves once blood sugar levels are under control. Diabetes patients with improved blood sugar management skills will delay the start and progression of diabetic retinopathy. AOA's 2018 American Eye-Q Survey found that nearly half of Americans were unaware of the existence of diabetic eye illnesses' visual signs (often which the early stages of diabetic retinopathy does not). The American Optometric Association (AOA) advises that everyone with diabetes have a comprehensive dilated eye examination at least once a year because a similar survey revealed that more than one-third of Americans were unaware that the only way to determine whether a person's diabetes will cause blindness is through a comprehensive eye exam. The risk of diabetic retinopathy causing major vision loss can be reduced with early detection and treatment. [1-3] Depending on the severity of the condition, there are many treatments for diabetic retinopathy. In order to stop blood vessels from leaking or to stop other blood vessels from leaking, people with diabetic retinopathy may require laser surgery. To reduce inflammation or inhibit the growth of new blood vessels, your Optometrist may need to inject drugs into your eye. [4-5] In this paper we will deal with image pre-processing and matrix handling. The second problem statement as mentioned in our previous introductory paper is technically dealt with in this paper.

Keywords: Image pre-processing, matrix handling, Diabetes Mellitus, American Optometric Association (AOA), Deep Learning, Convolutional Neural Networks (CNN), Diabetic Retinopathy (DR), Image Classification, retina of the eye, Optometrist, Gaussian filters, Mild DR, Moderate DR, Severe DR, Proliferate DR and NO DR.

Abstract: According to the WHO, approximately 1.3 million people die every year due to traffic related accidents. One of the factors determining survival probability is the response time of the paramedics. This variable depends on the actions of onsite pedestrians or the person responsible for traffic proceedings at the site of accident. We propose the use of a CNN with alternating max-pooling layers to classify images as accident and non-accident to automatically detect an accident over CCTV camera footage. One problem plaguing this field is the lack of available accident datasets, so we prepare the dataset from various sources. The results (training accuracy of 93.78% and validation accuracy of 82.65%) show that the use of alternating max-pooling layers help in accident detection even when the vehicle is not in the centre of the frame.

Keywords: accident detection, convolutional neural network, image classification, deep learning

Abstract: Research has shown that erratic human behaviour such as impaired driving, drugged driving, unbelted vehicle occupants, speeding and distraction are factors in as much as 94% of the crashes in roads today. Automation in this field has the potential to enormously reduce the incidence of such crashes. Higher levels of autonomy mean that the problem of driving is no longer one that human drivers have to solve. This is an area that has gained considerable traction in recent years. The modus operandi in the research community is to understand human driving behaviour and build autonomous units that can imitate this behaviour. This complicated issue domain calls for elaborate solutions that frequently involve numerous modules operating in unison. Each of these modules deals with a particular issue and transmits its solutions to the succeeding modules for processing. The vehicle's controller component, which carries out the predetermined behaviour, receives the ultimate outcome. Additionally, since everything must occur in real-time, prediction speed is just as crucial as underlying accuracy. This sophisticated modular design has been discovered to be inefficient, and deep learning has been found to be a good replacement. Deep learning involves automatically learning complex mathematical functions that characterise a specific domain. Understanding human drivers is a complex task. It involves emotions rather than logic, and these are all fuelled with reactions. It becomes very uncertain what the next action will be of the drivers or pedestrians nearby, so a system that can predict the actions of other road users can be very important for road safety. The car can observe, gather all the information it requires, and interpret it thanks to a 360-degree vision of its surroundings. Once the data is loaded into the learning system, it can think of every possible move those other drivers could make. It resembles a game in which the player must choose the best move from a limited number of options in order to beat the opposition. In this issue area, an autonomous unit's functions include localising the vehicle in its environment, enhancing perception, and actuating kinematic motions in self-driving cars. This guarantees both easy commuting and road safety.

Abstract: Computer Vision is an important field that has been revolutionised by the emergence of Deep Learning and Neural Networks. Object Detection is an important subclass of Object Detection that involves image classification and object localization. There are 2 major classes of object detection algorithms - one stage detectors and multi-stage detectors. Multi-stage detectors like Region-based Convolutional Neural Networks (R-CNN), Fast R-CNN and Faster-RCNN first make region proposals and then make separate predictions for each of these regions. Single stage detectors like YOLO (You Only Look Once) require only one single pass through the convolutional network and predict the bounding boxes in one go. Single shot detectors like YOLO perform better when speed is the most important factor, even more so than accuracy. YOLO has applications in real-time systems like autonomous driving, crowd management, etc. The algorithm developed performs object counting in addition to object detection.

Keywords: YOLO, Object Detection, Object Counting, Convolutional Neural Networks.

Abstract: Fatality on roads is one of the biggest issues due to which people lose their life. The enormous number of participant injuries and fatalities emphasizes the essential necessity for worldwide road safety. Our project focuses on gathering photos, comparing them to the training dataset, and categorizing them as accidents or not accidents. A message is then sent to the nearby hospital along with the coordinates of the accident's location. We employed the Densenet-161 architecture for this project where each layer is connected to all layers next to it. This is done in order to maximize the information flow between network tiers as each layer sends its information gained to all the layers next to it. In contrast to Resnet, it connects features rather than adding features to them to combine features. As a result, the "ith" layer contains I inputs and is made up of all the convolutional blocks' passing features. All other "n-i" layers are split into its own features. Data from on-board cameras is validated using а сомраriсоn with straightforward classifiers that use only video or audio data. This introduces '(n(n+1))/2' connections in the network as opposed to just 'n' connections as in traditional deep learning using a learning system, the learning system is located. The trained algorithm is tested using YouTube clips of related incidents. According to experimental tests, the suggested CAR detection system outperforms various improved classifiers and it offers up to 80% accuracy.

Keywords: CNN, densenet, accidents.

Abstract: Health and fitness have become a priority to a vast majority of the population ever since the COVID-19 pandemic has struck. People have resolved to eat healthy and exercise to ensure good health. The increase in the interest to exercise amidst public movement restriction led to the boom of the remote fitness industry. Various applications such Home Workouts, Nike Fit and Cult.fit prescribe a set of exercises to perform but do not assess how the exercise is being performed. Performing exercises using wrong postures might lead to injuries. Human pose estimation is a technique that uses Artificial Intelligence to detect the pose of a human and calculate angles between different parts of the body. Using human pose detection libraries like OpenPose, computer vision tools like OpenCV and geometry heuristics, appropriate posture correction suggestions can be given. This work aims to develop a solution that bridges the mentioned shortcoming of the remote fitness industry.

Keywords: Human Pose Estimation, Geometry Heuristics, Posture Correction, Remote Fitness Applications, Artificial intelligence, Computer Vision.

Abstract: Classification of underwater SONAR returns is necessary for detecting sea mines under the oceans as they impose serious threats to ships and submarines. ‘Connectionist Bench (Sonar, Mines vs. Rocks) Data Set’ chosen from UCI machine learning repository is considered. The dataset is in the form of a CSV file with 60 attributes and 208 records, 111 patterns obtained by bouncing SONAR signals off a metal cylinder at various angles and under various conditions and 97 patterns obtained from rocks under similar conditions. Standardization preprocessing technique is carried out on the data. Standard-scalar utility class is used to generate scaled data. k-Nearest Neighbour and Standard Vector Classifier classification algorithms are used to train the model, evaluate these algorithms and calculate the model accuracy in each case. Principal Component Analysis is performed for feature selection and the models are tuned using optimal hyperparameters to obtain better accuracy. As a result, the Standard Vector Classifier model gives a better accuracy of approx. 93 % compared to the k-Nearest Neighbour model which gives approx. 88%.

Keywords: Machine learning, SONAR, k-Nearest Neighbour, Standard Vector Classifier

Keywords: BERT, Question-Answering model, sequence-to-sequence model

Abstract: This paper shows the performance of artificial intelligence mainly associated with the swarm intelligence concept to find minima and maxima of a set of benchmark functions. The implementation is basically carried to optimize Neural Networks using swarm intelligence to overcome the effect of training algorithms (Back propagation) which get stuck at local minima or local maxima in many applications, using swarm intelligence. This is a part of research work which is carried to show the performance of above algorithms in finding the maxima/minima of the benchmark functions.. The results shows that these swarm concepts have no tendency to get stuck at local minima or local maxima and proper parameter selection to these algorithms produces excellent results.

Keywords: Ant colony optimization, Artificial. Intelligence, Evolutionary algorithms, Genetic Algorithm, Particle swarm optimization.

Abstract: The Transiting Exoplanet Survey Satellite (TESS) has now been in operation for slightly more than two years, covering both the Northern and Southern hemispheres once. The TESS team uses the Science Processing Operations Center pipeline and the Quick Look pipeline to generate alerts for follow-up. Combined with other community efforts, over two thousand planet candidates have been discovered, with tens confirmed as planets. We present Udva, our pipeline that is complementary to these approaches. Udva employs a combination of transit detection, supervised machine learning, and detailed vetting to identify a few planet candidates that were missed by previous searches with high confidence. We find shallow transits with a high signal-to-noise ratio (SNR) that may represent more than one transit. Future work will include approaches to enhance stages that have been conservatively abandoned because they lacked one or two datums in order to boost the yield.

Keywords: planetary systems, planets and satellites: detection, techniques: photometric, methods: data analysis

Abstract: One of the most catastrophic natural disasters that are extremely difficult to model are floods. Research on improving flood prediction models has helped to lower risks, recommend policy changes, reduce the number of fatalities, and lessen property damage from floods. Over the past two decades, research has shown that machine learning (ML) methods have greatly advanced prediction systems, offering better performance and cost-effective solutions. These methods include logistic reasoning, decision trees, support vector classification, KNN classifiers, and random forest classifiers. The process of modelling the likelihood of a discrete result given an input variable is known as logistic regression. Each internal node of a decision tree, which resembles a flowchart, represents a "test" on an Flood alerts, flood reduction, and flood avoidance are all possible benefits of using machine learning (ML) models for flood prediction. Due to their cheap computational requirements and predominance of observational data, machine-learning (ML) approaches have grown in popularity as a result. The goal of this study was to develop a machine learning model that can forecast floods in the Nigerian state of Kebbi using historical rainfall data from the previous 33 years (33). This model may then be applied to other high-risk flood-prone states in Nigeria. This paper assessed and compared the accuracy, recall, and receiver operating characteristics (ROC) scores of three machine learning algorithms: decision trees, logistic regression, and support vector classifiers (SVR). Compared to the other two techniques, logistic regression produces higher accuracy outcomes.

Abstract: Quick Response (QR) codes seem to appear everywhere these days. We can see them on posters, magazine ads, websites, product packaging and so on. Using the QR codes is one of the most intriguing ways of digitally connecting consumers to the internet via mobile phones since the mobile phones have become a basic necessity thing of everyone. In this paper, we present a methodology for creating QR codes by which the users enter text into a web browser and get the QR code generated. Drupal module was used in conjunction with the popular libqrencode C library to develop user interface on the web browser and encode data in a QR Code symbol. The experiment was conducted using single and multiple lines of text in both English and Thai languages. The result shows that all QR encoding outputs were successfully and correctly generated. Key Words: QR code, Quick Response Code.

Abstract: According to Swami Vivekananda, Education is the manifestation of the society. Education purifies the illness in the society. Universities/Colleges/schools are the temples for everyone. Everyone should visit these temple in their life. It is the responsibility of the teacher should teach the student a perfect education. Every teacher tries their level best to impart quality education. Then only the education reaches everyone. We should have one measurement to know the quality education is reaching every student or not. That is only examination system. Every examination tells about the student performance and level of understanding. At the same time, how to predict the student performance is question raises. It is also an important to know the student future performance. Both parent and teacher can work towards in the direction of improvement. Several machine learning algorithms are exist in the market. The project titled “STUDENT PERFORMANCE PREDICTION USING MACHINE LEARNING” is done for the benefit of students in my studying college with the guidance of my guide. A feasibility study is required to start any project. In any software engineering model, feasibility study is a phase plays a crucial role in beginning of a project. A feasibility study determines if the circumstances are suitable for implementing a specific project. These studies are often performed by engineers. Feasibility studies can be carried out for a variety of reasons, and they are occasionally performed in the IT industry to assess the viability of new hardware and software installations. Here, we have considered this study is very crucial to go next level to complete the task.

Keywords: Machine learning, Feasibility Study, University, School

Abstract: During this global pandemic urgency, scientists, healthcare specialists and researchers continue to look for the high quality feasible treatment of COVID-19 disease. The existence of Artificial Intelligence (AI) and Machine Learning (ML) majorly contributed in finding solutions for ongoing novel Coronavirus pandemic outbreak. Various machine learning algorithms like K-means Algorithm, Support Vector Machine, Decision Tree, have proved their importance in forecasting, predicting, analyzing, and visualizing spread and cautious effects of coronavirus in India.

Abstract: Memory management and computer programming both employ the stack notion. Stack management is crucial because it enables us to identify reliable users who can access any server and make modifications to a specific file or system. Currently, managing pull requests is done on a committed basis, which adds overhead. Additionally, a less time-consuming alternative for managing pull requests is the stack-based method. The main goal is to develop a micro service that uses Kubernetes, Spring boot and React JS to stage and manage the stack for accessing files using instances. Utilizing Spring Boot backend technology, many APIs (application programming interfaces) have been built. In order to test the APIs, these queries are first performed using Postman, and then, after integration with the user interface, they are made directly through the interface. By utilising React JS, a programming language that uses JavaScript, to create a sleek and clear user interface, the entire design is made user-friendly. React JS offers a declarative and component-based programming style that aids in the effective creation of user interfaces, no matter how straightforward or complicated they may be. Additionally, Jenkins was utilised for testing. For each part of the service, the microservice offers several APIs, facilitating future changes or additions. Even when doing several write and read operations to the database, all APIs have lower latency. Additionally, each API has an average response time of less than 400 milliseconds, which improves user experience by saving a lot of time and the tool's responsiveness. The entire microservice has been deployed to the AWS cloud and is available for usage so that files and documents may be accessed without causing concurrency. Since each team will have its own instance, modifications made by one team to a particular file will not be acknowledged by another team. This aids in pipelining usage alteration of files and databases that are crucial to the user.

Keywords: Kubectl, Staging stack, pipelines, Pagination, Instances, Deployment, Kubernetes.

Abstract: Deep learning refers to Artificial Neural Networks (ANN) with multiple layers. These networks are inspired by human brains and contain billions of neurons like human brain for communication. There are various types of architectures of Neural Networks and among all two of them is Multilayer perceptron and Bayesian Neural Network. Multilayer Perceptron is a feed forward neural network with more than three layers. Whereas, Bayesian Neural Network is an extended version of this Multi-layer perceptron neural network that use Bayes theorem to describe the uncertainty in weights so that uncertainty in predictions can be estimated which are not estimated by simple multi-layer perceptron. In this paper Multilayer perceptron neural network having 7 layers and Bayesian neural network having 7 layers is implemented and compared on Bank Telemarketing dataset. Finally, Accuracy, ROC-AUC curve, Binary cross entropy, and KL-divergence loss are used to compare both the models.

Keywords: Neural Networks, Bayesian Neural Networks, Multi-Layer Perceptron, Bank telemarketing, probability distribution, classification.

Abstract: Agriculture is an important sector of Indian economy and India is among the top three global producers of agricultural products. Protecting the crops and producing healthy yields is a prime goal of the agriculture industries. The agricultural crops are susceptible to diseases and demands proactive early diagnosis and treatment. Studies and Research are in progress to find smart methods and techniques for accurate diagnosis of crop diseases to prevent major yield losses and financial losses. The present study outlines the role of Deep Learning in the crop disease detection and discusses the future advancements in maize disease detection. The paper focuses on the Deep Learning techniques used in identification of diseases on maize plant leaf and describes about some common maize diseases and its classification methods. A disease detection process flow is described in the article which explains the steps involved in development of automated disease detection model. The paper shall help readers to gain insight on Deep Learning techniques to solve classification problems and encourage them to proceed for future work in the concerned domain.

Keywords: Agriculture, Convolution Neural Network (CNN), Deep Learning, Image Classification, Maize

Abstract: Chronic Kidney Disease (CKD) or chronic renal disease has become a major issue with a steady growth rate. A person can only survive without kidneys for an average time of 18 days, which makes a huge demand for a kidney transplant and Dialysis. It is important to have effective methods for early prediction of CKD. Machine learning methods are effective in CKD prediction. This document proposes a workflow to predict CKD status based on clinical data, incorporating data prepossessing, a missing value handling method with collaborative filtering and attributes selection. Out of the machine learning methods considered, the extra tree classifier and random forest classifier are shown to result in the highest accuracy and minimal bias to the attributes. We also consider the practical aspects of data collection and highlights the importance of incorporating domain knowledge when using machine learning for CKD status prediction.

Keywords: Chronic Kidney Disease, Data Mining, Classification, Healthcare, Machine Learning.

Abstract: Now in this living era where everything, every process in each sector is being automated. Automation frees human workers to handle the imaginative side of things, leading to better product variety. Internet of Things (IoT) conceptualizes the idea of remotely connecting and monitoring real world objects (things) through the Internet. The system focuses on building a gadget that makes use of the barcode, the user scans for the barcode and the product is predicted and converted from text to speech using raspberry pi. The alert is sent as soon as the barcode is scanned. If the details of the product are obtained after scanning, then it is outputted through microphone. Otherwise, if only the product ID is obtained, the information is obtained through web scraping.

Keywords: Internet of Things, Barcode, Raspberry pi, Microphone.

Abstract: As a part of VLSI technology, millions of transistors is integrated into a single chip called a system on chip (soc). AMBA protocol is much popular protocol for communication of soc component. AMBA was introduced by ARM for on chip communication. AMBA protocal has sub members like AHB, APB, and AXI etc. The APB is used for low bandwidth applications like timer, SRAM, UART etc. Hear in this project, mainly focus on design and verification of APB protocal using UVM, a standard verification methodology nowadays. Also this project involves in creation of coverage report for functionality check of the test bench environment, and also taking coverage report and analysing the design is covered 100% wrt test bench.

Keywords: AMBA, AHB, APB, UVM

Abstract: This study gives the knowledge about facial expression recognition by using hybrid technique. Hybrid technique is nothing but unifying two techniques to increase the recognition rate. Human expressions are fundamentally categorized by six classes, such as happy, neutral, sad, anger, surprise, and disgust. The implementation includes for finding facial expressions are local binary pattern used for face recognition and Haar-cascade classifier for face detection. Joint and transfer learning approaches will produce best outcomes and it will further increase the results. In this paper two techniques are used local binary pattern and local binary pattern histogram with haar cascade classifier. By using these techniques it will detect the facial expression and as well as it will differentiate the recognition rate between LBP and LBPH. This paper will notify the recognition rate of the respective image and it will also show the time taken for training the image. If we employ single technique the recognition rate will be low similarly if we combine two techniques then the recognition rate will be high. Face expression recognition is most effective and these are used in many real time applications by many apps for security purposes.

Keywords: Hybrid technique, facial expression recognition, feature extraction, face detection, face recognition, local binary pattern, haar-cascade classifier, local binary pattern histogram.

Abstract: Cloud computing has grown rapidly in recent years as a novel method. However, because security concerns have had a significant impact on the development and adoption of cloud computing, its importance and urgency must not be overlooked. This paper introduces cloud computing and its security situation, studies the main security problems of cloud computing, and proposes a cloud computing security framework that can effectively solve these security problems. It also points out that cloud computing can continue to expand, and its applications will become more and more widespread, if only the security problems are solved.

Keywords: Scope of Cloud Computing Security, Cloud Computing Security, Research on Cloud Security, Future of Cloud Security.

Abstract: Sudoku is a pretty popular number game. The goal of this game is to fill a 9x9 matrix with unique numbers, and there should not be repeated numbers in each row, column, or block. There are several possible algorithms to automatically solve Sudoku boards; the most notable is the backtracking algorithm, that takes a brute-force approach to finding solutions for each board configuration. The backtracking algorithm uses an array of the legal numbers in the cell to attempt a solution before it moves on to the next cell. If a solution cannot be found, it backtracks and attempts to solve the board again with a different guess choice. The more errors the solver makes, the more backtracks it must perform, which decreases its overall efficiency and increases its effective runtime. We analysed the difference in the algorithm performance by comparing the number of recursive backtracks between sequential and randomly distributed guesses. Analysis show that using values that are given in a shuffled array significantly reduces the number of backtracks done by the solver and, as a result, improve the total effective efficiency of the algorithm as a whole.

Keywords: Sudoku solver, backtracking algorithm, algorithm design and analysis

Abstract: One of the most well-liked frameworks for creating desktop and mobile applications is Angular. It has become more popular among front end and back-end developers since its debut in 2016. It has sophisticated features that improve the structure and effectiveness of code. Business executives should understand how to migrate from AngularJS to Angular and be prepared to do so. Each Angular version provides valuable advantages, but there are several advantages to using the most recent version. Angular is noticeably quicker than AngularJS, has a mobile-first approach, performs better with components, and facilitates easier version upgrades. Rewriting the application essentially gives developers the flexibility to do whatever they want. Use whatever framework you like. The structure of the application may be redesigned and reengineered, and even the application's interface and usefulness can be enhanced. Although the advantages are evident, there are certain more factors to consider before choosing to completely redesign the application.

Keywords: component, directive, MVC,Module

Abstract: The Automatic Parking System (APS) is a globally acknowledged methodology for identifying car licence plates. The number plate of a vehicle can be recognised in real time using APS technologies. Vehicle parking is a crucial part of any transportation system because vehicles are frequently parked at destinations. With an increase in the number of motor vehicles on the road, particularly in developing nations, a vehicle identification system that is effective, economical, and efficient is required. Security guards are utilised for security, parking, and details entrance in most gated communities, restaurants, malls, and other establishments, which is a time-consuming operation that requires keeping track of in the books. This solution was presented to automate the procedure and improve security by ensuring proper detail entry of vehicles. It also shows the parking details of the vehicle with vehicle number search and OTP verification, it shows the applicant parked details as date, in time, out time, and the total charges to be paid by the applicant and we provide a scanner so that they can pay online. The software program was created using an object-oriented analysis and design process, and it uses Optical Character Recognition (OCR) to recognize and capture the car number plate using the camera. The proposed method reduces the time it takes to register from 30 seconds to 6 seconds, while also improving security and ensuring correct data. We may also find the parking and pay option costs using the time calculation.

Keywords: ANN,Mechanism of Action, gene expression, cell viability, drug

Abstract: Plagiarism is the practice of using someone else's words or ideas as one's own. In many nations, plagiarism is considered to be a violation of moral rights. The unacceptable act of plagiarism has been rising significantly in today's environment of developing technology and expanding Internet usage. It is frequently seen in a variety of academic contexts, including research papers, blogs, essays, assignments, etc. In this paper we employed two ways of finding plagiarized text. One method focuses on building a plagiarism detector that examines a specified response text file against a source text file and, depending on the similarities between the two text files, identifies the answer text file as original or plagiarized. In order to create a binary classification model and identify plagiarism, a Support Vector Machine (SVM) was employed. Another method focuses on creating a web application that can identify plagiarism in text, offering a sentence-by-sentence analysis with the percentage of plagiarism and a link to a potential source article, including a method to check for source code plagiarism within a directory.

Keywords: SVM, NLP, Machine learning, Plagiarism Detection, n-grams containment.

Abstract: Seed testing has been developed to aid agriculture to avoid some of the hazards of crop production by furnishing the needed information about different quality attributes viz., purity, moisture, germination, vigour and health. It is very inconvenient to filter out every damaged seed and foreign elements by winnowing in industries and commercial farming. This issue can be minimized if the seeds are filtered in clusters. We have an approach to enhance the efficiency in seed cultivation and seed packaging processes. We created a high-quality dataset which includes fine maize seeds, damaged maize seeds, and foreign elements. By using the Deep Learning technique, the system categorizes an input image as Excellent, Good, Average, Bad and Worst quality seed cluster. The Excellent and Good clusters (sometimes Average) can be cultivated or packaged, and the Bad and Worst clusters can be rejected. We also have recommended the use of object detection to detect and filter out damaged seeds and foreign elements from good quality seed cluster

Keywords: deep learning, seeds, seed cultivation, seed classification

Abstract: The recent advancement in artificial intelligence approach or deep learning techniques explored the ways to facilitate automation in various sectors. The application of deep learning with the computer vision field has resulted in the realization of intelligent systems. World Health Organization (WHO) estimates the road traffic death in India to be 22.6 per 1,00,000 population. Several factors like lousy drivers, appalling road conditions, ignorance of the traffic rules, inability to understand the present road situation and making correct decisions instantly, may contribute to the road crashes and the eventual deaths. Thus an Intelligent Vehicle System has become very important in today's world which will provide an aid to the driver for dealing with road classification, identifying complex road situations and alert him or her beforehand about the probable crash. The technique to be used for vehicle detection is Mask -RCNN. The Mask R-CNN model predicts the class label, bounding box, and mask for the objects in an image. It will be accomplished using an online GPU and cloud services provided by Google Colab by using Tensorflow and Keras framework. The project should successfully detect each car in the image and mark them with independent masks and a bounding box of just the accurate size to fit in the segmented object. We will be able to observe that almost all the vehicles are recognized by the trained model. The model performs satisfactorily for occluded and small sized objects as well.

Keywords: Computer Vision, Image Classification, Scene Detection, Machine Learning, Convolution Neural Network, Places Dataset.

Abstract: Blockchain can make a massive difference to the decentralized food delivery app development - from improving supply chain and commission distribution to regulating restaurant participation and operations tracking. Adding custom functionalities like crypto wallets, different delivery modes, and optimized route detection, can have a powerful food delivery application. The purpose of the project is to reduce the commission taken by food aggregators by creating a peer-to-peer network among restaurant, customer and delivery person. This enables a convenient and easy to use application for all types of users irrespective of their location. The system is based on the Consensus Blockchain network with smart contract protected identity and functionalities. This research work has a database server supporting hundreds of major urban and suburban areas in India. Above all the proposed model provides a comfortable user experience along with the available best pricing.

Keywords: blockchain, consensus, proof of work, peer-to-peer.