VOLUME 11, ISSUE 5, MAY 2022

Abstract: Peer-to-peer (P2P) Data-sharing systems now generate a significant portion of internet traffic. P2P systems have emerged as a popular way to share huge volumes of data. Requirements for widely distributed information systems supporting virtual organizations have given rise to a new category of P2P systems called schema- based. In such systems each peer is a database management system in itself, ex-posing its own schema. A fundamental problem that confronts peer-to-peer applications is the efficient location of the node that stores a desired data item. In such settings, the main objective is the efficient search across peer databases by processing each incoming query without overly consuming bandwidth.

Keywords: p2p.

Abstract: With simulation, we imitate the operation of a real world process or system over time. It requires the use of models; model that represent the behavior or characteristics of the selected process or system. Computer are used to execute the simulation. In operating systems, OS-SIM is one of simulation application to represent the system characteristic or behavior of any process scheduling algorithm. Several scheduling algorithms in operating systems are available. There are preemptive shortest job first scheduling algorithm and non-preemptive shortest job first scheduling algorithm in operating system. Preemptive shortest job first scheduling algorithm is where when the shortest process arrives and is positioned at the head of the queue and interrupted the longer process. In this journal, we simulate preemptive shortest job first (SJF) algorithm with OS-SIM. Case study is discussed to understand the simulation thoroughly.

Keywords: Preemptive Shortest Job First, Scheduling Algorithm, OS-SIM

Abstract: Nowadays, we are facing many problems of environmental pollution. One of them is the process of waste management since the amount of waste is proportional to the number of people in urban areas. The classification of waste plays an important role in the recycling of waste contributing to minimizing the risk of spreading pathogens, toxic and dangerous elements. We are in the fourth industrial revolution, applying cutting-edge technology is the trend, specifically deep learning techniques in the waste recycling process. Smart waste recognition also contributes to saving human resources and reducing costs for waste collection and recycling. In this paper, we propose a waste detection and classification model based on YOLOv4 architecture. We experimented and obtained mAP of 90.27%, F1-score of 86% on the dataset that we synthesized including 4 main types of waste: plastic, metal, glass, and paper.

Keywords: Computer Vision, Object Detection, Classification, Deep Learning, YOLOv4.

Abstract: E-auction plan using cryptography is a web based application.This project will be done using ASP.Net as front end, and MY SQL as back end. Online auctions are among the most influential e-business applications. Despite efforts to set up marketplaces, online trading is still a relatively early stage. Very few companies have started their projects, trying to improve their buying and selling channels. The online auction program carries an online auction of various products on the website.

Abstract: One of the more intriguing project ideas that can be executed is the Android law system project. Our country's crime rate has steadily risen. The criminal provisions enshrined in our constitution are mostly unknown to the general public. The task would be much easier if they knew which legislation applied in which circumstance. This is a one-of-a-kind project idea. There are two options for implementing the android legal system project. The developers can put it in place while considering how the users will benefit from it. The administration can also be taken into account.

Abstract: Now Technology has unfolded in each and every area of our lives. In existing era, everybody is having some kind of connectivity with science whether or not in shape of mobile, laptop computer or others. Here we are going to talk about the use of technological know-how infield of domestic security. In this system, we are the usage of ARDUINOUNO microcontroller board. This device is primarily based on door lock security with the assist of two excessive degree safety passwords and simultaneously the machine would be related with owner’s mobile smartphone via GSM Module So that the proprietor ought toopen the door from far flung area also. When any licensed would attempt to open the door, he would have to enter two passwords when requested to do so. If he enters right passwords then the door will get open. But in case, he enters any of the two or both passwords incorrect then the gadget would get alert and ship a message to the proprietor to ask him whether or not it is he or now not and work accordingly. This device will be defend to Homes, Shops, Banks and establishments etc.

Keywords: Arduino Uno, GSM Module, Solenoid Lock, Home Security, Door Security

Abstract: The content of the material caching strategy is the way of using mobile community sources successfully. From a caching perspective we have a look at Small Cell Base Station Networks (SCBSNs). Firstly, Small Cell Base Stations are deploying with low doable backhaul links ,and have excessive functionality storage units. Define a Quality of Experience (QoE) metric in order to satisfy a given file request. To maximize the Quality of Experience (QoE) metric for beneath ability of constraints .For that we formulate the optimization hassle in order. We use an algorithm called “my caching” that relies on potential constraints. This algorithm selects the most popular documents until the total storage potential is achieved. Here the proposed caching algorithm is compared with Prop Caching for rows.

Abstract: Soil is an important key issue of agriculture. The target of the work is to predict soil sort using data processing classification techniques. Soil sort is expected victimization data processing classification techniques like JRip, 148 and Naive mathematician. These classifier algorithms are applied to extract the data from soil data and 2 forms of soil are thought-about like Red and Black. During this paper, data processing and agricultural Data Mining are summarized. The JRip model will manufacture a lot of reliable results of this knowledge and therefore the alphabetic character Statistics within the forecast was accrued. For finding the problems in huge knowledge, economical strategies may be created that utilize data processing to boost the exactitude of classification of big soil knowledge sets.

Abstract: Remote sensing data and field measurements were combined in this work to produce a simple yet reliable method for calculating tobacco hectarage and yield in Zimbabwe. Tobacco yield projections are currently based on seed purchase records. Land area records, and a visual assessment of the crop. This is prohibitively, time-consuming, and unreliable. Starting in September-2010 and endingin September-2013, Landsat Thematic Mapper Composite of agricultural field boundaries in pseudo natural Colour (TM) Satellite imagery was Digitised and graphically interpreted. MODIS photos that are cloud-free and cover the time period the data was retrieved and georeferenced data from September until the end of march. The NDVI was calculated for every MODIS image. Estimated. These crops’ mean temporal NDVI profiles for these crops were created. using data from sampled tobacco farms calculate and compared on its own. According to the findings of this study, the third to fourth weeks of November and the third to fourth weeks of February are the best times for distinguishing irrigated from non-irrigated tobacco on MODIS NDVI data. Model of regression in comparison to the previous three seasons, the average yield projections were 98.8% accurate. The traditional method received 122 percent of the vote.

Abstract: The design of the trial is two factorial R.B.D with 8 treatments and three replications. The treatments comported of four situations of potassium (K2O@ 80,120,160 AND 200 kg/ha) and two spray schedule of N@ 2 as foliar spray schedule of Urea. Results attained in the present disquisition reveal that the maximum vegetative growth parameters like factory height (149.72 cm), number of famers per factory (3.23) and number of leaves per factory (18.40) were recorded with the operation of potassium and nitrogen i.e, K2O@ 200 kg/ha N@ 2 double spray as compared with sole effect of both the nutrients. Yield and yield attributing characters were also plant to be told much with the operation of K2O@ 200 kg/ha also proved effective towards the number of primary rhizomes. The combined operation of K2O@ 200 kg/ha N@ 2 double spray indicated better rhizome product through enhancement of length and weight as also secondary rhizome product per clump. The operation of K02O@ 200 kg/ha N@ 2 double spray recorded significant on the yield per hectare (36.82 t/ha). The sole operation of potassium and nitrogen also showed significant variation with respect to yield per hectare. A progressive increase with the oleoresin content of turmeric is recorded with the adding boluses of potassium and the number of sparys of nitrogen. Still, the loftiest oleoresin content also impact significantly with sole operation of potassium and nitrogen. The operation of K2O@ 160 kg/ha N@ 2 single spray recorded advanced curcumin content (6.19) of turmeric as compared to double spray of N.

Keywords: Turmeric, Curcuma Longa, Potassium and Nitrogen.

Abstract: Two on-farm experiments were carried out in the coconut belt of southern Ghana from 2006 to 2009 to evaluate growth of young coconut plantings and yield of old coconut fields and their nutrient status under coconut-cassava intercropping system. For plantation managers, simulation modeling of perennial crops has enormous potential for providing data .we provide updates on the info crop- coconut project model and its application to the cultivation of coconuts variety of tropical and subtropical climates the model is based on the info crop crop model ,which simulates a variety of crops.

Abstract: Standardization of crop yield estimating methodologies at various levels of farming aids in the development of accurate agricultural statistics and the evaluation of agricultural practises' acceptability under diverse production situations. The current research examines various strategies for estimating maize yields.It examines the yield difference between maize and other crops, taking into consideration available yield factors.produce potential and attainability The simplest and most reliable approaches for estimating yield are based on yield parameters gathered on the job Farmer estimating approaches, on the other hand, are less expensive and speedier in comparison to any other way of estimating yields from farmers' fields. This document also goes into detail about the significance of using more advanced yield estimation approaches, such as remote sensingas well as crop modellingThese complicated approaches are more time-consuming.

Abstract: In recent years the wireless communication are advance in information technologies in demand of quality and the level of heterogeneity are finds more number of resources. The prompt conjunction of multimedia facilities such as wireless communication in recent years, the rising incorporated wired Wireless system is have been developing pattern of heterogeneity. The multimedia communication system is like an W-LAN are using today wide range communication.

Abstract: People utilising smart phones has expanded rapidly in today’s society, and thus a smart phone can be Utilised effectively for personal security or other types of protection. The horrible occurrence that Horrified the entire nation has reawakened us to the importance of addressing safety concerns, and as a Result, a slew of new apps have been developed to equip women with protection systems via their Phones. This Android Application for Women’s Safety and Security can be triggered with a simple click if The need arises. A single click on this app recognises the location of a place using GPS and sends a Message to the registered contacts with the location URL, as well as calling the first registered contact to Assist the person in danger.

Abstract: In the topic of parallel computing, load balance is being studied. Standard algorithms and dynamic algorithms are the two basic approaches. The technique of allocating a set of jobs among resources with the purpose of improving overall processing efficiency is referred to as load balancing. The multi-variable difficulties are load unbalancing, computer resource efficiency, and performance degradation, and the problem is multi-constrained. The process of load balancing is the distribution of workloads across numerous computing resources. The document management system maximizes resource. availability. DNS load balancing, on the other hand, uses software or hardware to execute the function.

Abstract: papaya ( carica papaya col) is well known for its exceptional nutritive and medicinal parcels throughout the would from the times old, the whole papaya factory including its leaves seeds ,ripe and callow fruits and their juice is used as a traditional drug .The fruit has a large round shape ,unheroic -green skin and unheroic meat. Currently , papaya is considered as a nutraceutical fruit due to its multi-faceted medicinal parceis. The prominent medicial parcels of papaya include anti-fertility , Diuretic anti-hypertensive , ,Anti-helmintic ,Crack-mending Anti-fungal ,Anti-bacterial , Anti-tamor and free radical scavenging conditioning . , the whole factory contains enzymes (papain) ,alkaloids , , flavonoids ,minerals and vitamins .In the present review composition ,a humble attempt is made to collect all the strange data available about this delicious fruit .

Abstract: According to the research, employee training aimed at raising awareness of the importance of preserving the organization's sensitive data is ineffective.Furthermore, popular third-party cloud services make it much more difficult for employees to safeguard their company's secrets. As a result of this critical issue, a considerable market for software products that enable endpoint data security for these businesses has emerged. Endpoint protection platform (EPP), a conventional, negative endpoint protection strategy, and endpoint detection and response, a novel, positive endpoint protection method, will be discussed in our research (EDR). There will also be a comparison and evaluation of EPP and EDR in terms of mechanism and effectiveness.The study will also look at the benefits, flaws, and critical characteristics that a good security programme should have. The goal of this paper is to help small and large businesses better comprehend insider dangers in today's fast evolving internet, which is full with potential threats and attacks. This will also help businesses gain a better understanding of their employees' endpoints, allowing them to prevent data leaks in the future. It will also assist careless users in understanding the gravity of the problem they are facing and how they should protect their privacy while surfing the Internet while connected to the company's network.

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

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

Abstract: We have presented an overview of strategies used in the applied behavioural sciences to assess variables. The majority of the methodologies are employed to varying degrees by quantitative/positivist and qualitative/constructivist researchers. Qualitative researchers prefer less regimented, more open-ended data collection procedures than quantitative researchers.

Abstract: The objective of this dissertation is to propose an improved ensemble classifier method based on Neural Network and Gaussian Support Vector Machines, for cyber-attack classification problem. Previous work done [1] using hybrid techniques for Cyber attack classification was suffering while working with less amount of data also the structure of hybrid technique is very complex. The improved ensemble classifier is built using two different types of classification techniques. In the proposed method base classifier is the Support Vector Machine and another one is Neural Network classifier. The process of ensemble is done by bagging process, which uses multiple kernel function. The multiple kernels are Gaussian in nature.

Keywords: Cyber,Neural network, SVM, Optimize, GSVM.

Abstract: The E-health model system allows people store large amount of information in different place. In many of the developed countries, healthcare has evolved to a point where patients can have many different providers– including primary care physicians, specialists, therapists, and even alternative medicine practitioners – to service their diverse medical needs. Telemedicine system is receiving great importance due to current changes in healthcare sectors all over the globe. The need for medical sectors to provide appropriate and precise remedy for various diseases is essentially increasing as they are facing new challenges every day. There comes a big problem that the information sharing increased the risk of medical misuse and data theft. The E-health record may include the patient personal information, like telephone number, age and so on, even more, the diabetes patients’ glucose, exercise information which are private, sometimes, the patients just want to share their relative information to their physician. Data theft can invade to patients’ medical records and stole patients records to do financial fraud. In order to forbidden this crime, how to keep the privacy and security becomes the key point in our work.

Keywords: Telemedicine, Data-Mining, Tools, Techniques, Medical-Data.

Abstract: Most facial recognition computer systems, including two-dimensional and three-dimensional systems, follow a basic algorithm. The algorithm consists of analyzing nodal points. Nodal points, in this case, are specific pixels on the face highlighting various facial features. These points combined are called a faceprint. Once the computer creates a faceprint for a captured face, it will try and match it to a face in the database. However, there is no guarantee that computers will be correct. During this research, the objective was to determine the probability that a novel GUI-based software program can match a subject’s captured facial photograph to the same subject’s photograph in a database, and to determine a facial recognition system’s accuracy. Two images of a voluntary sample of subjects were acquired. One set of images’ Sum Of Weighted Ratios (SOWR) value was saved to the program’s database and the second set acted as the captured images. The SOWR values were determined with internodal distances, ratios and weighted ratios. To decrease bias, a simulation was performed with a sample size of 10% of the population. An in-depth analysis of the average, standard deviation and matched pairs T-Test was performed to determine the significance of the difference in SOWR values. (Ideally, the difference of the two SOWR values of each subject should equal 0). Once statistical significance existed for a match, the expected value, or probability, of finding a match using the GUI-based software program with a margin of error was calculated to be 45%.

Abstract: Inventory management system which is helpful for the business operators, where shopkeeper keep the records of purchase and sales. This inventory is eliminate paper work, human faults , manual delay and speed up process .This inventory management system will have the ability to track sales and available inventory, tells a shopkeeper when it’s time to reorder and how much to purchase. Inventory management system is windows application developed for windows operating systems which focused in the area of inventory control and generate. We aim to make a hassle free Inventory Management System for the staff to keep track of the supplies and raw material, eliminating the need of manual book record system. While making this project we have used the basic as well as advanced knowledge of accounting for better used experience. The software is made up of two parts: The frontend is developed using IIS, .Net Framework and the Backend from MS SQL Express 2019.

Keywords: Hotel Inventory Management, MS SQL Express 2019, IIS, .Net framework, Web Application

Abstract: This kit will help doctor and their staff to monitor their patient accurately and take decision as fast as possible to help to improve their quality of service to patients. This system introduces a smart patient health tracking technique that utilize Sensors to track health of patience and uses wireless internet to inform their loved ones in case of any emergency or issues. Our system uses temperature as well as heartbeat sensing for monitoring the patient health. The sensors are bridge to a microcontroller to monitor the report which is in turn interfaced to an LCD display as well as WIFI connection in order to transmit issues in the particular range. If system detects any sudden changes in patient heartbeat or any sudden changes in body temperature, the system automatically alerts the end user about the patients status over IOT and also shows piece of information of heartbeat and temperature of patient live on the internet. Thus IOT based smart patient health tracking smart kit effectively uses internet to monitor health of patience stats using android platform and ardino and save lives on time.

Keywords: Flood detection system, Arduino, Android platform, monitoring system

Abstract: We are introducing a grocery android application which will help user to add local shop nearby its home. This application can even provide local stores new customers and even a reminder list. Here our main moto is to reach to the nearby or local stores, to gather small stores data which even other online app don’t register and how to increase its sales. User can even set a particular time range on which its product needs to be refill.

Keywords: Grocery System, Android Application, Data collection, firebase

Abstract: The e-marketplace has evolved as an efficient and important vehicle for e-commerce industry transactions. The academia and industry also recognized trust as a central factor for enabling e-commerce. Here, it includes two parties called buyers and sellers, we need to design and implement a system that will check both parties, because both parties should have trust in one another when transacting. Our project operates an online marketplace for consumer sales. It mainly targets users in emerging markets, by providing safe, reliable and efficient way for consumers to buy and sell goods. Our application provides information about all the nearby available products like plants, seeds, pesticides, agricultural machinery to all its users. The information retrieval facility, marketing from any place, and getting statistical information about fertilizers, pesticides, seeds, and plants are the main features of this application.

Keywords: e-marketplace, e-commerce, agriculture, farmers.

Abstract: iIn iour idaily ilife, iwe igo ithrough idifferent istages iand idevelop ia idifferent isense iof iemotions i. iThese ifeelings iand iemotions iare iexpressed ias ifacial iexpressions. iBusiness icommunities itoday iprefer ito iuse iemotional imarketing. iIn iemotional imarketing, ithey itry ito istimulate ithe iemotions iof ithe icustomers ito ibuy iproducts ior iservices. iThis iwork iwill ifocus ion ianalyzing ithe igender, iage iand ifeelings iof ithe iuninitiated ito ihelp iorganizations idevelop istrategies ithat ihelp ipeople ifeel idepressed, iexpand iefficiency iand iimproving itheir iemotional istate. iIn ithis iregard iwe iwill ibe ideveloping ia imini-Xception ibased iXception iand iConvolution iNeural iNetwork i(CNN), iwhich iis ieasy ito ifocus ion ias igood iparts ias iface iand icarry isignificant iimprovements iin iprevious iactivities. iA ilarge inumber iof iresearch iwork idoes ibest iin icontrolled idatabases i(i.e., ismall idata isets iwith ismall ifeatures), iwhile ifailing ito ifunction iproperly iand ithe ichallenge ito idata isets ivaries ithe irotation iof iimages ieven iin iimperfect ifaces. iIn irecent iyears, imany iactivities ihave iintroduced ia ifinal iword irecognition isystem, iusing iin-depth ireading imodels. iAlthough iemotions irecognition iis ia ihuge iundertaking, iit iseems ithere iis istill ia ilot iof iroom ito ibe ideveloped. i

Abstract: Alzheimer's disease (AD) is a health disorder that affects brain functionality and slowly destroys memory. These days Medical Treatment turns out to be exorbitant which builds demand for e-medical services (electronic medical care). In this research paper, I propose a Smart Health Monitoring System which helps Alzheimer's patients consistently observing of their health symptoms. The patient's location and movements can be followed and recorded with the assistance of GPS and the Internet. Subsequently, a medical specialist can perform a remote diagnosis of a patient's health condition. The e-medical services system is expected to work with clinical therapies, improve the life quality of patients, and minimize medical services costs.

Keywords: Alzheimer’s disease, health care, Remote Health Monitoring, and E-Healthcare.

Abstract: In finance sector online digital transactions are rapidly growing in world global market. Due to pandemic condition every part world uses the digital transaction to purchase daily used commodity. According the world payment report, digital transaction are drastically increase more than double after pandemic. As online transaction rapidly increases properly false and fraud transaction has been increased. According the survey report more than seventy percent of customer in India are confusion about digital transaction which is more percentage than last two years. In this paper we have addressing various machine learning approaches to detecting false or fraud transaction.

Keywords: Machine learning, Supervised learning, Unsupervised learning.

Abstract: The COVID-19 pandemic has led to the closure of educational establishments all around the world. To keep academic activities alive, most educational organizations have switched to online learning platforms. Since, problems about e-learning readiness, design, and efficacy remain unanswered, particularly in developing countries like India, where technological barriers such as device compatibility and network availability represent a severe issue. Studies suggest that digital learning can be as successful as traditional education that requires appearance, but learners for online training, especially in adapting different learning methods to online mode is very much crucial. Few studies have examined the satisfaction of e-learning[1][2]. According to the data, students' reaction to online teaching depends on their ability to use online tools, their ability to technically access e-learning materials, and their teacher's style of different learning activities. In this paper, we have clearly analyzed, examined and predict the impact of online education system by using different Machine Learning classifier and ensemble algorithms. We have collected some real time data to show some insight reviews on the satisfactory level of e-learners after pandemic.

Keywords: Algorithms, Machine Learning, Online Education, Predictive Analysis.

Abstract: A comprehensive and relevant performance review procedure should be initiated at the start of the academic year. The increasing number of colleges has expanded in recent years, emphasizing the importance of enhanced approach performance in worldwide competitiveness. Institutions can use performance evaluation to develop future initiatives. Every lecturer must define annual goals for each category.[1] Complete performance evaluations give constructive feedback and direction to help lecturers develop and improve. Using various Machine Learning classifiers and ensemble methods, we have clearly studied, assessed, and predicted the impact of online education systems in this study. The primary objective of this study is to explain the relevance of higher education in performance evaluation of students.

Keywords: Algorithm, Machine Learning, Performance Evaluation, Predictive Analysis.

Abstract: Mood and emotion play an important role when it comes to choosing musical tracks to listen to. In the field of music information retrieval and recommendation, emotion is considered contextual information that is hard to capture. Modern day entertainment and music streaming has largely been dependent on digital technologies. People prefer subscription based online services for buying physical copies of the music albums. online streaming services like Spotify, apple iTunes, google music offer great services to the listener with ease. However, drawbacks to these systems includes long delays in payouts for the artists, lack of transparency, confusing payments and licensing terms and so on. In order to give solution to these drawbacks the proposed system is an interface which is used between the user (fans or melomaniacs) and the independent musicians without involving the third parties and thereby satisfying the user by fetching them the songs of their mood by using the sentimental analysis. we have proposed it as a collaborative work by which the artists gets benefited as well as the user gets satisfied with the help of machine learning techniques.

Keywords: Melomaniacs, Machine Learning, Sentimental Analysis,

Abstract: This ipaper ipresents ithe idesign iof ian iembedded isystem ito idetect ithe isynchronization ifailure iof iany iexternal isupply isource iwith ithe ipower igrid. iIt isenses ithe iabnormalities iin ifrequency iand ivoltage. iA iprototype ihas ibeen ideveloped iand itested, ithe iresults iin ithe iform iof ipictures iof iLCD idisplay iare ishown. For ithe iproject, irange iof ifrequency iis i48Hz ito i50Hz iand i ivoltage irange iis i200V-240V. i

Abstract: : In today's world where we make things easy for our needs. We have created a program for the deaf worldwide. A simple and efficient system is an hour's need and in this busy world translating is a very tedious task. The tool can detect hand gestures in real time, captured using a webcam / camera. We used PYTHON IDE to process the program and display the translated text. Using TensorFlow, Keras, CNN to train our model. A large database to increase the level of matching and have the right system or tool to keep things simple and stable. We did not use external hardware to make the project cost less and easier to move from one location to another. It can be used for heavy loads with large databases. By using the python we can easily process the image and insert it into database. TensorFlow, Keras modules are very useful to use. The database is easily created and processed with the help of the modules we use. Creating a large database will help us to reduce the error in feature detection and touch detection.

Keywords: Gesture Recognition, Sign Recognition, CNN, Histogram

Abstract: News online has become the major source of information for people, much information appearing on the internet is dubious and even intended to mislead. Automated fake news detection tools like machine learning and deep learning models have become an essential requirement also used stemming, lemmatization, stop word techniques to obtain text representation for machine learning and deep learning models respectively. We use Kaggle dataset, for defining the fake news. This would allow to provide a filtered subset of fake news to end users. The advent of the World Wide Web and the rapid adoption of social media platforms (such as Facebook and Twitter) paved the way for information dissemination that has never been witnessed in the human history before. With the current usage of social media platforms, consumers are creating and sharing more information than ever before, some of which are misleading with no relevance to reality. Automated classification of a text article as misinformation or disinformation is a challenging task. Even an expert in a particular domain has to explore multiple aspects before giving a verdict on the truthfulness of an article. In this work, we propose to use machine learning ensemble approach for automated classification of news articles. Our study explores different textual properties that can be used to distinguish fake contents from real. By using those properties, we train a combination of different machine learning algorithms using various ensemble methods and evaluate their performance on 4 real world datasets. Experimental evaluation confirms the superior performance of our proposed ensemble learner approach in comparison to individual learners. Along with the data, our understanding of AI also increases and the computing power enables us to train very complex and large models faster. Fake news has been gathering a lot of attention worldwide recently. The effects can be political, economic, organizational, or even personal. This paper discusses the approach of natural language processing and machine learning in order to solve this problem. Use of bag-of-words, n-grams, count vectorizer has been made, TF-IDF, and trained the data on five classifiers to investigate which of them works well for this specific dataset of labelled news statements. The precision, recall and f1 scores help us determine which model works best.

Keywords: Fake news analysis, real news, Keywords Internet, social media, Fake News, Classification, Machine Learning.

Abstract: "What if we can bring our imagination into reality?" This is something this paper is trying to address with the help of image style transfer and CLIP. Image Style transfer is a technique used to take two images- a content image and a style reference image and blend them together so the output image looks like the content image, but “painted” in the style of the style reference image. As stated above, existing style transfer methods require reference style images to transfer texture information to content images. But what if one does not have a reference image but is still interested in transferring styles by just imagining them? To overcome the above issue, here we are using text-to-image embedding model of CLIP to perform text-driven image style transfer without the use of a style image as a reference. We also use a CNN Encoder-Decoder Model to capture the visual features of the content image and simultaneously stylize the image to obtain a realistic texture representation. Finally, the above model is deployed as a web application from which users can perform style transfer by uploading an image and specifying the desired styling with the help of a text description.

Keywords: Style Transfer, CNN, CLIP, VGG, U-Net.

Abstract: Crop monitoring is just harvesting the crop to get the best yield possible with the resources available. However, nowadays, crop monitoring also includes protecting the crop against theft or damage caused by unplanned weather changes. Farmers can employ cost-effective and user-friendly technological solutions such as highly dependable sensing equipment and their interaction with mobile networks to suit their monitoring needs. Farmers are more involved in many unproductive activities nowadays, such as defending the crop from human or animal intrusion, which may result in theft or harm to the crops that the farmers have grown over time

Keywords: IoT, Agriculture, Crop Protection, Arduino, Sensors

Abstract: In 2019 COVID-19 virus has spread to the various parts of the world including Indonesia.This pandemic becomes a lethal outbreak since there is no vaccine to treat or prevent transmission of the virus. Rapid Test is selected as an essential method to detect Covid-19 in Indonesia because the price is fairly cheap compared to the SWAB test. The increase in Covid-19 patients tends to lead to limited capacity for the Covid-19 test available at the hospital so that the latest technology to detect and overcome this pandemic is- sue is needed. Thus, the present research aims to examine the total of 100 X-Ray chest images of the Covid-19 patients and 100 X-ray normal chest images. The application of Contrast Limited Adap- tive Histogram Equalization (CLAHE) and Convolutional Neural Networks (CNN) methods are implemented to analyze the dataset with two scenarios in obtaining the detection results. The results of this research reveal that the application of CLAHE is likely to affect Covid-19 detection accuracy using CNN. Also, the application of the CNN basic model shows significant results compared to the applica- tion of VGG16 transfer learning.

Keywords: COVID-19, Multimodal Imaging, Machine Learning, CNN, Neural Network.

Abstract: In Global scenario the prime question in every girl’s mind is about her safety and the harassment issues. The only thought hunting every girl is when they will be able to move freely on the streets even in odd hours without worrying about their security. Our project suggests a new technology to protect women. Our project “A WEARABLE SYSTEM TO SAFEGUARD A PERSON” describes about safety electronic system, which is basically a shock generating jacket for providing security to the person who will wear it. It will not only give shock to the person who is going to touch it, but it will also share an “Emergency SMS”, connect call, share location of the victim to the pre-defined numbers. It will also upload photos of the surroundings of the victim to the server and provide self-shock protection to the victim.

Keywords: Shock generating Jacket, Stun gun technology, GPS, GSM, Self-shock protection, Camera

Abstract: Based on the surveys conducted water management has become very difficult and the issues are arising frequently because of insufficient supply of water resources and degradation in water quality. So we have to effectively utilize our water resources efficiently by real time monitoring of water quality parameter to differentiate the quality of the water. Some areas in a city will have stable supply of water resources while compared to other cities based on the supply channel. This is due to some problems in the distribution line such as defects or cracks in pipeline caused by over pressure or low water pressure where in water cannot reach consumers located on a high-ground areas or far away from the pumping stations or water tank. All of these issues concerning water distribution arise because on lack of real time monitoring of these water resource and also because of complex manual testing procedures and time taken by it. Today, cities are now transforming rapidly and people rather concern themselves about their comfort regarding the issue. As they participate for economic advancement and our standing regarding their contribution in saving these natural resources, water has become a priority in their checklists. Creating water sustainability requires a multidisciplinary approach. It also requires awareness and state of the art facilities to be given by the national authorities which can give a significant boost to these movements regarding water management.

Keywords: IoT, Water quality, monitoring, pH, detection.

Abstract: The medical imaging community has long been interested in brain tumor segmentation, which is an important yet difficult issue. Successful applications of sparse coding and dictionary learning in different vision issues, including picture segmentation, have recently emerged. A superpixel-based framework for automated brain tumor segmentation is presented in this research. It is proposed that the procedures that make up the split and merge technique be reformulated. First, a recursive split is performed; subsequently, after the merge procedure, an image segmentation is acquired. This is possible because the merging is done as a growth process, removing the need for grouping. The usage of a complete quadtree aids in the reformulation process. Because of the differences in nature of the two processes, the region homogeneity in each process is determined using a different predicate. Experiments with a blocks world image and an industrial components image are presented to demonstrate the algorithm's effectiveness.

Keywords: MRI, Brain Tumor, Segmentation, Superpixel, Split and Merge

Abstract: Sign language is indeed the best mode of communication for people who are unable to talk or pay attention to anything. Sign language allows physically challenged people who are physically challenged to express their thoughts and emotions. There are numerous methods for recognizing hand gestures, including Random K-NN, Tree K-NN, and Fuzzy K-NN. The K-Nearest Neighbor method seems to be worth investigating. While the weighting method is used to improve classification accuracy, the Simple Multi-Attribute Rating Technique (SMART) can then be used to optimize classification accuracy results. A novel framework of signal language reputation has been presented in this project for determining the alphabets and gesticulations in signal language. We can locate the symptoms with the help of computer imaginative and prescient neural networks.

Keywords: Sign Language Recognition, Convolution Neural Network, Image Processing, Edge Detection, Hand Gesture Recognition.

Abstract: This project is about developing a cross platform application. Nowadays, gadgets are rolling around the world. Many people cannot imagine even one day without their favorite mobile device. We use them for everything: find information, stay connected with our friends and families, find the way around, decide what to do, and many other things. But very often we want to order some food we like but going to the restaurant is not convenient. Developing an application usually takes lots of time and needs professional knowledge of software. And then as people do not find the application they tend to wait until somebody is developing one, or they have to go to the web and ask people to implement their ideas. On different forums there are tons of brilliant ideas but they will wait until developers will see them. On the other hand, there are lots of enthusiastic developers who are looking for ideas to implement them. The project has been planned to be having the view of distributed architecture, with centralized storage of the database. The application for the storage of the data has been planned.

Keywords: React Native, Android, iOS, Application.

Abstract: A music genre is a term used to classify certain types of music as belonging to a common tradition or set of rules. It must be distinguished from musical style and form. Music can be classified into several genres in a variety of ways. Pop, hip-hop, rock, jazz, blues, country, and metal are some of the most popular music genres. Machine learning techniques have been used for music genre classification for decades now. As the amount of music released on a daily basis continues to rise, especially on online platforms like Soundcloud and Spotify — according to a 2016 estimate, tens of thousands of songs were posted on Streaming services every month. Music classification is increasingly widely used by businesses, whether to provide suggestions to clients or simply as a commodity. The initial stage in the music selection process is determining music genres. Machine learning techniques are used in the majority of today's music genre classification methods.

Abstract: Internet has been a huge part of our day to day life. Since we are highly depended on Internet for all our daily activities, we are prone to cybercrimes. URL-based phishing attacks are one of the major threats facing by internet users. It is a way of fraudulent communication to steal the confidential data of user.Attackers mainly target people and reputed organizations, by tricking them to click on the URLs that seems to be secured and hence steal personal information of user or by injecting malware into machines.Researchers are constantly making several attempts to improve the accuracy and make model efficient. In this paper, we aim to study and review various machine learning algorithms along with the datasets, that are used to detect legitimacy of the URL.The paper also provides statistical information about performance of the model. Our objective is to create a survey aid for researchers to examine the latest trends of phishing attacks and contribute in building phishing detection models that yield greater accuracy. Index Terms: Phishing, Legitimate, URL features, machine learning, phishing detection

Abstract: In recent years, recommendation systems have been used to make people’s lives easier with product recommendations used by Amazon/Flipkart, movie recommendation used by Netflix/Amazon Prime. The idea of our project is to integrate the recommendation system with user emotion detection in a seamless way. The user’s emotion will be captured through live feed and his/her emotion will be predicted by a trained model, based on the predicted emotion, the user will be given a playlist containing songs based on the emotion. Key words: Emotion Detection, Deep Learning, Web Development, Recommendation System

Abstract: Due to the huge advancements in computer vision research in recent years, many real-world tasks can be automated without human intervention using deep learning models. Hand gesture and sign language detection and translation is also one such area where using a person’s webcam, the hand gestures can be automatically detected and translated accurately. In this paper, we have explained our research on developing a real-time hand gesture and sign language detection and translation web application. Details about our implementation and the tools used are given. Finally, a summary of the results, future scope and conclusion are explained.

Abstract: The data was collected through respondents in the form of different tests. Purposive sampling method was used, as the researcher selected Basketball Players with a specific purpose. 15 Basketball players selected under Performance based physical fitness program. This study involves a cross sectional, comparative pre and post-test of experimental group. This study was conducted in a quasi-square experimental design. The Performance based physical fitness program were planned for 4 days a week 30 minutes in a day for 06 weeks The result of the study shows that significant effects of Performance based physical fitness program were found on Passing, abilities enhance due to performance based physical fitness program of basketball players.

Keywords: Performance based, physical fitness, Basketball, Passing

Abstract: AIn 2019, the COVID-19 virus has spread to various parts of the world including Indonesia. This global pandemic becomes a lethal outbreak since there is no vaccine to treat or prevent transmission of the virus. Rapid Test is selected as an essential method to detect Covid-19 in Indonesia because the price is fairly cheap compared to the SWAB test. The increase in Covid-19 patients tends to lead to limited capacity for the Covid-19 test available at the hospital so that the latest technology to detect and overcome this pandemic is- sue is needed. Thus, the present research aims to examine the total of 100 X-Ray chest images of the Covid-19 patients and 100 X-ray normal chest images. The application of Contrast Limited Adaptive Histogram Equalization (CLAHE) and Convolutional Neural Networks (CNN) methods are implemented to analyze the dataset with two scenarios in obtaining the detection results. The results of this research reveal that the application of CLAHE is likely to affect Covid-19 detection accuracy using CNN. Also, the application of the CNN basic model shows significant results compared to the application of VGG16 transfer learning.

Keywords: COVID-19, Multimodal Imaging, Machine Learning, CNN, Neural Network.

Abstract: Empowering women socially, economically, and financially would help every woman in society reach heights. The availability of all the required resources helps women a lot in their life. The paper illustrates a website model with the help of which women can be able to access the portal which provides a discussion panel through which one can discuss any topic with each other by posting their views. A job portal to apply for a job of their interest. A web page containing basic information regarding healthcare and education. The website also contains a chatbot for easier access to the application. The project is implemented using the Django framework. For the front end, we have used HTML, CSS, and JavaScript using the Bootstrap framework. We used Python, SQLite database, and the Django Framework on the backend.

Keywords: Django, Bootstrap, Python, SQLite, HTML, CSS, JavaScript, SDLC, Google DialogFlow, Women Empowerment.

Abstract: Charity plays an essential role in our society, and often recognized as a type of social debt, leading to the circulation of a significant amount of money worldwide. We have witnessed increased growth of non-commercial organizations and charity funds through recent years, collecting donations for various philanthropic needs. Unfortunately, charity funds frequently gain much traction from the unscrupulous organization, leading to significant damage for industry's reputation, reducing trust level, affecting the power to boost donations. We strongly believe that utilizing blockchain technology will boost trust, increase efficiency, and encourage more donations. The Charity Webapp project, a blockchain-based charity foundation platform that facilitates the trustful network's formation and is accountable for collecting donation funds. The blockchain network would be comprised of publicly known, trustful, and prestigious organizations. All organizations' operations within the platform will become fully transparent and visual , leveraging properties of immutability, provenance, and non-repudiation. Therefore the platform will alleviate the results of dishonest actions, revealing fraudulent organizations' activities.

Keywords: Blockchain; ensuring trust; NGOs; encryption, Bitcoin, Beneficiary, Donars.

Abstract: In recent years, recommendation systems have been used to make people’s lives easier with product recommendations used by Amazon/Flipkart, movie recommendation used by Netflix/Amazon Prime. While recommendation systems alone help the user make decisions, integrating emotion analysis with this system would automate a variety of things. The analysis of human sentiment, which is also referred to as mining of opinions or Emotion AI in circumstances, is the study of different states of the human brain. The use of emotion detection technologies has garnered a lot of interested patrons over the years so the project is based on detecting user’s real time emotion and then using the detected emotion to generate a playlist of songs, recommending songs based on a person’s emotions.

Keywords: Emotion Detection, Deep Learning, Web Development, Recommendation System, Machine Learning, Image Processing

Abstract: Human cerebral mantle not requires a second to separate the area of thing inside the image similarly as recall it when it ensures; in spite of that, machine requires a time and large amount of data to perform a similar task. Deep neural network dependent on convolution neural network allows high accuracy and better results in object discovery .To develop deep neural networks, large amount of information such as images, video recordings are required and also it requires large amount of time. As computational cost of PC vision is incredibly high, highly learning methodology, where a model ready on one endeavor is reused on one more associated task, gives improved results. Through the survey and investigation of deep learning-based article recognition techniques recently, this work integrates the going with parts: spine interconnection, setback limits and planning procedures, customary thing distinguishing proof plans, multi-layered issues, the datasets and appraisal aspects, applications, and future headway headings. We belief this overview paper will be helpful for experts in the field of object detection.

Keywords: Artificial Intelligence, Deep Learning, Neural Network, Object Detection

Abstract: More institutions, governments, and private organizations are investing in and encouraging people to use these firms to explore their ideas. Companies are easily raising millions of dollars and achieving unicorn status in just a few years. There is a dearth of systematic empirical data on entrepreneurship enthusiasm. As a result, the purpose of this research was to look at the link between entrepreneurial enthusiasm, entrepreneurial orientation, and perceived performance. We give our system a single database with R&D, Administration, Marketing, and State as inputs, and we use the DNN algorithm to generate profit.

Keywords: Start-up, Deep neural network (DNN);

Abstract: Nowadays, holdup has become one in every of the foremost critical problem thanks to increasing population and automobiles in cities. Hold up causes delay and stress for drivers and also increases pollution and carbonic acid gas emissions. The traffic controller is one in all the critical factors affecting the traffic flow. This paper proposes a control system supported image processing including video processing within which traffic signals change accordingly the density of traffic and it'll also make use of Arduino UNO board for Traffic Lights, Emergency Vehicles and Barrier. A video camera and traffic lights are interfaced with Arduino UNO. The video is processed and Arduino enables the traffic lights to vary when required. Along with this, barrier at zebra crossing and emergency vehicle passing are the best concept for today’s smart city.

Keywords: Image Processing, Time, Signals, Emergency Vehicles, Barrier.

Abstract: The project aims to provide the facility to the small scale organization who has the leave management application. It does not help the project coordinators that much, they need to manage their own time sheet to track the leaves of the teammates in order to provide the deadline to the end users. This application allows employees to announce their leaves. Management is the most important aspect of any sector today, this project demonstrates the design and implementation of working module of office. It makes it easy to manage the groups and also provides reliability to the user. It enriched the management of the office. The dividing of group and allocating the roles, dividing work is done through office-work management software that is accessible on smartphones. We need to consider a useful method to effectively manage our projects by using an office-manager system. A properly managed group can bring significant benefits to our projects. As a result, you can ensure that your projects and work is efficiently managed and profitable in the long term.

Abstract: The introduction of IoT in India has brought the next level of industrial revolution also known as Industry 4.0. IoT plays a leading role in an evolving IoT business and technology context besides in the new Digital India program launched by the Government. According to a recent report, IoT investments in India were close to USD 5 Bn in 2019, and this is expected to go up to USD 15 Bn in 2021.

Abstract: The introduction of IoT in India has brought the next level of industrial revolution also known as Industry 4.0. IoT plays a leading role in an evolving IoT business and technology context besides in the new Digital India program launched by the Government. According to a recent report, IoT investments in India were close to USD 5 Bn in 2019, and this is expected to go up to USD 15 Bn in 2021.

Abstract: Nowadays robots are at a very perk and can be seen in every field, But the robots which are majorly used in Industries are of heavy body and large in size. As we know, when it comes to archaeological sites and rescuing people, we use heavy machinery to dig up holes and take off debris and skilled people who can effectively make the operation possible. So we have innovated a soft robot name “VINE ROBOT”, which is based on pressure and eversion process. Our soft robot is divided into three parts 1). Robot base, 2). Growing part, 3). Output device. ROBOT BASE is made up of a rigid body, which is the stable part of the robot and contains all the circuitry of the robot. GROWING PART(tail) is also the part of robot base, Hence the tail’s one side is connected to the robot base from where the pressure is provided to the robot by the air pressure pumps, and on the other side of the growing part is called the tip where the camera and mic are mounted. And the third part is OUTPUT DEVICES where we will get the output response of the mic and camera. Our project “VINE ROBOT '' is a pressure based device for exploring the site to remove such heavy machinery to dig up the holes and use less manpower. The main aim of the proposed project is to develop a light weighted, flexible robot with a compact working body which will operate at very low electrical power. Another aim is to design a robot irrespective of the surface, which can travel over fields, under water, over sticky and sharp terrain. Here in this model the pressure will be provided from the Air pumps which are available in the circuitry of Vine robot, using this pressure the growing part (which is of non-stretchable fabric) evert and the movement occurs in the robot

Keywords: Vine, Robot, Rescue, Archaeological Sites, Air Pressure pump, Eversion process.

Abstract: In mathematics, the logarithm is the inverse function to exponentiation. That means the logarithm of a given number x is the exponent to which another fixed number, the base b, must be raised, to produce that number x. In the simplest case, the logarithm counts the number of occurrences of the same factor in repeated multiplication.

Abstract: Data in our world is like a gold mine which has to be processed first to make something out of it; In our project data needs to be analysed so as produce good result. There are many companies where they pay their consumers for reviewing their product and these reviews plays a major role to analyse the factor which influences the review rating. Here, we have used EDA i.e., Exploratory Data Analysis where data interpretations can be done in row and column format. We have used python language for data analysis, it is object oriented, interpreted and interactive programming language and it is open source. Lending club receives a loan application, and it has to decide whether to approve the loan or reject it based on the application. Based on the decision there are two types of risks that can occur which will either result in loss of business or financial loss. Our research paper tried to find out the factors that can reduce the occurring of above factors. We have used EDA to understand how consumer attributes and loan attributes influence the tendency to default.

Keywords: Exploratory Data Analysis, Python, Jupyter, Numpy and Pandas

Abstract: In todays world ,the recommendation system are grownly important. Peoples now days finding out best services or products for themselves. Due to this, the recommendation system are important as they helping to make the right choice, without expending the cognitive resource. In this article, we aim to reduce human efforts by giving him the suggestion, to the users on the basis of their interest. we use Collaborative recommendation by implementing K-Nearest Neighbors algorithm. Collaborative filtering technique most widely used by recommendation system. Collaborative filtering predicts the user choice in item selection based on the known user rating of the items. It is effective for solving the information overload problem.’ Collaborative filtering can be divided into two main branches, Memory based collaborative filtering and model based collaborative filtering. Keyword: Recommendation System, Movie Recommendation System, KNN, Machine Learning.

Abstract: Areca nut, sometimes called betel nut, is a tropical crop. Areca nuts are produced and consumed in India, which is the world's second-largest producer and consumer. It suffers from a range of ailments during its life cycle. Farmers use their senses of sight to detect disease. Multiple image processing techniques for categorization of Areca nuts with various properties such as colour, texture are examined in this paper. Computer detection systems have been widely employed in the real world for retrieval tests because they can provide rapid, efficient, accurate, and clear testing. Until now, areca nut separation has been done by hand. Areca nut separation employing a complex colour sorting mechanism is made up of a variety of exterior properties of the nut, such as colour, texture, form, and size. Various approaches will be used to extract information from the captured image. The areca nut's colour can also be used to classify it. To efficiently plan the areca nut, all of these traits are essential. To extract composition characteristics, the co-occurrence matrix of wavelet coefficients at the second level of details, as well as contour let coefficients, is used. Separation is accomplished by mixing three texture elements namely strength, contrast, and homogeneity. This approach has been shown to work effectively in the contour let domain, allowing for a reduction in the vector dimension feature. When given training data, it categorises the data into healthy and unhealthy areca nuts based on colour and quality. Areca nut is separated using CNN and SVM classifiers.

Keywords: Convolution Neural Network (CNN), Support Vector Machine(SVM), Machine Learning (ML), Artificial Intelligence (AI), K-Nearest Neigbor (KNN), Artificial Neural Network(ANN), Gray Level Co-occurrence Matrix (GLCM).

Abstract: Computers are now an essential part of people's lives, as they are used to accomplish all of human job with greater accuracy and efficiency. Visual scene analysis is a high-level computer vision task that acquires knowledge from videos or digital images. Object detection is a branch of computer vision and image processing concerned with detecting items of various classes (animals, humans, and automobiles) in photos and movies. Car detection, face detection, picture retrieval, and video surveillance are some of the well-researched applications of object detection. This study focuses on the many image and video-based object recognition technologies that can be used to support varied contexts. This review focuses on examining the many image and video-based object identification technologies that can be used to serve varied contexts. The primary goal of this study is to investigate various picture and video-based objects. Detection methods for detecting and addressing object detection difficulties in photos and videos. This publication contains information on extensive information about numerous object detection algorithms in a variety of situations. Finally, there are analogies drawn for In diverse picture and video settings, different object detection approaches are used. Lives of animals are valuable. As global citizens, we must work to ensure the survival and development of animals in order to maintain the ecosystem's balance and stability. Wildlife monitoring collects data on wildlife species, numbers, habits, quality of life and habitat conditions to aid researchers in understanding the status and dynamics of wildlife resources and to serve as a foundation for effective wildlife resource protection, sustainable use and scientific management. Continuous hunting has resulted in the extinction of many animal species and the government has enacted legislation and is undertaking surveys to conserve certain species. Conducting surveys is a difficult undertaking, especially if don't have the necessary resources are not available. Conducting a survey is a difficult task, especially without the help of technology. The implementation of a Species Classification wireless camera is being done to address this. The smart camera is used in conjunction with phython-based programming that incorporates a Tensor Flow model that has been pre-trained. Some species are difficult to locate, and even when they are, determining their classification can be difficult. Varied species present in various locations appear in various sizes, forms, colours, and angles from a human perspective. In order to better conserve and preserve species, a better choice of technique for identifying and classifying them must be made.

Keywords: LIDAR, FSP, SVM, CNN, Forest stand,UWB,SIFT,SURF.

Abstract: Due to its complexity and durability, precipitation prediction has recently gained the highest research relevance. Among other applications, such as flood forecasting and pollutant concentration monitoring. Existing model uses a complex statistical model that is often too expensive for both calculations and budgets. It does not apply to downstream applications. Therefore, an approach using machine learning algorithms. It is being studied in combination with time series data as an alternative to overcome these shortcomings. To this end, this study presents a comparative analysis based on a simplified precipitation estimation model. Efficient traditional machine learning algorithms and deep learning architectures for this Downstream application. This paper presents a time-series method called Neuralprophet for predictions of Maharashtra’s ten most popular cities. This method provides an estimate of rainfall using different atmospheric parameters like average temperature and cloud cover to predict the rainfall. The main advantage of this model is that this model estimates the rainfall based on the previous correlation between the different atmospheric parameters. Thus, an estimated value of what the rainfall could be at a given period and place can be found easily. Introducing Neural Prophet, the successor to Facebook Prophet, which sets the industry standard for a explainable, scalable, and easy-to-use prediction framework. NeuralProphet is a hybrid prediction framework based on PyTorch and trained using standard deep learning techniques, so developers can easily extend the framework. Local context is introduced in autoregressive and covariate modules that can be configured as classical linear regression or neural networks. It includes traditional statistical and neural network models for time series modeling used for forecasting and anomaly detection. This model produces high-quality predictions of time series data showing multiple seasonality’s with linear or non-linear growth. Use this model to predict future temperatures in Maharashtra's most popular cities using historical temperature data from the same location.

Abstract: The corona virus disease 2019 is an emerging worldwide threat to public health. Early detection and diagnosis are critical factors to control the COVID-19 Spreading. For the diagnosis of COVID-19 Computed tomography has an important role in the early diagnosis of COVID-19 as it provides both rapid and accurate results. The lung infection due to COVID-19 has affected a larger human community globally. The COVID-19 disease has adverse effects on the respiratory system, and the infection severity can be detected using a imaging modality. As the COVID-19 continues to spread rapidly across the world, CT has become essentially important for fast diagnosis. Hence it is very important to develop an accurate computer-aided method to assist medical experts to identify COVID-19 infected patients by CT images. Early identification of severely ill patients can enable easy intervention, prevent disease progression and help reduce mortality. The study aims to develop the Artificial intelligence-assisted tool using CT imaging to predict disease severity and further estimate the risk of developing severe disease in patients suffering from COVID-19. CT images can effectively complement the reverse transcription polymerase chain reaction testing. Early and accurate diagnosis of corona virus disease is essential for patient isolation and contract tracing so that the spread of infection can be limited.

Abstract: Sociologie de 1’Innovation of the Ecole Nationale Superieure des Mines of Paris and the CNRS (Centre National de la Recherche Scientifique) of France and previously it was called “LEXIMAPPE”. For decades, scientists struggled to map the interrelations in a subject to realize an effective and efficient plan structure of research. Hence, to resolve this problem some quantitative methods were developed like co-citation analysis, co-word analysis, and co-nomination analysis. Co-word analysis is a bibliometric technique that measures the co-occurrences of keywords to examine the content in the textual data. This technique has proved to be a powerful tool among the scientists to quantify and visualize the relationships between the various subject areas within the corpus. This paper aims to outline a timeline review on development of co-word analysis and discuss the issues of the researches. It summarizes the current state of knowledge of the topic to create an understanding of the topic for the researchers by discussing the findings presented in recent research papers.

Keywords: Co-word analysis, Social Network Analysis, Co-occurrence Matrix, Strategic Diagram, Clustering. Multi- dimensional Scaling.

Abstract: Security has reliably been a huge concern in our regular daily existence. Locks are a piece of it whether it is the crucial door lock, interconnecting door lock, bathroom door lock, furniture lock, stuff lock, screen, and barbecue door lock, etc. Here, we have proposed making a Knock-Knock system for door lock using Arduino which can distinguish the example of your knocks at the door and will possibly open the lock on the off chance that the knocking example coordinates with the right example. This paper depends on uniquely crafted Arduino whose sole plan is cost cutting of the completed outcome and the calculation for knock design identification is created utilizing the Arduino programming condition. We have integrated a reset button close by two situations with that are important for the testing of the undertaking and joining up or enrolling new knock designs. Right when the client knocks, custom Arduino board arranges the knock plan with the knocking calculation and opens the door assuming the knock design coordinates with the model enrolled. Key words: security, knock- knock, Arduino UNO, knock detection, sensor.

Abstract: From past couple of years, Counterfeit products are having a massive impact in manufacturing industries. This is affecting companies name, sales, and profit. Innovation in blockchain have acquired interest in the course recently. The most important issue about this is currency exchange, but its application is not restricted to only Digital currency. This technology has the potential to influence different business sectors. Blockchain has brought high transparency and ease in the way transaction are dealt. Blockchain technology identifies real product from fake ones. Blockchain is a distributed, decentralized, and digital ledger that stores transaction related information in the form of blocks in the databases which is connected in chains. Blockchain technology is secure and the blocks cannot be changed or easily hacked. By using this technology, customers or users need not rely on third party services for the safety of the product. In proposed system, we will be using Quick Response (QR) code to provide robust technique to try and stop the practice of counterfeiting the products. Fake products can be detected using a Quick Response scanner, where a QR code attached to the product is linked to the Blockchain network. Now, this concept might be used to store the data like product details and generated unique code for that product as blocks to the database of Blockchain. When the user uploads the unique code and the code is compared to the Blockchain database. If the code matches the code that was generated during the manufacturer, it will notify the customer saying the QR code is matched otherwise it will notify the customer that QR code is not matched and the product is fake.

Keywords: — Blockchain, Smart Contracts, Quick Response Code, SHA 256 algorithm.

Abstract: Our project deals with online voting system that facilitates user(voter), candidate and administrator (who will be in charge and will verify all the user and information) to participate in online voting. our online voting system is highly secured, and it has a simple and interactive user interface. The proposed online portal is secured and have unique security feature such as unique id generation that adds another layer of security (except login id and password) and gives admin the ability to verify the user information and to decide whether he is eligible to vote or not. It also creates and manages voting and an election detail as all the users must login by username and password and click on candidates to register vote. Our system is also equipped with a chat bot that works as a support or guide to the voters, this helps the users in the voting process.

Keywords: Blockchain Based Online Voting System, Face Recognition Based Online Voting System, Fingerprint Based Online Voting System, AADHAAR ID Based Online Voting System

Abstract: Educational Data Mining is an emerging discipline, concerned with developing methods for exploring the unique types of data that come from educational settings, and using those methods to better understand students, and the settings which they learn in. EDM refers to the techniques, tools, and research designs utilized to obtain information from educational records, typically online logs, and examination results, and then analyses this information to formulate conclusions. The problem with educational data is it is a data rich and information poor collection. Data Mining is a process of finding potentially useful patterns from huge data sets. It is a multi-disciplinary skill that uses machine learning, statistics, and AI. Data mining process have the ability to discover the hidden knowledge present within the collection of educational data and then identify students’ performance with great accuracy. Also, it is playing a vital role in the process of diagnosis and prediction of problems in students’ education. This proposed paper presented a detailed systematic study of the role of various data mining techniques and algorithms in the field of educational data mining.

Keywords: Educational Data Mining, Data Mining algorithms, Student Performance, Naïve Bayes, Neural Network

Abstract: In this project i have created a website for the purpose of request and stock management For chemicals of the corresponding Departmnet. This Website is used to calculate The Stock Availability of materials used in the labs of the Respective Department. we can add the user data who maintain the stocks. it is easy for the maintenance than the manual records. Users can directly request the unavailable materials to the corresponding higher authorities through this website. users can also able to view the request status. the request will be proceesed based on the hierachy level. there are seven heirachy levels. the request letter can also get printed for the official use. user can able to easily view the stocks. the data can be easily modified in the respective menus. a new item can also be added in the list. New features are added to this website to make the user more convenient to use. this website is just a runnable protoype for real time project were the website can be actually implemented and used in the real time environment. inventory management system plays a main role in the supply chain management system.

Abstract: We propose and examine the usability and security of Cued Click Point (CCP), a cued-recall graphical password technique. Users click on one point per image for a sequence of images. The next images are based on the previous click point. We present the result of an initial user study which revealed positive results. Therefore graphical password has been proposed by many researchers as an alternative to text based password Graphical passwords can be applied to workstation, web log-in applications, ATM machines, mobile devices etc. This paper presents implementation of Cued click point (CCP) graphical password which uses circular tolerance. Then it is found that CCP with circular tolerance is better as compared to CCP with rectangular tolerance. Key words: CCP, Secret click, Graphical password.

Abstract: In this project i have created a website to give feedback for the student and the faculty. college feedback system is a web application which is used to know the feedback of the students and faculty which contains the data about their behaviours and teaching methodology and many other factors. it i s a secure system as the user like student and faculty should be authenticating before login to the website. the website contains two diffrent types of feedback which can be given by the student and faculty about their respective factors. feedback is used to get suggestion for the improvement and can also report on any factor. the security system is wellmaintained as the result this website can be managed only by the admin of the college. it is a secure system as the user can only be entered if they have proper login authentication. the system consists generation and analysis of the feedback given by the students and faculty. the security of this website is high so feedback can be only viewed by the admin of the college. it is a secure system as the user can only eneterd into this website with proper login authentication. the website contains two types of feedback form wich can be filled by the students and faculty. The security of this websit is so high so only admin can only viwed by the admin this website.

Abstract: In agriculture, detecting plant diseases is a difficult task. It is time consuming and require highly knowledgeable individuals to identify diseases. Plants are often at risk of disease that will result in social and economic losses. Many diseases are starting to emerge on plant leaves. If the disease is not recognised in early stage, it might result in serious damages to the plant. The current way of identifying plant disease is an inspection performed by a specialist who must monitor the plants on a constant basis. But costs increase with the size of the farm. In the existing system, Support vector machine algorithm technique is used to predict an infected plant disease with 80 percent of accuracy. In such types of conditions, to achieve a high degree of accuracy and to reduce the difficulty of time, the proposed system contains a comparative study on different machine learning algorithms to predict the disease and build a system that will easy to use by anyone. This system uses computer vision and deep learning strategies. Using the Image Processing technique system will get a picture of the leaf of an infected plant and turn it into a grey scale image. The system will give suggestions on the features and characteristics of various types soils for plant growth without any infection using deep learning techniques. The system uses a different deep learning algorithm to improve its accuracy in diagnosis of plant diseases and offer a suggestion.

Keywords: Computer vision, Gray scale image, Image Processing, Deep learning, Neural networks, Support Vector Machine.

Abstract: Public places are often characterized with incessant traffic congestion, especially during special occasions and events, as large number of automobiles attempt to use the same parking lot concurrently. This usually results in confusion and dispute, auto crashes, waste of time and resources, and release of more carbon into the ecosystem. Radio Frequency Identification (RFID) technology offers effective solution for distant object identification without requiring a line of sight. In this paper, the authors developed an intelligent, cost-effective, and eco-friendly park management system for scalable traffic control using RFID. In this communication we present a new control system for intelligent speed control, which is based upon Radio Frequency Identification (RFID) technology for identification of traffic signals on the road, and high accuracy vehicle speed measurement with a Hall effect-based sensor. Moreover, these car will be more users friendly help the users in many ways, such as these cars will helps user to follow RTO rules such as managing the traffic in better way which further results in improvement of performance of the cars, speed control, direction control, automatic car parking light turn on/off etc. This will lead in improvement such as handling of emergency conditions like accident, theft etc

Keywords: Intelligent cars, RFID, Radio frequency Transponders

Abstract: This paper discusses the work on online proctoring system capable of detecting malicious activities or malpractice during online examination. Proctoring involves detecting examinee action using the help of a webcam and in-built microphone. Since the academic practices are moving towards digital media, this system removes the need of any human proctor. Candidate eye tracking, lip movement analysis, presence of second person, detecting any electronic gadgets used for malpractice are taken care of by the system along with the necessary warning, along with visual analysis, audio analysis done and it’s compared against the answers associated with the exam.

Keywords: Proctoring, Malpractice, You Only Look Once, Person Detection, Head Pose Estimation.

Abstract: Software is inseparable part of society from households to spacecraft. It is essential part of any electronic device. That’s because software development has exciting career. However it has many challenges. Software is complex and also requires quality in it. Customer’s awareness about quality in software product increases workload and responsibility of the software development team. That is because testing has gained so much popularity. Testing is important segment of software development team.

Keywords: Software Testing, STLC, Types of Testing, Manual Testing.

Abstract: The available weather forecasting information is not accurate to every region. Typically, areas are separated into districts or taluks, and the weather conditions of one measured location are used to define the weather for the entire region. It will be different in real life. The proposed low-cost weather monitoring system can be placed in any location, allowing weather data to be sensed and updated to the cloud. Based on the specified location, the weather information will be displayed in plot format in a website developed with the Django framework, and the weather forecasting is done using Open weather API which is displayed through the web application.

Keywords: Weather Forecasting, Django, Framework, Web Application

Abstract: We all know about various types of hazardous diseases but out of them all the Cancer is the most fatal and common among people. A large number of population get suffered and lose their lives due to it. If cancer is diagnosed in early stages it could be cured, but if it diagnosed in later stages, the chances of survival became negligible.The prominent cause of cancer-related mortality throughout the world is "Lung Cancer". Hence beforehand detection, prediction and diagnosis of lung cancer is a necessity as it can increase the chances of survival .Various types of machine learning algorithms (ML) like Naive Bayes, Support Vector Machine (SVM), Logistic regression, Artificial Neural Network (ANN), Convulational Neural Network (CNN) have been applied in the healthcare sector for analysis and prognosis of lung cancer. This paper will highlight the methods by which we can diagnosis or predict the presence of the tumor in the lungs using image data.

Keywords: Lung Cancer, Entropy, Classification, Thresholding, Tumor, Histogram, Segmentation, Dilation.

Abstract: Agriculture is the basic source of food supply in all the countries of the world whether under-developed, developing or developed. Besides providing food, this sector has contributions to almost every other sector of a country. According to the Bangladesh Bureau of Statistics (BBS), 2017, about 17% of the country’s Gross Domestic Product (GDP) is a contribution of the agricultural sector, and it employs more than 45% of the total labor force. In light of the decreasing crop production and shortage of food across the world, one of the crucial criteria of agriculture now-a-days is selecting the right crop for the right piece of land at the right time. Therefore, in our research we have proposed a method which would help suggest the most suitable crop(s) for a specific land based on the analysis of the data of previous years on certain affecting parameters using machine learning. In our work, we have implemented Random Forest Classifier, Gaussian Naïve Bayes, Logistic Regression, Support Vector Machine, k-Nearest Neighbor, and Artificial Neural Network for crop selection. We have trained these algorithms with the training data and later these were tested with test dataset. We then compared the performances of all the tested methods to arrive at the best outcome. My target is focused largely on agriculture. In agriculture, farmers play the most important role. When the price falls after the harvest, farmers face immense losses. A country's GDP is affected by the price fluctuations of agricultural products. Crop price estimation and evaluation are done to take an intelligent decision before farming a specific type of crop. Predicting the price of a crop will help in taking better decisions which results in minimizing the loss and managing the risk of price fluctuations. Therefore, the web app also includes a crop price predictor to predict crop prices for the next 12 months. In this paper, we predicted the price of different crops by analyzing the previous rainfall and WPI data. We used the decision tree regressor (Supervised machine learning algorithm) to analyze the previous data and predict the price for the latest data and estimate the price for the twelve months to come.

Keywords: Agriculture, Crop yield, Logistic Regression, k-Nearest Neighbors, ANN, price prediction, decision tree, crop price, regression, forecasting, machine learning.

Abstract: In traditional ways of quality control of hardware steel products (regular rectangular shape), the industrial experts use Vernier Caliper for error checking. Usually, this is done manually which takes a lot of time and cost, and this might have some error while checking. To avoid this problem, there should be an automated system which will not require any man power and perform this task fast as well as accurately. The proposed system will allow users to make accurate non-contact measurement detect a fault in product’s shape and dimensions. The proposed system will measure dimension of hardware steel products. An image of the product captured from the specified height will be used to measure the dimension. The proposed system will use image segmentation, area detection and then size measurement. The dimensions obtain from the process is compared with the expected dimensions. Based on this, if the obtained dimensions and expected dimensions match, the product will be classified as correct else fault. The proposed system aims for fault detection process which will detect faults quickly and precisely.

Keywords: Fault Detection, Quality Check, Dimension Calculation

Abstract: In recent years there has been growing interest in use of machine learning classifiers for analyzing MRI data. There are number of soft tissues present in human body. These soft tissue tumors are like sarcoma that connects, supports and encircles the body. Minor injury to it can cause tumor called soft tissue tumor. MRI of such soft tissue looks like as other diseases like fibroadenoma mammae, lymphadenopathy, struma nodosa. These errors could have an adverse effects on the patient’s medical processes. Existing system are not fully able to differentiate the tumors and may lead to misdiagnosis. To get the accurate diagnosis of soft tissues an automatic technique to segment brain tissues from volumetric MRI brain tumor pictures can be implemented. To identify exact presence of soft tissue tumor, the proposed system classifies if there are soft tissue tumor or not using machine learning algorithm. The system will help in effective diagnosis of Soft tissue tumor using machine learning algorithm.

Keywords: Convolutional Neural Network,Machine Learning,Preprocessing, Soft Tissue Tumor,Unet

Abstract: Heart disease is the leading cause of death worldwide. According to a recent study by the Indian Council of Medical Research (ICMR), roughly 25% of the deaths among people aged 252 to 69 are caused by various heart- related issues. The most common diseases are cardiovascular disorders. Due to a shortage of professionals and a significant number of incorrectly diagnosed cases, a quick and efficient detection method is required. So we should have always leaped on vigilance and care approaches and methods to avoid folks working extra due to the guts attack. Machine learning techniques are frequently used to make disease predictions. Blockchain technology has the ability to prevent data leaks and fraud. It has the potential to improve patient-hospital coordination. The suggested method improves data security while reducing the cost, time and resources needed to maintain a patient’s data and outcomes.

Keywords: Blockchain, Healthcare, Machine Learning, Arrhythmia, Convolution Neural Network, Inter-Planetary File System.

Abstract: Visual secret sharing (VSS) systems hide hidden images in shares that are also published on clarity or decrypted and saved in digital form. The shares can seem as noise-like pixels or as meaningful images, but this will raise suspicion and increase the risk of interception during transmission. As a result, VSS schemes face a transmission danger problem for both the secret and the individuals involved in the VSS system. To solve this issue, we presented a new palette-grounded steganography technique that uses a texture with LSB, as well as a natural-image-grounded VSS scheme (NVSS scheme) that shares secret images via colored carrier media to hide the secret and the actors during the transmission phase. To conceal secret messages, we convert the texture conflation process into steganography. Rather than using a being cover image to conceal dispatches, our algorithm conceals the source texture image and embeds hidden dispatches during the printing process. Prints or hand-painted filmland in digital or published form can be used for the natural shares. We also propose possible methods for concealing the secret in order to reduce the transmission threat problem for the share. The experimental results show that the proposed approach is an excellent solution to the transmission threat problem for VSS schemes.

Keywords: visual secret sharing (VSS), steganography, natural-image-based VSS scheme (NVSS scheme), OR Code, Palette Based Steganography.

Keywords: Hybrid Approach, American Sign Language, Gesture Recognition. Feature Extraction.

Abstract: Agriculture is the foremost basic essential and important way to produce food & it plays a major role in the economic growth runs each nation by contributing to GDP. There are many crucial issues in agriculture associated with manual method such as wastage of water for the purpose of irrigation in the field, need for non-renewable source like time, money, human resource (Labour) etc. By using IOT technology and different field sensors, it is possible to do the automation techniques in agriculture. The main purpose of automating the irrigation system is to provide adequate water for the crops, when it is required. The smart irrigation system uses an Arduino based micro controller which takes the data related with the contents of moisture percentages in the soil by using sensors. In addition, servo motor is used to control the flow of water from the water resources. A decision controller algorithm is used to turn on the motor or to turn off the motor, which supplies the water to the agriculture field. The soil content information such as moisture, humidity, temperature is sent to the controller unit and then all these data were sent to the server database for the future analysis using wireless mode of transmission.

Abstract: Forest is one of the very important and indispensable resources. The aim of this project is to style and implement an approach that would predict and observe the forest fires and send the precise location to involved officers which might facilitate firefighting personals to extinguish the fireplace within the location once it's in its initial stages using GSM. In this advancing world, it's crucial to protect our surroundings. This project implements a system for watching and menacing for the protection of trees against forest fires. Today IOT devices enable the observation of various environmental variables, like temperature, humidity, flame, smoke etc. Arduino based platform mostly IOT enabled fire detection and observation system that is the resolution to the current problem. This project we've designed fire detector system using Arduino interfacing using few sensors that is a smoke detector, a flame detector and a buzzer.

Keywords: Arduino, GSM module, IOT, Sensors, Solar energy.

Abstract: Rendering covering objects in such some way that user will customize them as per there would like. Rendering 3D objects is even tougher on 2G/3G network information measure because the size of objects is sort of massive. So, to attain the target for same, implementation of second pictures rendering in 3D canvas of ThreeJs. With the event of science and technology, among the strategy of drawing sketch has been regenerate from hand-painted to lighting tricks, the speed of constructing sketches and 3D model has been greatly improved. However, it's still the because of image sketch of digital graphic presentation, although the assembly technique has been greatly reduced, but in between the householders and styler's among the look technique of communication and mutual agreement stage continues to be a retardant, so the householders and styler's among the look of the communication technique, some way to use WebGL sharing and agreement once the strategy of but the WebGL can effectively shorten the design method, will become an important analysis topic. This study will use WebGL based three.js as a result of the core technology of the system construction, interior vogue is easy and simple interactive surroundings, through a web based virtual house simulation system, the designers and homeowners|homeowners} exploitation constant WebGL with constant interface then trying to find the appliance of this technique in cooperation with each other designers and owners of feedback. the advantages and disadvantages of the system and thus the present modelling computer code area unit mentioned. More into user centric aspect added the AI enabled chatbot system, which provide more ease to E-commerce platform and give quick results to user.

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

Abstract: Web traffic forecasting is a key topic since it has the potential to cause major problems with website functionality. Making predictions about future time series values is one of the most challenging problems, hence it has become a popular issue for research. As a result of the increased web traffic, the site may crash or load very slowly. Such disruptions may cause numerous disruptions for users, resulting in a lower user rating of the site and user migration to another site, which has an impact on the business. To predict online traffic, we created a forecasting model. The ARIMA model is used to forecast Web traffic time series. We used some of the information, such as the name of the page, the date it was seen, and the number of visits, to make more accurate predictions. Keywords Web traffic prediction, ARIMA model, Time series forecasting, Data Collection and Feature Understanding.

Abstract: The human brain is the primary controller of the humanoid system. A brain tumour is caused by abnormal cell growth and division in the brain, and so brain tumours can lead to brain cancer. Computer vision plays an important role in human health by reducing the accuracy of human judgement. CT scans, X-rays, and MRI scans are all common imaging modalities. Magnetic resonance imaging is the most reliable and secure method (MRI). MRI is used to detect every minute thing. The application of various methodologies is examined in our research. During this experiment, we used the Gaussian filter(GF) to remove noise from brain MRI for the identification of brain cancer. Index Terms: BraTS,Classification, medical imaging, Segmen- tation, SVM, tumor detection,watershed.

Abstract: Crime is one of the most predominant and alarming aspects of our society and its prevention is a vital task. Crime analysis is a systematic way of detecting and investigating patterns and trends in crime. Thus, it seems necessary to study the reasons, factors and relations between the occurrence of different crimes and finding the most appropriate ways to control and avoid more crimes. Our System focuses on finding spatial and temporal criminal hotspots. We will make cluster analysis by using the k-means cluster algorithm on the criminal dataset of India. The cluster input is used to create a custom India map with the cluster zones of states. To cluster the crime activities based on some predefined cases and the results of these clustering are compared to find the best suitable clustering algorithm for crime detection. Our System aims to raise people’s awareness regarding the dangerous locations and to help agencies to predict future crimes in a specific location within a particular time [1].

Keywords: Clustering, Crime Analysis, Data mining, Hot Spot detection

Abstract: The goal of data analytics is to delineate hidden patterns and use them to support informed decisions in a variety of situations. Credit fraud is escalating significantly with the advancement of modernized technology and became an easy target for frauds. Credit fraud has highly imbalanced publicly available datasets. In this paper, we apply supervised machine learning algorithms to detect credit card fraudulent transactions using a real-world dataset. Furthermore, we employ these algorithms to implement a super classifier using ensemble learning methods. The software identifies faces which are already recognized and automatically adds the credit points to the customer’s account. If the customer is not found, then the system requests the customer picture and contact details for customer to be added to the database. The points can be redeemed as the company pleases. Additionally, we compare and discuss the performance of various supervised machine learning algorithms that exist in literature against the super classifier that we implemented in this paper. Finally, we design and assess a prototype of a fraud detection system able to meet real-world working conditions that is able to integrate investigators feedback to generate accurate alerts.

Keywords: Credit Card, Fraud detection, supervised machine learning, face recognisation Classification, Imbalanced dataset, Sampling.

Abstract: An Image Encryption and Decryption Using AES (Advance Encryption Standard) Algorithm is proposed in the project. Due to increasing use of image in various field, it is very important to protect the confidential image data from unauthorized access. The design uses the iterative approach with block size of 128 bit and key size of 128, 192 or 256 bit. The numbers of round for key size of 256 bits is 14 , for 128 bits is 10 and for 192 bits is 12. As secret key increases the security as well as complexity of the cryptography algorithms. In this project , an algorithm in which the image is an input to AES Encryption to get the encrypted image and then input it to AES Decryption to get the original image is proposed and explained which will further be implemented by me . Also time will be calculated for the encryption and decryption process and analysis of the comparison of time taken by different types of images of different sizes/resolutions will be done.

Abstract: Machine Learning is a category of algorithms that allows software applications to become more accurate in predicting outcomes without being explicitly programmed. The basic premise of machine learning is to build models and employ algorithms that can receive input data and use statistical analysis to predict an output while updating outputs as new data becomes available. These models can be applied in different areas and trained to match the expectations of management so that accurate steps can be taken to achieve the organization’s target.The object of this research paper is to create a project that can be used predict calories burnt using Machine Learning with Python. Xgboost Regression model is used in this project.

Abstract: Machine Learning is a category of algorithms that allows software applications to become more accurate in predicting outcomes without being explicitly programmed. The basic premise of machine learning is to build models and employ algorithms that can receive input data and use statistical analysis to predict an output while updating outputs as new data becomes available. These models can be applied in different areas and trained to match the expectations of management so that accurate steps can be taken to achieve the organization’s target. In this paper, the case of Big Mart, a one-stop-shopping center, has been discussed to predict the sales of different types of items and for understanding the effects of different factors on the items’ sales. Taking various aspects of a dataset collected for Big Mart, and the methodology followed for building a predictive model, results with high levels of accuracy are generated, and these observations can be employed to make decisions to improve sales.

Abstract: Cryptocurrencies have been a global trend since inception and have emerged as important pecuniary software systems. Cryptocurrencies lack a central authority to mediate transactions because they were designed as peer-to-peer systems, and they rely on users' activities to validate transactions and require strong, secure mining algorithms to maintain its block chain. This research project presents an overview of cryptocurrencies and process automation for instant procurement using influencer’s tweets. Tweets are culled from twitter and used to streamline the procurement process and predict its market volatility based on available data.

Keywords: Cryptocurrencies, instant procurement, process automation for instant procurement, algorithms

Abstract: In gift state of affairs, folks area unit buried up during a significant work culture, as everyone seems to be engaged with busy schedules, and feverish tasks that build them deviate from family life. If any problems encounter unexpectedly, it distracts them and makes them select over the work they need to accomplish primarily. it's vital to manage each skilled and family life. In such circumstances, each one folks would have fantasized a few quite house that doesn’t have any leaks in pipes, if it doesn’t have any mess in fixing a article of furniture and a form of house that ne'er face any maintenance problems and each one among U.S. have thought that a life would be far better if no purpose of issue arises in obtaining a service at your door step and if there's no mess in talks a labour for home service. In such situation’s E-Commerce plays a significant role in today’s life because it has such a large amount of benefits in our life as a result of it makes convenient in existence of the folks. So, giving an idea to it facet of life is to style and develop a system that has several services at your step in only one click. A System that has style of services like plumbers, repair persons, cleaners, electricians, painters, taxi service laundry and plenty of a lot of. to form it snug for all the users our system additionally offers mobile surroundings that offers ease in accessing our services that's Booking Home and Individual Services Booking Home and Individual Services is on-line platform that provide Customers to rent trained staff on-line for his or her home services. Its aim is to produce fast and very best quality services to their customers. currently a days for any services like Plumbing, Electrical, Electronic, Mechanical management, Home Paint and Machine Repairing, if any client desires to use this kind of services than they will undergo a private meeting or mobile decision. it's troublesome for client to seek out any service in emergency at any time and place. therefore with this project we tend to area unit attending to develop web site and golem app which can facilitate customers to seek out out answer for any issues associated with Plumbing, Electrical, Electronic, and Mechanical, pesterer management, Home Paint and Machine Repairing service. Our web site and golem application can offer a platform for all quite house hold services at any time and place. Our project also will offer the facilities like security, on-line payment, map navigation and additionally promotion,Pest

Keywords: Android; Booking; Workers; purchasers.

Abstract: Diabetic retinopathy is a consequence of Diabetes Mellitus that affects the Retina (back of the eye) due to excessive blood sugar levels. If left undiagnosed and untreated, it might result in blindness. The retina is the light-sensitive layer of cells that turns light into electrical signals at the back of the eye. The signals are transmitted to the brain, which transforms them into the images you see. The retina requires a constant supply of blood, which is delivered via a network of small blood capillaries. Advanced cases of diabetic retinopathy may necessitate a surgical treatment to remove and replace the vitreous, a gel-like fluid in the back of the eye. A retinal detachment may also necessitate surgery. This is a separation of the rear of the eye's light-receiving lining. Diabetic retinopathy (DR) diagnosis by colour fundus images necessitates skilled doctors recognizing the presence and significance of several minor characteristics, which, combined with a complicated grading system, makes this a challenging and time-consuming task. In this study, we present a CNN approach for diagnosing DR and reliably grading its severity from digital fundus images. [1-4] We create a network with CNN architecture and data augmentations that can recognize the complex elements involved in the classification task, such as micro-aneurysms, exudates, and haemorrhages on the retina, and deliver diagnosis automatically and without the need for human input. We train our network on the acquired images, which are applied with Gaussian filters. On 3500 validation photos, our suggested CNN achieves a sensitivity of more than 95% and an accuracy of 98% on the image set. The proposed method is extremely accurate at objectively diagnosing and grading diabetic retinopathy, removing the requirement for a retina specialist and increasing access to retinal care. This technique allows for early detection and objective tracking of disease progression, which may aid in the optimization of medical therapy to reduce visual loss. [5]

Keywords: Diabetes Mellitus, Deep Learning, Convolutional Neural Networks (CNN), Diabetic Retinopathy, Image Classification, retina, Gaussian filters, Mild DR, Moderate DR, Severe DR, Proliferate DR and NO DR.

Abstract: In software testing, the main challenge is to develop software that is defect-free, high quality. Testing ensures whether the software developed is according to the customer’s expectations. The verification and validation process plays very important roles in software testing. Verification testing is performed by the quality assurance team to check whether it is according to the customer’s expectations. Validation testing is executed by the testing team.

Keywords: Unit, Integration, quality, testing.

Abstract: Traffic sign detection and recognition are vital in the improvement of clever vehicles. Detection and recognition of traffic signs have for quite some time been at the focal point of interest for significantly affecting the wellbeing of the driver. Programmed street signs recognition is turning into a piece of Driver Assisting Systems whose job is to increment wellbeing and driving solace. Considering different datasets of various RTO/Traffic Signs, the location module will distinguish the particular sign and show Alerts for drivers. Traffic sign recognition is generally founded on the shape and variety credits of traffic signs, and traffic sign recognition is frequently utilized with classifiers, for example, convolutional neural network (CNNs). The response time of the relative multitude of above tasks will be determined and contrasted with demonstrate that the CNN executes quicker (25ms/outline).

Keywords: Algorithms, Conventional neural networks, Database, Deep learning, Recognition System.

Abstract: Dyslexia is a neurodevelopmental reading disability. Dyslexia is thought to be a standard learning disability characterized by a persistent deficit in rapid word recognition and by spelling. Detection of dyslexia is critical, expensive. Early diagnosis of dyslexia is incredibly important. Eye tracking may be a useful approach to detect dyslexic and non-dyslexic people. Eye tracking doesn't rely on the person’s verbal response so it provides a natural means to objectively assess the reading process. Although dyslexia may be a learning disorder, eye movements in reading can predict individual reading ability. Eye tracking movements are going to be fed to the model for classification and will predict whether the person is dyslexic or not.

Keywords: Classification, Dyslexia, Eye Tracking

Abstract: With the growing number of vehicles, millions of people are killed in road accidents every year around the globe. Also, traffic congestion and air pollution has led to poor quality of life. This has brought in the focus to improve road safety and traffic efficiency. Vehicular Adhoc Network also referred to as VANET is a vital application of Intelligent Transportation System (ITS) with enormous societal impact. Cooperative communication among the vehicles can make the driving experience safer and comfortable. But the major challenge for the effective deployment of Vehicular networks is the bandwidth allocated for VANET by Federal Communication Commission (FCC) gets insufficient during high traffic density scenarios which affects the transmission of safety messages. Cognitive Radio technology integrated with Vehicular Networks extends the spectral efficiency with Opportunistic Spectrum Access (OSA) and can improve the communications in emergency situations. Leasing additional spectrum outside of the Dedicated Short-Range Communications (DSRC) band can improve the performance of vehicular networks. This survey paper sheds light on the latest advancements that took place in Cognitive Vehicular Networks as well as current research challenges.

Keywords: Cognitive Radio, Vehicular Adhoc Network (VANET), Opportunistic Spectrum Access (OSA), Dedicated Short-Range Communications (DSRC).

Abstract: With the arrival of new mobile technologies, the mobile operation assiduity is advancing fleetly. conforming of several operating systems like Symbian OS, iOS, blackberry, etc., Android zilch’s is honoured as the most extensively used, popular and stoner-friendly mobile platform. Tourism has come one of the fastest growing diligences worldwide; and in India it represents a substantial chance of GDP, we prevision the great eventuality of this sector and the wealth that it could bring to Indian people, thus we're developing system for stint attendants in India. As we're apprehensive of the big environmental challenge that the world is facing, we know that Tourism can either play a positive or a negative part in similar sense. thus, we promote a Sustainable Tourism, whose proposition and practice are tutored to the sightseer as well. likewise, we ensure that the sightseer internalize generalities similar as work ethics, fair working conditions and professionalism which are always guaranteed to them from our side. Beside this, we also developed a about India runner on the website in order to educate history and culture to sightseer, with the end of eventually stimulate the curiosity of the children about the literal knowledge of their own megacity and culture, with a substantial attention to the environmental education, in order to educate youthful scholars to admire their own girding. This system designs the visit with the end thing that the customer can save fresh time in probing most extreme places rather than with nothing to do in arriving at his expostulations. It has following modules 1. Top Tourist magnet in India 2. Stylish Tour Guide 3. Stylish trip Agency in India 4. Enquiry. At first. that point, it'll show the rundown of spots of lodestones of that spot from which the customer can pick his favoured spots as per his need. also, at that point, it takes the top assistant for the visit. also, he selects the place and, also person add reserving information also online payment runner is open. when we successfully add payment also successfully payment shows and also, it'll show that another reserving the posterior to creating an examination trippers can see the craft of stylish trip service.

Keywords: Android, Tourism, Lodestones, Unique, Inventor

Abstract: The Secure Socket Layer (SSL) and Transport Layer Security (TLS) is the most widely deployed security protocol used today. It is essentially a protocol that provides a secure channel between two machines operating over the Internet or an internal network. In today’s Internet focused world, the SSL protocol is typically used when a web browser needs to securely connect to a web server over the inherently insecure Internet. In order to electronically exchange information between network users in the web of data, different software such as outlook is presented. So, the traffic of users on a site or even the floors of a building can be decreased as a result of applying a secure and reliable data sharing software. It is essential to provide a fast, secure and reliable network system in the data sharing webs to create an advanced communication systems in the users of network. In the present research work, different encoding methods and algorithms in data sharing systems is studied in order to increase security of data sharing systems by preventing the access of hackers to the transferred data. To increase security in the networks, the possibility of textual conversation between customers of a local network is studied. Application of the encryption and decryption algorithms is studied in order to increase security in networks by preventing hackers from infiltrating. As a result, a reliable and secure communication system between members of a network can be provided by preventing additional traffic in the website environment in order to increase speed, accuracy and security in the network and web systems of data sharing.

Abstract: Identification of plant health is the new challenging area for the researchers. One of the most important steps in automatic identification of plant diseases is to extract the infected region from the normal portion of the plant. Studying the infected leaves it has been observed that the greenness of the infected portion of the leaves changes significantly with respect to the normal leaves. Images of potato leaves of both categories healthy and diseased captured with digital camera and resolution of 256x256 pixels forms the dataset. CNN model is used for identifying the health status of plants.

Keywords: Convolutional Neural Networks, Plant Health Identification.

Abstract: This chapter attendants’ stoner through Android operation development in Android Studio. It starts by creating an Android operation design for phones and tablets and continues with fresh development modules for the operation. Creating a new Android design is enough straightforward with Android Studio. Android Studio helps to elect the stylish SDK interpretation for the operation. One needs to make the operation and launch it on a device after creation of the operation project. However, he/ she can produce a virtual Android device to run the operation, if a stoner formerly has a device attached to the development machine with a compatible Android SDK interpretation. The chapter also covers the introductory structure blocks of Android operations and the capabilities of Android Studio. The main structure blocks of Android operations are conditioning, services, means, XML lines, the Android Manifest train, and modules. Android operations are organized as a collection of factors. There are four types of factors, and operations can be composed of one or further of each type. A dynamic case of a element corresponds to an operation subset that can be executed singly of the others. So, in numerous ways, an Android operation can be allowed of as a collection of interacting factors. Android operation factors come in four flavours

Keywords: Android, Diagram, Entities, Relationship, Modelling.

Abstract: With the development of Machine learning and AI- assisted trading has gained interest in the past few years. To bring out the abnormal profits from the cryptocurrency market, we use this machine learning and AI assisted trading. We store the daily data for a certain period. With the strategies assisted by state-of-the-art algorithms we obtain great outcomes. With the help of simple algorithms and architecture, the outcomes made the growth in the cryptocurrency market. The cryptocurrency has become popular in 2017 because of the growth in market capitalization. More than 1500 crypto currencies are actively trading in today’s scenario. The crypto currency can be generated and be used for online transactions. Bitcoin is a cryptocurrency technology. The value of Bitcoin keeps varying every second. Therefore, to predict the value of bitcoin price here, we use the LSTM Architecture. Bitcoin is the first digital decentralized cryptocurrency that has shown a significant increase in market capitalization in recent years. The objective of this paper is to determine the predictable price direction of Bitcoin in USD by machine learning techniques like RNN and Tensor-Flow Keras.

Keywords: Cryptocurrency, Prices Prediction, RNN, BeautifulSoup, CoinMarketCap, TradingView, Binance.

Abstract: Banking is the backbone of brand new economic area. one of the most essential facilitators of our society's progress is the economic sector. with out the banking gadget, we might not have the sector we've got nowadays. but, the banking device is presently reliant on the principal bank. CORE (Centralized Online Real-Time Exchange) banking has some of drawbacks, such as a single factor of failure, the fact that power and authority for making plans and decision-making are focused inside the fingers of top control, who are organized in a hierarchical structure and are dictatorial and rigid. Decentralized/disbursed banking is the manner of the destiny because it lets in the anonymity, low/no hobby charges, no unmarried point of failure, and electricity to public. it's miles resilient, democratic, and green via nature. Crypto Banks are decentralized banking systems that provide comparable services to standard banks, together with lending and credit score score. however, it efficaciously gets rid of all the intermediaries that a centralized financial institution employs. There isn't always any centralization in any respect. smart contracts and peer-to-peer services update the workers needed in a centralized bank to structure monetary records and approve loans in a crypto banking surroundings. the majority of the community might be on line because all concerns may be resolved online. The software is designed to look like a computer interface, whether or not on a computer or a cell tool, and the currencies used are in large part cryptocurrencies. on this venture, author advanced a bank-like smart settlement at the Ethereum community. It covers the basics of banking, inclusive of stake and unstake tokens, paying and getting loans account holders, and seeing balances. The smart settlement became written in Solidity, and a few checks were written in JavaScript. Author used truffle framework for testing and deployment of clever contracts. The experiment demonstrates how crypto banks operate in a actual-time placing.

Keywords: Decentralized Finance App, Crypto Bank, Decentralized Bank, Dapp, Smart Contract, Blockchain.

Abstract: Firstly, the image is uploaded from the outside environment with a smart device, followed by detection of the edge of a signboard. It will not check if the image which is captured by the device is related to the sign board or not. It will capture all types of images as input. The next phase is the detection of text and the recognition of the text into two languages such as urdu and english. Here the capture image will be check, that the image is related signboard or not. If the image is related to the signboard it displays the output. Final phase uses Artificial Neural Network for the classification and recognition of the manual extracted from the natural scenes or an outside atmosphere. This paper present , it detect the color image as input and produces the output in the form of black and white. Here the images are capture based on color segmentation and Thresholding. CNN is used to identify the type of pic. Our model has achieved accuracy about 99%.

Keywords: Traffic sign ,detection,CNN,Prediction

Abstract: Mobile Adhoc Network (MANET) is one of the kinds of Wireless networks. The general nature of MANET comprises of non- fixed infrastructure, dynamic nodes, each node act as a router, it is an autonomous user which communicate through wireless links. Due to random movements, the network topology frequently changes, to find the route between source and destination nodes, we use a techniques namely Routing protocol. There are three types of routing protocols in MANET like proactive, reactive and hybrid. In this paper, we would like to improve the performance of one type of proactive routing protocol called Optimized Link State Protocol through Machine Learning (ML) techniques.

Keywords: MANET, OLSR, Machine Learning (ML)

Abstract: Cloud storage service has shown its great power and wide popularity which provides fundamental support for rapid development of cloud computing. However, due to management negligence and malicious attack, there still lie enormous security incidents that lead to quantities of sensitive data leakage at cloud storage layer. Once data is stored in the cloud, a client's sovereignty over its data is lost, leaving the data vulnerable to many security threats. From the perspective of protecting cloud data confidentiality, this project proposed a Mimic model Virtual Assistant that combines cloud computing with blockchain that assures data integrity for homomorphic encryption schemes. To establish a secure CSP platform apart from encrypting data homomorphically, there is a need for a robust, tamperproof, and verifiable security architecture. Virtual Assistant will be hired to store and perform computations on client data. Each VA will have to periodically compute a master hash value of their database to be stored on a private blockchain. A client can compare these master hash values to detect if data tampering has occurred. This distributed verification system fulfils the requirements of confidentiality (HE will be used for encryption), and integrity because data modifications by the CSPs can be detected by comparing master hash values stored on the blockchain. The data sharing process is performed via a smart contract, and involved parties have to escrow to encourage honesty. The schemas of data storing and sharing guarantee the security properties including confidentiality, integrity, privacy, non-repudiation, and anonymity.

Abstract: The world is shifting from analog to digital and marketing is no exception. As technology development is increasing, the use of digital marketing, social media marketing, search engine marketing is also increasing. Internet users are increasing rapidly and digital marketing has profited the most because it mainly depends on the internet. Consumer’s buying behavior is changing and they are more inclined towards digital marketing rather than traditional marketing. The purpose of this review paper is to study the impact of digital marketing and how important it is for both consumers and marketers. This paper begins with an introduction of digital marketing and then it highlights the mediums of digital marketing, the difference between traditional and digital marketing, and the pros, cons, and importance of digital marketing in today’s era. Keywords - digital marketing, internet, online advertising, internet marketing

Abstract: People now-a-days utilize Automated Teller Machines (ATMs) in large numbers. People rely on ATMs to meet their daily demands in a convenient manner. As it is a crucial aspect, security is a must. ATMs are automated teller machines that allow clients to deposit or withdraw money from banks. It has been discovered that the frequency of crimes involving ATMs has increased, necessitating the need for improved ATM security. RFID technology, fingerprint, facial recognition, iris scan, OTP, reference number, random keypad, and other technologies are all utilized to ensure the security of ATM machines. In a standard ATM system, card and PIN numbers are required for authentication, which causes security issues like lost cards, stolen pin numbers, card cloning, shoulder surfing, fake keyboard, skimming, etc. This paper mainly focuses on the implementation of Anti spoofing based facial recognition for ATM system using liveness detection.

Keywords: ATM, Liveness Detection, Facial Recognition, Landmark Detection, OTP.

Abstract: The proposed paper surveys the big data usage in multiple sectors and calls attention to big data tools and big data analytics in numerous fields. In the proposed paper, the usage of big data and its tools have been discussed and numerous examples have been shown. Regarding the efficient tools in big data, more than 10 papers have been reviewed and their summaries and important takeaways are mentioned in the literature survey of the paper. This paper will provide an overview to the researchers and practitioners about the extensive usage of big data and its tools. Use of big data in the healthcare sector has been explained along with the names of the sources where data is collected from. This paper explains the importance of big data in our life and details the numerous ways in which it solves real-life issues. Big data tools such as Apache, Hadoop and HPCC has been highlighted in this paper with their attributes and advantages.

Keywords: Big data, Hadoop, usage, medical-sector, dataset, big data tools

Abstract: Covid is eventually a constant scourge and the huge premium for testing of the dissuasion has asked inadequate money vaults in shows. To make the adequacy of Coronavirus openness, PC vision predicated textures can be utilized. Anyway, a tremendous game plan of planning data is required for making a careful and reliable model, which is at this point not feasible to be achieved permitting about the peculiarity of the dissuasion. Various models are at this point being utilized inside the clinical consideration region for requesting brilliant conditions, one relative model is for relating pneumonia cases by practicing radiographs and it has satisfied adequately high delicacy to be utilized on cases (18). With the underpinning of having bound data for Coronavirus ID, this presumption evaluates the upside of including move capability to unite the show of the Coronavirus divulgence model. By practicing pneumonia dataset as a base for point birth the thing is to affect a Coronavirus classifier through move instruction. Practicing move schooling, a delicacy of 98 was satisfied, changed with the main delicacy of 33 when move capability was not utilized.

Keywords: COVID19, Early detection, chest x-ray images, combination of deep learning model, transfer model, rural area.

Abstract: In these tough times, during a pandemic, when a virus of the size of few microns has taken the whole world back. With the global economy declining, people are finding new ways to make money online, sometimes also through illegal means. Phishing is regarded as one of the most dangerous risks to internet users, and it is growing at an exponential rate. As a result, hackers have become more innovative in their assaults and have been able to execute them on a big scale. A phishing attack works by creating an accurate clone of an actual site and directing people to the site's page. Because the site's page is deceptive and identical to the actual, legitimate individuals are frequently duped into performing activities on such pages. Phishing is a type of assault that combines foundations of social engineering with emerging technological approaches. This wrapping of the faux site to appear to be the real one persuades the user to give their identity. Our system developed with the concepts of Hybrid learning which is a amalgamation of Machine Learning and Deep Learning, aims to detect such Phishing attacks by marking websites as legitimate or phishy.

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

Abstract: The miniaturization of existing technology has been on the forefront of development, optimization—both of function and cost—and advancement of electro-mechanical systems. The need to develop smaller, more cost and energy efficient electronics with a more varied portfolio of applications will lead to the continued creation of complex MEMS devices. The creation of MEMS microphones is an example of the necessity of packaging the function of existing larger recording equipment into objects such as cell phones, hearing aids, and other complex devices. Due to the minuscule nature of these systems, placing them into an array allows for the same amount of data acquisition as their larger counterparts in a similar array, but in a much smaller footprint. This paper discusses some of the current uses of MEMS microphones, their manufacture and the mathematics necessary to quantify and utilize their function. That information was utilized to develop a simulation of a MEMS microphone using the COMSOL software. Lastly, a physical demonstration was developed to offer a proof of concept for a larger array in the function of object detection.

Keywords: MEMS, 2D, 3D, piezoelectric, capacitive, COMSOL, diaphragm, Active noise cancelling, UAV, SOG, ASIC, SNR, I2S

Abstract: In everyday life, electricity is necessary, and proper use is critical, Electricity is a form of energy and is playing vital role in the world. Electricity has become an essential part of human life and is now considered to be a necessity. India is a vast country and relies upon the power. 95% of the people are blessed with the power supplied by the both centre and state government. So as to achieve balanced regional development of the country. The main objective of our project is to monitor the status of the electricity transmission line in real time, and whenever there is a fault in the line, we make use of an IoT device to locate the faulty line/area and display its location in a digital map we make use of an IoT device to locate the faulty line/area and display its location in a digital map.

Keywords: IoT, Faulty Transmission Lines, Thingspeak, Arduino.

Abstract: Now a day’s vehicle parking is an important issue and day by day its necessity is adding. In some countries we're still using the homemade vehicle parking system and that's why we're facing problems like destruction of time and energy, chancing free space around the parking ground when we need to situate our car which requires a good quantum of lighting. Another issue is chaos that happens while parking because there's no particular system anyone can situate anywhere that eventually causes damage to the vehicles while moving out or in the parking place. Security is also an issue there. To break these problems, we're introducing new car parking system. Control along the transmission path.

Abstract: The future of virtual experience has been enhanced nowadays, these results in the form of various diplomatic problems and desired solutions are given via Beta-Verse. Science fiction often refers to this as a hyperbolically developed version of the Internet that takes the form of a single, universal virtual world that is facilitated by the use of virtual and augmented reality headsets. Whenever the user is interacting with the machine, they will have a Virtual and Perceptual experience in Real-Time, XR Technology combines virtual, real-world environments and realities through the use of VR (Virtual Reality) and AR (Augmented Reality), Users can generate new forms of reality by bringing digital objects into the physical world or by bringing physical objects into the digital world.

Keywords: Beta-Verse, Augmented Reality (AR), Virtual Reality (VR), Extended Reality (XR), Digital World, Physical World.

Abstract: Pneumonia is an acute pulmonary infection that can be caused by bacteria, viruses, or fungi and infects the lungs, causing inflammation of the air sacs and pleural effusion, a condition in which the lung is filled with fluid. It accounts for more than 15% of deaths in children under the age of five years [1]. Pneumonia is most common in underdeveloped and developing countries, where overpopulation, pollution, and unhygienic environmental conditions exacerbate the situation, and medical resources are scanty. Therefore, early diagnosis and management can play a pivotal role in preventing the disease from becoming fatal. Radiological examination of the lungs using computed tomography (CT), magnetic resonance imaging (MRI), or radiography (X-rays) is frequently used for diagnosis. X-ray imaging constitutes a non-invasive and relatively inexpensive examination of the lungs. Fig 1 shows an example shows an example of a pneumonic and a healthy lung X-ray. The white spots in the pneumonic X-ray (indicated with red arrows), called infiltrates, distinguish a pneumonic from a healthy condition. However, chest X-ray examinations for pneumonia detection are prone to subjective variability [2, 3]. Thus, an automated system for the detection of pneumonia is required. In this study, we developed a computer-aided diagnosis (CAD) system that uses an ensemble of deep transfer learning models for the accurate classification of chest X-ray images.

Abstract: Hand gesture recognition systems have advanced rapidly in recent years, owing to their capacity to successfully collaborate with machines. In a virtual environment, gestures are seen to be the most natural way for humans and computers to communicate. We frequently use hand gestures to convey information because they are a form of nonverbal communication that allows us to express ourselves freely. To extract the hand region in our system, we employed background subtraction. Our PC's camera records a live video, from which a preview is taken with the assistance of its functionalities or activities.

Keywords: Gesture recognition, OpenCV, human-computer interaction, python, machine learning.

Abstract: College Management System provides a complete solution for your college administration. Student Information, Online Results, Quotation Paper, Online Attendants are the main modules of our College Management System. Dynamic and highly motivated, with a liberal & modern outlook on education and organization and a contemporary vision and working style, Educational Management are trying to Incorporate modern concepts, amenities & system to create a forward and vibrant institute, comparable with best & most modern in country. Educational Management Would is able to manage student personal information, Education statistic and highlight achievement and awards. Fee collection of the students is a cumbersome task and there would be a system in place to monitor the fee collection and report to the account department on regular basis. Finally account department to manage, monitor and generate all account detail during the operation of educational management. CMS is a comprehensive system that addresses all functional requirements that can be implementing in operator of college management. Below module, which scope the entire operational requirement of any College Management System.

Keywords: Online Results, Quotation Paper, Online Attendants

Abstract: This project titled “Prison Management System” aims at providing management software for handling the inner working of Tihar Jail across the country. Since Tihar Jail already offers certain recreational facilities, employment opportunities and educational prospects with an official degree, however on my research, I realized that there was no inner management system for handling all activities taking place within the prison premises and could use a lot of improvisation. The report is based on 5 main sections- Introduction and Motivation, Literature Review, Design Modules, Implementation, Benefits and Scalability. Introduction and Motivation deals with the details of facilities offered with aim of transformation of prisoners so that they don’t resort to their criminal ways, it also elaborates the inspiration taken from Kiran Bedi, former IPS who had a vision of transforming criminals into civilized human beings.

Abstract: College Fest Management System for the fest organizing team of the college web-based application project which deals with the maintenance of events and managing of the fest. This will help the coordinators, judges, and the organizing team in managing various types of records about events and their participants respectively. The admin will be able to manage the overall information pertaining to the events, participants’ coordinators, departments, and the winners. The guest user will be able to view the events and get enrolled the same as a participant.

Keywords: Login module, Registration model, view competition detail model, view event location model, view events model, view winners model, view judge model.

Abstract: Authentication enables organizations to keep their networks secure by permitting only authenticated user or processes to gain access to their protected resources. this may include computer systems, networks, databases, websites and other network-based applications or services. With the rise in cyber- crime, security threats related to logins & accesses have become a major concern. Also, the use of single security authentication is not sufficient enough to keep you protected from cyber threats. Hence to increase the security level we have Different types of password authentication that will make sure that only the authorized person will have access to the system or data. It contains three-level- logins having three different kinds of passwords systems for ensuring adequate security.

Keywords: Authentication, Authentication Techniques, Information system, Security.

Abstract: We gift PACK (Predictive ACKs), anovel destination to destination traffic redundancy elimination (TRE) system It especially designed forcloud computing customers. PACK’s main advantage is its capability of offloading the cloud-server TRE effort to finish shoppers, so reducing the process prices induced by the TRE rule. Not like earlier solutions, PACK relies on a unique TRE technique, which allows the consumer to use recently received chunks to spot antecedently received chunk chains, that in flip can be used as reliable predictors to future transmitted chunks.PACK want not need the server to continuously maintain clients’ standing. This makes PACK terribly omfy for pervasive computation network environments that mix consumer quality and server migration to take care of cloud physicalproperty.Cloudrelated TRE wants to apply a even handed use of cloud resources thus that the information measure value reduction combined with the additional value of TRE computation anddata storage would be optimized. we tend to gift a replacement fully purposeful PACK implementation, clear to all or any transmission control protocol protocol primarily based applications and every one network devices. Finally, we tend to analyze and implement PACK edges for cloud users, exploitation traffic traces from various sources.

Keywords: Predictive Acknowledgement, Traffic Redundancy Elimination System, Caching,Cloud Computing, Network Optimization.

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

Keywords: This project proposes and automatic teller machines security model that would combine a physical access card and electronic facial recognition using Deep Convolutional Neural Network.

Abstract: The COVID-19 pandemic outbreak has resulted in an unprecedented crisis across the globe. The pandemic created an enormous demand for innovative technologies to solve crisis-specific problems in different sectors of society. In the case of the education sector and allied learning technologies, significant issues have emerged while substituting face-to-face learning with online virtual learning. Several countries have closed educational institutions temporarily to alleviate the COVID-19 spread. The closure of educational institutions compelled the teachers across the globe to use online meeting platforms extensively. The virtual classrooms created by online meeting platforms are adopted as the only alternative for face – to-face interaction in physical classrooms. In this regard, student’s attendance management in virtual classes is a major challenge encountered by the teachers. Student attendance is a measure of their engagement in a course, which has a direct relationship with their active learning. However, during virtual learning, it is exceptionally challenging to keep track of the attendance of students. Calling student’s names in virtual classrooms to take attendance is both trivial and time-consuming. Thus, in the backdrop of the COVID-19 pandemic and the extensive usage of virtual meeting platforms, there is a crisis-specific immediate necessity to develop a proper tracking system to monitor student’s attendance and engagement during virtual learning. In this project, we are addressing the pandemic-induced crucial necessity by introducing a novel approach. In order to realize a highly efficient and robust attendance management system for virtual learning, we introduce the Random Interval Query and Face Recognition Attendance Management System(hereafter, AI Present).

Keywords: virtual classroom, attendance, random interval query.

Abstract: Security plays a vital role in protecting the valuable data or information from the unauthorized access and its misuse.one of the most discussed technique for insuring data security is “cryptography”. Cryptography provides the secure communication in the presence of malicious third parties. This paper mainly focuses on the role of cryptography in data security and discussed some of the popular techniques used in cryptography.

Keywords: Cryptography , Encryption, Decryption, Data security.

Abstract: cyber security is the state of process of protecting and recovering computer systems network devices and program from any type of cyber-attack. It plays important role in field of information technology. Today in the modern life style most of the people use internet, and uses new technologies in which they give their data to many apps and websites. Securing the information have become one of the biggest challenges in the present day. In this present time cyber-attacks are increasingly rapidly; cyber threats can come from any level of organization. whenever we think of cyber security we first think about cybercrime. Information theft is the most expensive and fastest – growing segment of cybercrime. This paper primarily focuses on cyber security concerns related to the new technology latest cyber security techniques, principals, trends and developments that impacts cyber security.

Keywords: Cybercrime, cyber security, cyber ethics, cybersecurity techniques, social media.

Abstract: Now a information and communication technology made deep effect on human life. But E-Learning system are use to online learning refers to instruction that is delivered electronically through multimedia and internet platform and application.It is used to digital tools for learning with other terms such as web based learning , computer – assisted instruction, and internet based learning. The Research results shows that the design implementation of the proposed system integrate all the critical and valuable communication tools that of effectively improve the collaboration in e- learning environment.

Keywords: E-Government, E- University, E- learning , Course materials

Abstract: Security is at most concern for anyone nowadays, whether it's data security or security of their own home. With the advancement of technology and the increasing use of IOT and AI, digital door locks have become very common these days. Face recognition system is broadly used for human identification because of its capacity to measure the facial points and recognize the identity in an unobtrusive way. The application of face recognition systems can be applied to surveillance at home, workplaces, and campuses, accordingly. The problem with existing face recognition systems is that they either rely on the facial key points and landmarks or the face embedded from the recognition process. Deep convolutional neural networks have been successfully applied to face detection recently. Despite making remarkable progress, most of the existing detection methods only localize each face using a bounding box, which cannot segment each face from the background image simultaneously. To overcome this drawback, this project present a face detection and identification method based on improved Mask R-CNN, named G-Mask, which incorporates face detection and recognition into one framework aiming to obtain more fine-grained information of face. This paper also investigates the robustness of the face recognition system when an unknown person is being detected, wherein the system will send an SMS Web link to the owner of the house through edge computing. The door lock can also be accessed remotely from any part of the world by using a door lock integrated server account.

Keywords: open smart door ,unknown person identification, send to SMS authorized person.

Abstract: Healthcare is consequential for everyone in their life so when people have minor issues and can’t go to hospital all that time here comes the healthcare chatbot. Healthcare chatbot is an emerging platform for medicos to dispense minor health issues by sitting at home. It avails them to get remedied from minor issues like pyrexia, arctic, etc. this even avails to dispense sizable voluminous consultation fees when liable to meet the medico. Here medicos will be available throughout the day which avails the patient not to get panic. To lead a better life healthcare is prodigiously much paramount. But it's very arduous to get the consultation with the medico just in case of any health issues. The proposed conception is to make a medical chatbot utilizing Artificial Perspicacity which will diagnose the disease and supply rudimentary details about the disease afore consulting a medico. To abbreviate healthcare costs and ameliorate accessibility to medical erudition the medical chatbot is made. Certain chatbots acts as a medical reference book, which avails the patient ken more about their disease and avails to enhance their health utilizer can achieve the authentic advantage of a chatbot only if it is able to diagnose all quite disease and produce obligatory information. A text-to-text diagnosis bot engages patients in conversation about their medical issues and provides a personal diagnosis fortified their symptoms. Hence, people will have a cerebrated about their health and have the correct aegis.

Keywords: Artificial Perspicacity, Prognostication, Pattern matching. Disease, Query processing

Abstract: We implement a basic solution for accumulating and obtaining user data within the existing home automation system in this paper. Data collection modules that operate on the home automation gateway and within the home automation cloud are implemented, allowing us to connect to the already existing big data middleware platform. It's the first step toward constructing the extensive data storage and analysis component for the existing housing automation solution. The collected data can be used to enable various scenarios of interest to end-users, such as the detection of emergencies and system irregularities.

Keywords: Data Gathering, Big Data, Machine Control, Cloud Computer.

Abstract: Cloud computing is the next big thing in information technology after the internet; some say it's a metaphor for the internet. It is an Internet-based computing technology in which software, shared resources, and information is delivered to consumers and devices on-demand and on a pay-per-use basis. Even though the cloud is becoming increasingly popular, usability and respectability issues, data protection and privacy issues, and other security issues continue to be major roadblocks in the field of cloud computing. The primary concern for cloud storage is privacy and security. Encryption is a well-known technology for safeguarding sensitive information. The use of a combination of public and private key encryption to conceal sensitive user data, as well as cipher text retrieval. The paper investigates the viability of using an encryption algorithm for data security and privacy in cloud storage.

Keywords: Online storage, cypher text retrieval, Privacy and encryption techniques.

Abstract: Internet of things (IOT) moderately progressing as the subsequent phase of evolution of internet, it become very important to recognize the various domains having the potential for application of IOT, and challenges that are related to this application. Covering from smart cities, health care, smart agriculture, to even smart living and smart environment. In the recent years IOT allowing technologies are improving greatly, but some of its problem still needs attention to solve. This paper presents the recent improvement in IOT technologies and discuss about future scope and research challenges.

Keywords: Internet of Things (IOT), Blockchain of Things (BCOT), Agriculture, Domains of IOT.

Abstract: Any information on the internet may be found using search engines. Search Engines are used to search any information on the internet. .Any website owner's primary goal is to have their site appear at the top of all search engine results pages (SERPs). The art of enhancing a website's exposure OR RANKING in Search Engine Result Pages is known as SEO. Apart from search engine ranking, it also allows websites to compete with their competitors' websites, as each website owner expects to see their own website first on the list. This paper presents some basic SEO ideas and tactics. It also expresses the various approaches used by search engines to improve their results.

Keywords: SEO, Techniques, Google, Google Ad-words, Tools.

Abstract: Association rule mining is one of the important part in the field of data mining. The scope of association rule mining is very broad. In association rules mining, frequent item sets mining is essential. Apriori algorithm, Eclat algorithm and FP-growth algorithm are famous algorithms to find frequent item sets. This algorithm can reduce the database and improve mining efficiency.

Keywords: Association Rule, Itemset, Data Mining, Algorithms.

Abstract: The blockchain innovation was found with the development of Bit coins (the first cryptographic money). How share information and design the information in a software engineering term. The blockchain innovation is a fundamental way to deal with the appropriated data set which is a gathering of independently control and that store and offer data. Furthermore, it's an information structure that makes it conceivable and simpler to freely make an advanced record of information and offer it a larger part of the members in the framework. A blockchain is a peer - to - peer framework with no focal authority overseeing information stream if once enter any sort of information that data can never be eradicated in light of the fact that it’s contains a contain and obvious record of each and every exchange made. That is the reason the Bitcoin is decentralized peer - to - peer computerized cash, and it's the best illustration of purposes of blockchain innovation. There are comprise of some unique sort of blockchain, public blockchain (for example Bitcoin an enormous conveyed network are gone through a local token.), Permissioned Blockchains (for example Ripple its control jobs that people can play inside the organization.), Private Blockchains (for example private blockchain is a permissioned blockchain), Hybrid (use in Medical Records and land.) and Consortium (Mainly use in banking, Research, Supply Chain). The primary centre part of blockchain are hub (client or PC inside the blockchain); exchange (littlest structure square of a blockchain framework); lock (information structure utilized for keeping a bunch of exchanges which is appropriated to all hubs in the organization); Chain (a succession of squares in a particular request); Miners (explicit hubs which play out the square check process); Consensus (set of rules and arrangements to do blockchain activities).

Keywords: Information, Working, Structure, and Phases, Market value.

Abstract: This paper proposed that the way of controlling the cursor with our hands without using the electronic device , The operation performed like clicking dragging removing deleting will be performed by the different hand gestures and sign. This system needs only a webcam as input device which will control the system of gesture and the software which is required to implement this system is OpenCV and python. The camera output will be displayed on the operating system screen so that it can be further calibrated by the user. And it also perform the file transfer between the two system which are connected to a same and single network the system uses nothing more only the low resolution webcam which will act as sensor and able to track the user hand bearing color caps into the two dimension the hand gesture is a natural way of communication and also the transferring file scheme will be implemented by using the python server. Keyword: OpenCV, Hand gesture , Image capture, Masking

Abstract: We have been living in the modern technology of the world where all the data and the resource comes us in the online mode rather it is personal data or any information notice and so on as nowadays all the information are available online there are large number of user who are accessing it among some of them uses the information for gaining the knowledge and some think how to destroy or steal the data which are present in the website or database without any knowledge of the owner of the website. This paper purpose is that how the data has been stolen by someone its know as hacking who are those hackers , what code conduct of ethical hacker and need of them. As we can see that the state security on the internet is very poor hacking is the activity in which the person exploits the weakness in the system for the profit of themselves. The public and the private organization migrates the function applications such as marketing, commerce and database which are access on the internet. This paper describes about the attacks of the hacking and what is the ethical hacking and impact of ethical hacking.

Keywords: Ethical hacking, hacking, hackers, risk management

Abstract: Nowadays, more and more professions require long-term concentration. Drivers must keep a close eye on the road, so they can react to sudden events immediately. Driver fatigue often becomes a direct cause of many traffic accidents. Therefore, there is a need to develop the systems that will detect and notify a driver of her/him bad psychophysical condition, which could significantly reduce the number of fatigue-related car accidents. However, the development of such systems encounters many difficulties related to fast and proper recognition of a driver’s fatigue symptoms. One of the technical possibilities to implement driver drowsiness detection systems is to use the vision-based approach. Here we are detecting the driver's drowsiness by estimating the vision system.

Keywords: car accident, drowsiness, recognition.

Abstract: Sentiment Analysis is used to determine whether a given text contains negative, positive, or neutral emotions. It’s a basic form of text analysis that use the natural language processing (NLP) and machine learning (ML) techniques that are combined to assign sentiment scores to the topics, categories or entities within a phrase. It usually helps in textual data to help business monitor brand and product sentiment in customer feedback, and understand customer. It refers to the use of text mining and other technologies to extract attitudes, opinions, and other information for analysis is classifying the polarity of a given text as the document, sentence or feature of aspect level so whether the expressed option in a document, sentence or an entity feature is positive, negative, or neutral.

Keywords: Sentiment analysis tasks, Tasks of sentiment Analysis, Level of sentiment analysis.

Abstract: Brain tumors are the most common and the aggressive leading to very short extensive in their higher grade thus treatment planning is the highest grade key stages to improve the quality of patients. Brain Tumor Segmentation is one of the most crucial and arduous tasks in the terrain of medical image processing as a human-assisted manual. Magnetic resonance image is the image widely used for imaging technique to access these tumors but large amount of data produced by(MRI) privence manual segmentation in a reasonable time. Brain tumor is also known as aberrant growth of cells a particular region of a human body. Results show that the CNN archives rate of 97.5% accuracy with low complexity and compared with the all other state of arts methods

Keywords: Brain tumor, Brain cancer, Magnetic Resonance Imaging (MRI), CNN (Convolution Neural Networks), Convolutional Layer, Pooling Layer, Fully Connected Layer etc.

Abstract: The 2019 novel coronavirus disease (covid-19), with a starting point in china, has spread rapidly among people living in other countries, and is approaching approximately 34,986,502 cases worldwide according to the statistics of european centre for disease prevention and control. There are a limited number of covid-19 test kits available in hospitals due to the increasing cases daily. Therefore, it is necessary to implement an automatic detection system as a quick alternative diagnosis option to prevent covid-19 spreading among people. In this study, five pre-trained convolutional neural network based models (resnet50, resnet101, resnet152, inceptionv3 and inception-resnetv2) have been proposed for the detection of coronavirus pneumonia infected patient using chest x-ray radiographs. We have implemented three different binary classifications with four classes (covid-19, normal (healthy), viral pneumonia and bacterial pneumonia) by using 5-fold cross validation. Considering the performance results obtained, it has seen that the pre-trained resnet50 model provides the highest classification performance (96.1% accuracy for dataset-1, 99.5% accuracy for dataset2 and 99.7% accuracy for dataset-3) among other four used models.

Keywords: coronavirus; bacterial pneumonia; viral pneumonia; chest x-ray radiographs; convolutional neural network; deep transfer learning.

Abstract: Social media is a platform for public around the World to discuss their issues and opinions. Before knowing the actual aspects of social media people must have to know what does social media mean? Social media is a term used to describe the interaction between groups or individuals in which they produce, share, and sometimes exchange ideas, images, videos and many more over the internet and in virtual communities. Children are growing up surrounded by mobile devices and interactive social networking sites such as Twitter, MySpace, and Facebook, Orkut which has made the social media a vital aspect of their life. Social network is transforming the behavior in which youthful people relate with their parents, peers, as well as how they make use of technology. The effects of social networking are twofold. On the positive side, social networks can act as invaluable tools for professionals. They achieve this by assisting young professionals to market their skills and seek business opportunities. Social networking sites may also be used to network efficiently. On the negative side, the internet is laden with a number of risks associated with online communities. Cyber bullying, which means a type of harassment that is perpetrated using electronic technology, is one of the risks. In this paper we cover every aspect of social media with its positive and negative effects. Focus is on the particular field like health, business, education, society and youth. During this paper we explain how these media will influence the society in a broad way.

Abstract: The voting system take place in every country every cites and every village every country has the robust and the stable way of organizing the election so that the people can give their vote to A appropriate person, as we talk about the modern technology every thing should be according to the modern world as today we Are Been living in a technology world every day new invention we come to see rather than that in the era we have Saw that the election are taking place in the polling station stations every individual person goes on polling station to give the vote and select their leader But it Consumes large number of time people have stand in a Queue for vote and for those who cannot come due to some work than there vote is empty in order to evolve this system can come across the many ideas which consume less time and people can give their vote at the place where they are it is only the digital voting system in this system one can give the vote there vote where there is net connection or by the smartphone application so on this system is build by using the blockchain technology it can also be replaced by the traditional solution as today the foundation of the blockchain has received the at mentation in present day it can be used in the number of fields such as in ATMs bank security so on however the blockchain has been developed by the many techniques some techniques are mathematics algorithm and the many more techniques this provides the description of digital voting system based on the blockchain.

Keywords: Digital voting system, digital voting system based on block chain, proposed system & architecture working of the system

Abstract: As the world recovers from the Covid-19 crisis, major steps are taken worldwide to boost the recovery process. The world is becoming more resilient as a result of vaccination campaigns. In such circumstances, we as citizens must ensure that we adhere to security protocols and norms established by the government. Social distancing and wearing a face mask are the rudimentary elements of this system. The proposed system makes a systematic effort to comply to this. The system keeps track of every person who enters and exits the area under surveillance. In addition to this, a person with high body temperature is blacklisted. This data is entered into a database, and daily logs are maintained. A headcount of people in the area is maintained and admits to the area are given accordingly. If any violations take place, alerts are issued and sent directly to the primary android device. The face mask detection model is trained on a comprehensive real-world dataset. The model uses Convolutional Neural Network (CNN). It will function by recognizing facial boundaries and predicting whether or not you are wearing a face mask in real time. YOLO Object detection algorithm is used to identify people and calculate the euclidean distance between them. This distance is used to keep track of social distancing. A heat map can be generated which later can be referred to sanitize the crowded locations.. Index Terms—Covid-19, Social distancing, Convolutional Neu- ral Network , YOLO, Face Mask Detection.

Abstract: This review paper is all about aquaponics and its implementation using IoT. The motivation for this literature study is to provide insights into the usage of various sensors in the system. This includes studying of turbidity in different solutions with comparison and different values of pH. Sensors are the heart of IoT-based projects and their accuracy needs to be at par for the smooth functioning of the system on they have been implemented. This information on some sensors can be compiled and studied further to also resolve the challenges in farming.

Keywords: Aquaponics, IoT, pH, and Turbidity

Abstract: As today the growth of the electronic devices are resulting in the very high demand because the things get faster because of the electronic devices we can see as for withdrawing the money one has to go the bank and stand in a Queue for money when the numbers come after two three hours then they are browning money from the bank so as today there is large number of demand of the electronic device which Automated Teller Machine (ATM) it is machine in which one can take the money immediately from the ATM whenever they want as this system works online we know that in the online system there must be security and most of them try to do fraud also in the ATM ass while in the transaction the user already gets the password and card for withdraw his own money, although this security aspect are there than also the fraud happens it has become the biggest issue for the user in order to gain trust and confident over the ATM’s, purpose of this paper is to examine the different types of Automated Teller Machine, Security which has been improved for all the user who are using the ATM for transaction, This paper assumes the frame security of the ATM transaction.

Keywords: ATM, Authentication, Integrity, Security

Abstract: The goal of resume screening is to find the best candidates for a position. In order to match and rate candidates in real-time, the software must employ natural language processing and machine learning. Our system is a resume ranking software that uses natural language processing (NLP) and machine learning. Input would be resumes and job descriptions, output would be a highly ranked candidate’s resume. Output results are acquired instantly in real-time. We will be using Mong for string matching, Cosine Similarity, TF-IDF. The existing systems are simple and effective but are not robust in terms of accuracy, efficiency, and processing. Through the analysis of the works of literature on existing methods, it can be found that these are traditional systems that could lead to inaccurate assumptions and loss of human potential. We propose a web application that aims to order the resumes, by intelligently reading job descriptions as input and comparing the resumes which fall into the category of given Job Descriptions. In order to match and rate candidates in real-time, the software employs natural language processing It provides a ranking after filtering and recommends the better resume for a given textual job description. The Advantages of the proposed system are Secured, Interpretability, High accuracy, Lightweight model & fast processing. Real-time use cases. It could be used in MNC’s where multiple resumes must be screened every single day for multiple jobs, government, and administrative offices.

Abstract: Location based alarm using GPS is an attempt to add an alarm facility for mobiles, based on the location of the device and to find the nearest places from the current location of the mobile device. The location based alarm will give you alert when you reach your desired destination. Location based alarm is a GPS based alarm, If you set an alarm, it will make a sound and notification once it's detected you are within the user defined range from the destination. The user needs to save the current location using longitude and latitude, the alarm will ring when the user is near to the location. This location based alarm is useful for the traveling sales persons and persons who are traveling in a train. The traveling sales person needs to do different kind of works in different places. It is difficult to remember all the places for him. So by using this application he can set an alarm to the places, where he need to go. The GPRS settings must be enabled on a mobile device to use this application.we are using a SHA1 signature to generate a key google map API key and google play service API for displaying the map in mobile device. The generation of SHA1 signature will be discussed in the methodology.

Abstract: For maintaining the discipline in the classroom and let students grasp there knowledge the attendance system was introduced every organization department school colleges where the student comes in the college the attendance is compulsory to see whether he or she is present in the classroom or absent in the classroom, and we can also see that the attendance taken by the teachers most of them uses the old technique as by calling the roll number and another is signing in the sheet of the paper this system makes the disturbance in the classroom, and it consumes a large time for calling the individual roll number and signing, In order to evolve this system many ideas come across in the mind, but our purpose of attendance is only through the face recognition system in the system the attendance will be marked automatically by recognizing the person facial features it can also be implemented in many fields where there is attendance and plays the vital role. The purpose of this paper is to recognize the person face and mark the attendance.

Keywords: Face Recognition, Face Detection, Haar-Cascade classifier, attendance system.

Abstract: Problems in agriculture supply chain like broken supply chain, deceptive traders, a good considerable price for the commodity have become more severe. This has lead to current situation like increase in death rate of farmers, high margins for successive chain members this also bought high inflation in rates of the commodities which has badly affected the consumers. So we have come up with a solution using block-chain technology to make this efficient. The fundamental structure of block-chain makes it highly secure and systematic way to store the data. Block-chain uses different algorithms like hashing, cryptography, consensus, digital signatures, digital certificate, smart contracts etc. Different organizations are working to overcome such problems in supply chain. Block-chain is prime solution to create communities and ownership in an virtual system. Index Terms: Hashing, Cryptography, Con- census, Smart Contract, Digital Signature, Digital Certificate, Blockchain.

Abstract: we aim to develop a prediction system using machine learning to detect and classify the presence of diabetes in e-healthcare environment using Ensemble Decision Tree Algorithms for high feature selection. A significant attention has been made to the accurate detection of diabetes which is a big challenge for the research community to develop a diagnosis system to detect diabetes in a successful way in the e-healthcare environment. The existing diagnosis systems have some drawbacks, such as high computation time, and low prediction accuracy. To handle these issues, we have proposed diagnosis system using machine learning methods, such as preprocessing of data, feature selection, and classification for the detection of diabetes disease in e- healthcare environment. Model validation and performance evaluation metrics have been used to check the validity of the proposed system. We have proposed a filter method based on the Decision Tree algorithm for highly important feature selection. Two ensemble learning Decision Tree algorithms, such as Ada Boost and Random Forest are also used for feature selection and compared the classifier performance with Wrapper based feature selection algorithms also. Machine learning classifier Decision Tree has been used for the classification of healthy and diabetic subjects. The experimental results show that the Decision Tree algorithm based on selected features improves the classification performance of the predictive model and achieved optimal accuracy. Additionally, the proposed system performance is high as compared to the previous state-of-the-art methods. High performance of the proposed method is due to the different combinations of selected features set. Furthermore, the experimental results statistical analysis demonstrated that the proposed method would be effectively detected diabetes disease. Index Terms: Machine Learning , Random Forest, PIMA Dataset, IDT-3, ADA Boost, e-Health Care.

Abstract: Recently, the huge amounts of data and its incremental increase have changed the importance of information security and data analysis systems. Intrusion detection system (IDS) is a system that monitors and analyzes data to detect any intrusion in the system or network. High volume, variety and high speed of data generated in the network have made the data analysis process to detect attacks by traditional techniques very difficult. To proposed Recurrent Neural Network (RNN) algorithm to detect the IDS. The data processed by the preprocessing module are compressed by the auto-encoder module to obtain a lower-dimensional reconstruction feature, and the classification result is obtained through the classification module. Compressed features of each traffic are stored in the database module which can both provide retraining and testing for the classification module and restore these features to the original traffic for post event analysis and forensics. We used KDD cup 99 to train and test the model. Through this way, we could reduce the number of false alarms and increase the accuracy of the designed intrusion detection system.

Keywords: Intrusion detection system, Recurrent Neural Network, KDD cup99

Abstract: Object detection is the process of determining the presence, location, and type or class of at least one object using a bounding box. The person detection process produces a bounding box and allot a class label as a person based on YOLO v3. In YOLO v3 the features are learned, divides the image cells and each cell says a bounding box and entity classification directly. There could be more than one bounding box per person, but the system makes use of non-maximum suppression to reduce the number of bounding boxes to one per person. Finally, the number of persons in the image and video are calculated using the count of the bounding boxes. The dataset used for static pedestrian detection is the INRIA dataset and ShanghaiTech dataset. Yolo_Mark is used for marking bounding boxes of persons and gets its annotation files using 243 images from the INRIA dataset. Darknet is used as the framework for implementing YOLOv3. From INRIA Dataset 120 images are used for testing purposes. Testing on the INRIA dataset resulted in an accuracy of 96.1%. From the Shanghai tech-B, dataset 56 images are used for testing. Testing resulted in an accuracy of 87.3%.

Keywords: Yolo, CNN, CUDA.

Abstract: Cyberbullying is a major problem encountered on internet that affects teenagers and also adults. It has lead to mishappenings like suicide and depression. Regulation of content on Social media platorms has become a growing need. The following study uses data from two different forms of cyberbullying, hate speech tweets from Twittter and comments based on personal attacks from Wikipedia forums to build a model based on detection of Cyberbullying in text data using Natural Language Processing and Machine learning. Three methods for Feature extraction and four classifiers are studied to outline the best approach. For Tweet data the model provides accuracies above 90% and for Wikipedia data it gives accuracies above 80%.

Abstract: Designing a system for automatic image content recognition is a non-trivial task that has been studied for a variety of applications such as face detection, face recognition, person identification. Face recognition is one of numerous presentations of digital image processing. Automatic face detection is a complex problem which is concerned with the automatic identification of an individual in a digital image. But there are no solutions to detect faces automatically with low resolutions in various applications scenario. We can implement this project computer vision system to predict the screens which are near to their vision or not. This can tiredness the eyes and place stress on the torso because the backrest is no longer provided that support. Viewing distances that are too short may cause eyes to work harder to focus (convergence problems) and may require sitting in awkward postures. For instance, user may tilt their head backward or push chair away from the screen, causing you to automatically type with outstretched arms. But there is no alert system for measuring distance from monitor to eye. The minimum distance is 0.38 m (1.2 ft.) and maximum distance is 1.02 m (3.3 ft.). It can be achieved by using artificial intelligence. We can use web camera for capturing human head positions and separate the background from foreground head positions. If the distance is minimum to pre-define threshold value means, alert is automatically generated and intimate to users without using any sensors. And also extend the approach to design the parent children framework to send alert at the time of seeing unwanted websites.

Keywords: Online Results, Quotation Paper, Online Attendants,

Abstract: The goal of this paper is to disclose a library of image enhancement and comprehension algorithms that have been developed to improve and recognize surface flaws from remote live imagery of an aircraft surface. Improved remote visual inspection could allow the inspector to undertake the essential visual examination on an aircraft in a safe, timely, and accurate manner. CIMP sends high-resolution, real-time stereoscopic pictures of the aircraft crown to an inspector at a console. The inspector examines the images for surface problems using computer augmentation and intelligence. We will discuss many image enhancing methods as well as an inspector's interface for emphasizing surface cracks, scratches, lightning strikes, and corrosion in live imagery in this paper. Surface-specific image enhancement techniques emphasize image features that are unique to the surface.

Abstract: The world is deal with various kind of datal like social media data, medical data, stock market data, environmental data, scientific data, financial data, Mathematical data .So analyzing and summarizing this data manually is impossible because of incredible increase in data due to daily uses of internet and information sharing . This research investigate the fundamental of data mining, scope of data mining and develop new techniques for assimilate uncertainty management in data mining.

Keywords: Data mining , scientific data ,deal , investigate, assimilate

Abstract: The world is aware of the current scenario, the population is increasing day by day hence number of vehicles are also increasing. Thus, everyone is facing the problem of parking, as there are less options available for legitimate parking. This problem leads to congestion, accidents, lack of space availability etc. Annual survey which is carried out has figured out that there is consistent growth in the ratio of traffic jam and accidents. Illegal parking plays a vital role in increasing the chances of traffic jams for hours. Due to increase in the number of vehicles. Moreover, it is much more time consuming as well. In this world of fast growing technologies, we should be able to save our time for the thing which is essential rather than searching space to park our vehicle. A car user must be able to book car before starting the journey and heading to the destination. The main objective behind developing such applications is to overcome such problems. An application will be developed according to the user point of view, which will be user friendly, so that a user can easily make use of it and could be able to book their parking space. The user will beable to book parking space in advance. Keyword: - Android Application, Smart Parking, Reservation of Parking, and Parking Guidance.

Abstract: In this paper, we present the design and implementation of the Cross Platform game called ZOMBIE SHOOTER. This game get vary from other Zombies game, because the idea of our game is different form others. It is a shooting game and was developed keeping the Android, Windows, and Windows Phone Operating System in mind. The aim of our project is to connect player with more than four guns and hundred percent of health and consumables are provided. The players should rescue two members from the zombie world. It’s like an one man army game. This game can be played in the Android, Windows, and Windows Phone Operating System, it depend upon the game conversion. The game has been designed and implemented and soon will be available on the Google Play Market and Windows Store. The game has been tested on Windows 10 for PC, running Android Lollipop and Redmi Note 7S running Android KitKat. So, it should run on other compatible devices as well.

Keywords: Cross-Platform Plugins, Unity Game Engine, ZOMBIE SHOOTER, Software Development, Android Development, Windows Development.

Abstract: Since the term first coined in 1999 by Kevin Ashton, the web of Things (IoT) has gained significant momentum as a technology to attach physical objects to the web and to facilitate machine-to-human and machine-to-machine communications. Over the past 20 years, IoT has been a lively area of research and development endeavors by many technical and commercial communities. Yet, IoT technology remains not mature and plenty of issues must be addressed. during this paper, we identify 5 key research topics and discuss the research problems and opportunities within these topics.

Keywords: Internet of Things (IOT), Energy Harvesting, Data-Driven IOT, Hydra project4

Abstract: Eye movement can be regarded as a pivotal real-time input medium for human-computer communication, which is especially important for people with physical disability. In order to improve the reliability, mobility, and usability of eye tracking technique in user-computer dialogue, a novel eye control system with integrating both mouse and keyboard functions is proposed in this paper. The proposed system focuses on providing a simple and convenient interactive mode by only using user’s eye. The usage flow of the proposed system is designed to perfectly follow human natural habits. Additionally, a magnifier module is proposed to allow the accurate operation. In the experiment, two interactive tasks with different difficulty (searching article and browsing multimedia web) were done to compare the proposed eye control tool with an existing system. The Technology Acceptance Model (TAM) measures are used to evaluate the perceived effectiveness of our system. It is demonstrated that the proposed system is very effective with regard to usability and interface design. Objective The main objective of the project is to develop a software that useful to all peoples including physical disabilities to access system through eye commands and files (multimedia).and some peoples affected by diseases like Cerebral palsy or Amyotrophic lateral sclerosis(losing control of hands ) also can access system through eye gaze actions and pointes access.

Keywords: Eye Gaze ,TAM(Technology Acceptance Model),Mouse Functions, Eye Tracking.

Abstract: This Paper proposes a global localization system based on Lora technology where the position data is parsed and displayed for the end-user’s consumption. This work provides an alternative ship-tracking system to the existing Automatic Identification System (AIS), A reader installed on the boat measures the received signal strength indication (RSSI). This paper focuses on implementing border identification system for all boats. However, the existing system is not powerful enough to prevent the crime against fishermen as it gives only the information about the border identification but not about the exact distance that the boat has travelled from the border. It provides lesser possibility to know about their location in case of any danger. The proposed system’s transmitter section includes Seismic sensor and Ultrasonic sensor in order to pick up Tsunami seismic signals and Coral reefs respectively, Arduino microcontroller Lora module, APR voice playback circuit, Relays and DC motor and the receiver section includes Master Lora module which is connected to PC as monitoring database in the controlroom of the port. Keywords - Ultrasonic sensor, LoRa, Vibration sensor, UART.

Abstract: Video-based facial recognition has gotten a lot of interest in recent years due to its wide range of applications. Face identification is complicated by the significant diversity of pictures caused by position changes, lighting conditions, facial emotions, and image occlusion. Surveillance and mobile cameras, on the other hand, are low-cost equipment that cause significant motion blur, out-of-focus blur, and a broad range of posture variation, lowering video frame quality. Face recognition from video image processing is achieved using machine learning techniques. Image capture, segmentation, feature extraction, classification, and face detection are all processes in the process. The retrieved characteristics are used to train classifiers for pictures that have been processed. As a result, the most current algorithms produced provide an overview of the state of the art in video facial recognition technology.

Keywords: Face detection, security monitoring, video retrieval, face recognition.

Abstract: A social distancing monitoring robot that measures the distance between disease-spreading persons in order to minimise the spread of Covid. This approach is necessary since banks, government offices, malls, schools, and theatres all have long lines that last for hours every day. To assure social separation in lineups, a social distancing monitoring robot was designed. The robotic vehicle is driven by a robot with a two-wheel design system. It uses a line-following approach to keep up with the queue and keep an eye out for social distance breaches. In order to detect violations, the robotic employs IR sensors to traverse back and forth with the queue. To detect obstructions in the vehicle path, the robot now has an obstacle detecting ultrasonic sensor

Keywords: Smartphone, Automated, Wi-Fi, obstacle, Android robot

Abstract: Diabetes is a chronic illness with the potential to cause a worldwide health catastrophe. Diabetes affects 382 million people globally, according to the International Diabetes Federation. This headcount will have more than tripled to 592 million by 2035. The fundamental purpose of this study is to develop a prediction model based on the medical data provided by diabetic and non-diabetic individuals. The purpose of this study is to create a hybrid model that physicians may use to manage diabetic patients. To begin building the prediction model, key parameters such as Pregnancies, Glucose, Blood Pressure, Skin Thickness, Insulin, BMI, Diabetes Pedigree Function, and Age were selected from the PIMA Indian Diabetes Dataset. The dataset was separated into two parts: training and testing. We then proceeded based on these findings. Following that, we utilised a random forest machine learning system to predict whether the patient will be normal (non-diabetic) or diabetic.

Keywords: Type 2 Diabetes, Machine Learning, Random Forest, Prediction.

Abstract: In the rising edge of technology everyday new technologies have been coming in the market, but with the new technologies it becomes difficult to use the older ones. Image is one of the very important things in day-to-day life as it makes visualizing the things very easy also it become easy to store our memories. But viewing the same image on different devices is not easy as of now every device has different size and aspect ratio and resolution so that image may look different on different device. So, to handle this scene we have to resize our image but the traditional ways of image resizing such as cropping, scaling etc. can lead to loss of important content, distortion of image. To overcome these deficiencies seam carving is the best method to resize the image. It is a retargeting method which considers the images in a semantic manner for resizing to bring them to target aspect ratio. The change in the final resized image is trivial to the human eye and the final image will look very similar to the original one. Also using seam carving image enlarging, object removing is possible.

Keywords: Image retargeting, seam carving, image processing, content-aware image resizing.

Abstract: The online knowledge assessment is a web application which allows and access to conduct a test online to gauge the participant’s learning and mastery over a particular subject. The assessment knowledge is a project developed to provide an easy way to develop student’s skills. This project helps users by analysing the areas where students are weak and allows tests accordingly. This project is developed in php platform. Main aim of this project is to implement a web based portal with education information which will be useful for college students. Online education is one of the fast growing filed on web where users can directly solve problems by visiting website without any help from teachers. This system increases scope of online education and online courses. Online course portal is software developed for student in schools, colleges and institutes to access online course material. The project aims at creating a courses portal for a campus/organization. This allows registered users of the system to join a course available in the site and access the materials published for the course. People can register themselves as students of a course or Faculty for the course. It facilitates to access the information of a particular course. The information is provided by the teacher for a particular course. The purpose of developing software is to computerized the tradition way of taking class

Keywords: Online quiz, Conducting test, Provide certificate

Abstract: Millions of students complete their education each year and go on to do higher studies or a corporate job. In this case student credentials are verified through a lengthy document verification process. This results in significant overhead as documents are transferred between institutions for verification. It is a costly, lengthy, and time-consuming procedure as university authorities invest millions of dollars in maintaining the entire process each year. The employer also takes plenty of time to counterfeiting certificates. A fake certificate generated by skilful scammers is always tough to identify and address as the original one. Therefore, there is a crucial need to upgrade the certification and verification process. This project introduced a Block chain based decentralized Student Verification platform that offers an easy way to issue, check, and verify educational certificates. The student's identity and document are both verified by matching the hashes already present in the Block chain. Also, in the proposed method the documents are linked to the student to another layer of verification. The implementation of this proposed platform can be used to issue, receive and verify the student and their certificates.

Abstract: Cloud computing is an emerging concept combining many fields of computing. The motive of mobile cloud computing is to deliver the services, software and processing capacity over the Internet so far to reduce the computation cost and increase the storage capacity. The goal of this paper is to implement a user authentication algorithm, which can be used in cloud storage to verify the authenticity of the user. In this paper we build a secure mobile cloud-based algorithm, where the user's mobile phone is used as an authentication device, presenting a onetime encrypted password for the user and password is decrypted using proposed algorithm in user's mobile application.

Keywords: IAAS, PAAS, SAAS, Virtual Machine, Cloud

Abstract: Internet extensively used in almost all communication applications because of its integrity and availability. Recently, several applications built on the net has evolved to build transmission inherently further authentic and systematic. Many applications, email is popular and dependable means of communication with everyone. Using email is very simple and easy to understand for the average user, but using the system for the visually impaired is still very difficult. The ongoing system is not useful for visually impaired people. This is because the systems available are based on visual perception. . However, the current email system has not yet been upgraded for use by the visually impaired. In this regard, there is a need to modernize existing systems to make this system most practical for nearly blind people . Therefore, this paper, we commenced the Voice Activated E-mail System to provide simple and easy approach to the E-mail System for people with visual impairments. The rescue will also benefit people with other disabilities, along with blind people.

Abstract: A distributed AI-Powered system that can help security personnel detect various types of weapons in real time. The deep learning architecture interfaces uses single shot detection to allow users to interact with the threat detector system conveniently at the camera and cloud sides. A motion detection module is proposed for detecting moving objects in surveillance videos in real - time. The developed module is integrated seamlessly with both the camera and cloud sides. Security is always a main concern in every domain, due to a rise in crime rate in a crowded event or suspicious lonely areas. Abnormal detection and monitoring have major applications of computer vision to tackle various problems. Due to growing demand in the protection of safety, security and personal properties, needs and deployment of video surveillance systems can recognize and interpret the scene and anomaly events play a vital role in intelligence monitoring. This project implements automatic weapon detection using a convolution neural network (CNN) using Alexnet. Proposed implementation uses datasets, which had pre-labelled images. Results are tabulated, achieve good accuracy, but their application in real situations can be based on the trade-off between speed and accuracy.

Keywords: AI power system, image processing, MatLab, M-files . CNN

Abstract: Big data and its analysis are within the focus of current era of massive data. The most production sources of huge data are social media like Facebook, twitter, emails, mobile applications and also the migration of manual to automatic of virtually every entity. Currently, there’s a requirement to research and process complex and big sets of information-rich data in all told fields. This paper provides a survey of massive data issues and also the effectual and efficient platforms and technologies which are needed to deal and process the remarkable amount of knowledge. It turns around two major areas namely: clustering and scheduling.

Keywords: Include Big Data Issues, Clustering, Scheduling, Analysing Data.

Abstract: Autonomous vehicles using Artificial Intelligence (AI) technologies requires various sensors such as radars, lidar, ultrasonic, etc. to have the human visual perception in monitoring the road. Wide angle camera is often used for better coverage and experience for view. Those sensors generate massive amount of data that could be processed with the cloud computing through the wireless communication. The cloud computing may not be a feasible solution, as for real- time detection systems. In this work, we examine the implementation of the deep-learning and real-time object detection on the edge devices that is connected to the wide-angle camera. This system can achieve real-time object detection with a latency of less than 0.2 ms. This model also helps to mitigate the distortion that is introduced by the wide-angle camera. Detection system will be able to warn user of his or her surrounding road conditions.

Keywords: Artificial Intelligence, Deep-Learning, Edge Computing, Real-time Object Detection.

Abstract: Our mission in the city is to decrease the crime and increase the trust about the police by the online crime reporting system to engage public, The NGOs, government and police agencies should be proactive and responsive to combat with the criminals and crime. The aim of the artificial intelligence (AI) is to realization the dialogue between human beings and machines. In the present years the structure of the dialogue are called interactive conversational system this system is faster in developing the area in AI. The dialogue system has been used by many companies for establishing virtual personal assistants of various kinds based on their application and areas, for such as Amazon Alexa, Google Assistant, Microsoft’s Cortana ,Apple’s Siri, and Facebook’s M. In this proposal we have used multi-modal dialogue system with to are more combined user input modes such as image recognition speech recognition. The smart virtual assistance plays a vital role for launching the FIR with speech to the text conversion after analyzing the compliant apply appropriate laws with the unique identification (UID) for serious offense. As well as we are also providing online web application for registration non-serious offense complaint. For the communication between police and public which improve usage of time for solving crime by this not lot time is wasted to speak with police.

Keywords: Law text classification, semi supervised learning, World association mining, Sentimental Analysis, Neural Network

Abstract: The study was carried out to compare the usability of fisheye, linear and tree menus on a web based interfaces. Usability concept has been under focus over the years and has evolved with different definitions by researchers. The usability of four Web page layouts were compared: the web pages comprise of tree menu and linear menu of which a fisheye effect was applied to each of the two menu types to make four menus, (tree menu, fisheye tree menu, linear menu, fisheye linear menu). Seventy three (73) participants partake in the experiment. The time to complete tasks for each of the four menu types were measured. There were no significant differences observed in completion times between the two test conditions. This research questions the current leading Web design thought that menus with the fisheye effect may perform faster. However, it was concluded that some participants commented on fisheye linear menu and fisheye tree menu that they are nice and looked attractive although the selection time was not faster than the linear and tree menu.

Keywords: Computer Menu, fisheye Menu, linear Menu, Tree Menu, usability.

Abstract: An Artificial Neural Network (ANN) is additionally a science paradigm that’s inspired by the way biological system, rather a touch just like the brain, process information. The key element of this paradigm is that the novel structure of the knowledge processing system. ANN’s like people, learn by example. An ANN is configured for a particular application, like pattern recognition or data classification, through a learning process. It’s composed of an out of doors number of highly interconnected processing element working in unison solve specific problems. Learning in biological system involves adjustment to the synaptic connections that exist between the neurons. This could be true of ANNs also. This paper gives overview of Artificial Neural Network, working & training of ANN. It also explain the applying and advantages of ANN.

Keywords: Artificial Neural Network (ANN), Artificial Neuron, Biological Paradigm, Pattern Recognition, Feedback Network, Feed Forward Network.

Abstract: Generation has been evolving constantly and it is making our lives simple. With a quick-paced life all people these days is harnessing the advantages of generation besides some components of the society. One of the visual disease due to several other diseases are Diabetic Retinopathy, Cataracts, Glaucoma, etc. Diabetic Retinopathy (DR) is a typical complexity of the diabetes which is in-line with the retinal vascular damage which is brought by long standing Diabetics. Diabetic Retinopathy is a condition which relates to increased glucose level in blood. As there is increase in glucose levels, the veins in the retina changes. As glucose level increases, the person may start to lose his/her vision, leading to Diabetic Retinopathy. It is usually seen in moderately aged and older persons. In this paper, we use Fundus eye images and those features are extracted using a technique called Image Processing technique. These images are trained, tested and the severity of the disease is seen using K-Nearest Neighbor (KNN) algorithm.

Abstract: In India, 73% of rural people depends on the agricultures and forests. Due to forest fire issues and diseases caused by insects and pests in fields, they have faced heavy loss and it also reduces the crops productivity. In order to enhance the crop quality chemical fertilizers and pesticides are used to kill the pests and insects. According to the research of World Health Organization (WHO) about a million of people are ill affected by manually spraying the pesticides and fertilizers to the crop, to reduce these threats and huge losses to ecosystems. To overcome this problem the Unmanned Aerial Vehicle (UAV) aircrafts can be used to detect the fire at the early stage and to spray the chemical pesticides and fertilizers in order to avoid the health issues for people who are involved in spraying manually. Also, we have many developments in agriculture for increasing the production of crop using drone. The agriculture UAV drone used to expand the all areas of field which the drone will be able to cover it and the drones are highly capable, and also includes fertilizer and pesticides spraying, seed sowing, mapping etc. The market for agriculture UAV drones is expected to grow continuously by relating the technologies.

Keywords: UAV, Flame Detector Sensor, Artificial Intelligence, Smart Farming, IoT.

Abstract: The term "air pollution" generally is the process of releasing pollutants into the air which can be harmful to the health of humans and the environment in general. It is one of the greatest challenges humanities has have ever had to face. It can cause harm to crop, animals, and forests, among others. To stop this from happening in the transport sector, it is necessary to identify air quality issues caused by pollution using machine learning techniques. Therefore, air quality assessment and prediction are now an important area of research. The objective is to explore methods based on machine learning to achieve forecasting the air quality of air using predictions that have the highest accuracy. Analysis of data by a supervised machine-learning technique (SMLT) to collect a variety of data points such as, variables identification, univariate analysis bi-variate and multi-variate analyses as well as missing value treatment and examine the data validation as well as data cleaning/preparing, and visualization will be carried out for the entire data set. The analysis we present gives an entire guideline for the analysis of the sensitivity of model parameters with respect to their performance in predicting levels of pollution in the air by accuracy calculations. The aim of this paper is to propose a machine-learning-based method for accurately predicting an accurate Air Quality Index value by predictions in the form of highest accuracy by the comparison of supervised classification machine learning algorithms. Furthermore, to evaluate and analyse the effectiveness of different machine learning algorithms based on the transportation traffic department data with an evaluation classification reports, to identify the confusion matrix, and then categorizing the data according to priority. the outcome shows the efficiency of the proposed machine-learning algorithm method can be evaluated with most accuracy, precision, recall as well as F1 Score.

Keywords: Air Pollution, Air Quality Index, Machine Learning Algorithms, Decision Tree, Support Vector Machine.

Abstract: As industrialization and urbanization grow to be a concern in food production and scarcity, urban farming was introduced to cope with the above conditions. aquaponics, where plants and aquatic animals were grown together for a better outcome, was considered as one of the effective types of urban farming. as with any method of farming aquaponics came with its own set of cons: so in this paper, we discuss a fully automated aquaponics system (smart aquaponics) with the integration of Internet of things (IoT) Applications to double the outcome of the production more efficiently and sustainably.

Abstract: This study presents a camera vision system that's grounded on Hand movements taken from a camera using a color discovery approach to control the cursor. The technology will allow the stoner to move the computer cursor with their hand, right- click, and execute other conditioning using colorful hand movements. The suggested device consists of a low- resolution camera that serves as a detector and can follow the stoner's hand. Python and OpenCV will be used to make the system. Hand gestures are the most natural and simple manner of communicating. The camera's affair will be shown to the examiner. Hand discovery will be used to acquire information about the gesture's shape and position.

Keywords: Virtual Mouse, Hand Gestures, Image capture, Processing, display frame, masking

Abstract: Handwritten recognition has been one of the most challenging researches. . Major motives consist of the styles, and strokes of the huge variety of handwritings. Handwritten recognition is the cap potential of a pc to acquire and interpret handwritten entries from sources consisting of paper documents, photographs, contact screens, and different devices. Present techniques in the field of Handwritten Text Recognition are Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Ngram, and Long-short Term Memory (LSTM). They predict the handwritten word with good accuracy. Language translation cannot always translate a language 100% because of the slang structure and linguistics. Machine translation techniques are majorly used for language translation to get culturally and linguistically appropriate translations. In our project, we have used CNN and LSTM (BLSTM) for handwritten recognition and For Language recognition, we have used Encoder-Decoder using LSTM. Our main objective is to combine handwritten recognition and language translation to interpret handwritten words appropriately and translate them into one of the native languages in India (Hindi) acquiring good accuracy.

Keywords: Handwritten recognition, IAM dataset, Language Translation

Abstract: One of the most difficult challenges in medical image processing is detecting brain tumours. The challenge is challenging to complete since the photographs have a lot of variety, as brain tumours exist in a variety of shapes and textures. Brain tumours are made up of several types of cells, and the cells can reveal information about the tumor's nature, severity, and rarity. Tumors can appear in a variety of areas, and the location of a tumour can reveal information about the sort of cells that are creating it, which can help with further diagnosis. The process of detecting brain tumours can be made more difficult by issues that can be found in practically all digital images, such as lighting issues. The picture intensities of tumour and non-tumor images can overlap, making it challenging for any model to make accurate predictions from raw images. This research offers a novel method for detecting brain cancers from various brain pictures by using image preprocessing techniques such as histogram equalisation and opening, followed by a convolutional neural network. Apart from the picture preprocessing approaches that have been finalised for training, the study also explores the impact of alternative image preprocessing techniques on our dataset. The experiment was done out on a dataset that included tumours of various shapes, sizes, textures, and locations. For the classification challenge, a Convolutional Neural Network (CNN) was used. CNN achieved a recall of 98.55 percent on the training set and 99.73 percent on the validation set in our research, which is quite impressive.

Keywords: Brain Tumor Detection, Convolutional Neural Networks, Deep Learning, Image Processing, Computer Vision, Computer-aided Diagnosis, Transfer Learning.

Abstract: Cervical cancer, second only to breast cancer, is one of the cancer is a leading cause death among women. Cervical cancer is a cancer that forms in the cells of the cervix, which is the lower section of the uterus that connects the uterus to the pelvis to the vaginal area Various forms of the papilloma virus (HPV), a sexually transmitted infection that plays a role in cervical cancer. Cervical cancer plays a critical part in the majority of cases. The risk of cervical cancer developing can be reduced by undergoing screenings and receiving a vaccination that protects against HPV infection Cancer prevention is important. The majority of the time, this is accomplished by checking the transformation zones. Cervical pre-cancerous stages can be observed in three different types, and all can transfigure into cancer. As a result, it's crucial to screen cervical anomalies sensibly and have a reliable process to determine if a cervix is normal (healthy) or pre-cancerous. Presently, the test being carried is a Pap smear test, commonly referred as a Pap test, which is a cervical screening procedure. It examines your cervix for the presence of pre - cancerous or cancerous cells. The Pap test's main drawback is that like many it cannot ensure reliable results. A misdiagnosis Pap test showed that there are abnormal cells in the cervix when there aren't any. At present times deep learning is becoming more important alternative for cancer screening. A cervical cancer detection and classification system based on CNN has been proposed. Deep-learned features are acquired using the CNNs model. The method has exhibited exceptional performance, demonstrating the proposed method's strength in delivering an effective tool for cervical cancer classification in clinical settings.

Abstract: In today's world, Human Activity Recognition [HAR] plays a critical role in 'human- to-human' interaction. HAR displays and provides the identification of a human as well as the action done by that human, which is tough to recognize. Due to the high processing time, deep learning techniques such as CNN and LSTM cannot be used, instead we will apply transfer learning to recognize human activities. For many computer vision-based applications, such as video surveillance, criminal investigations, and sports applications, human action recognition is one of the difficult issues. Using the similarities between each pair of frames, each extracted sub-unit is further separated into frames that represent action. We will detect the action by comparing the generated HOG to the existing HOGs in the training phase, which represents all the HOGs of many actions using a dataset, utilising the Histogram of the Oriented Gradient (HOG) of the Temporal Difference Map (TDMap) of the frames.

Abstract: New super resolution approach that uses significant and general information. The training process is performed on the significant parts of the training data set, and the reconstruction process considers significant parts separately then, a super resolution image will be obtained according to each different demand. This concept is easy to understand, Experiments show that our new approach can reduce the testing time and obtain a high-quality reconstructed image. Keyword: Super Resolution, Image Processing, Deep learning, Image resolution

Abstract: The world today is largely dependent on computers; therefore, not being aware of the tricks of this trade is bound to make a person feel left out. Computers changed the world a lot. It helped man step forward into the future. Thanks to computer, exploration came true, new designs of vehicles and other transportation were made; entertainment became more entertaining, medical science made more cures for diseases, etc. the computers impacted our lives in many ways. They did make life a lot easier. Without computers, world would be a harder place to live in. Thanks to the computer, everyday life is easier for us. This project is proposed for people those who are using public transport for daily commuters in Tamil Nadu. Even though the automobile industry has been developed in India still may of the commuters are depend on public transport which is the budget friendly way in metropolitan cities and college students. But in morning time it is difficult to get a ticket in the crowd. Daily we need a proper chance for our transport. Even bus pass renewal also in manual process. This manual process requires man power and consumes more time. Also, user needs to go bus depot on the particular date and time to apply with required details with in due-date. If they fail to appear with in due-date they can’t apply .to avoid such difficulties, this service rectifies those problems. It will help to save their time without standing in a line for hours in counters.

Abstract: The use of machines to perform different tasks is constantly increasing in society. Providing machines with perception can lead them to perform a great variety of tasks; even very complex ones such as elderly care. Machine perception requires that machines understand their environment and the interlocutor's intention.Thus, deep learning has the potential to improve human-machine interaction because its ability to learn features will allow machines to develop perception. And by having perception, machines will potentially provide smoother responses, drastically improving the user experience. The process of creating a textual explanation for a set of photos is known as image captioning. In the Deep Learning arena, it has been a critical and basic endeavor. Image captioning has a wide range of uses. Image captioning is a popular research field in Artificial Intelligence as it combines the 2 major fields in Artificial Intelligence i.e., Deep Learning and Natural Language Processing. This paper presents a model that combines Natural Language Processing modules (Glove Embedding and LSTM) and Deep Learning (Feature extraction from images) to generate a sentence describing an image. The model is combined with a function that generates facts based on the primary feature in the image. Given the training image, the model is trained to maximize the likelihood of the target description sentence. Also, this has been deployed using streamlit, hosted on the web.

Keywords: Deep Learning, Artificial Intelligence, Natural Language Processing, Image Captioning, Streamlit.

Abstract: Generative Adversarial Networks, or GAN for short, is a productive modeling model using in-depth learning methods, such as convolutional neural networks. In recent times, supervised learning with convolutional networks (CNNs) has seen huge adoption in computer vision applications. Comparatively, unsupervised learning with CNNs has received less attention. We introduce a class of CNNs called deep convolutional generative adversarial networks (DCGANs), that have certain constraints, and demonstrate that they are a strong candidate for unsupervised learning. Training on various image datasets, such as anime we show convincing evidence that our deep convolutional adversarial pair learns a hierarchy of representations from both the generator and discriminator. Additionally, we use the learned features for novel tasks - demonstrating their applicability to be used for various purposes such as advertising.

Abstract: The detection of plant leaf is a very important factor to prevent serious outbreak. Automatic detection of plant disease is essential research topic. The commitment of a plant is very imperative for both human life and condition. Plants do experience the ill effects of ailments, similar to people and creatures. There is the quantity of plant maladies that happen and influences the typical development of a plant. These ailments influence finish plant including leaf, stem, organic product, root, and blossom. More often than not when the illness of a plant has not been dealt with, the plant bites the dust or may cause leaves drop, blossoms and organic products drop and so on. Suitable determination of such illnesses is required for precise ID and treatment of plant sicknesses. Plant pathology is the investigation of plant infections, their causes, methodology for controlling and overseeing them. Yet, the current strategy incorporates human inclusion for order and distinguishing proof of maladies. This strategy is tedious and expensive. Programmed division of illnesses from plant leaf pictures utilizing delicate registering approach can be sensibly valuable than the current one. In this paper, we have presented a strategy named as Bacterial searching improvement based Radial Basis Function Neural Network (BRBFNN) for recognizable proof and characterization of plant leaf illnesses naturally. For doling out ideal weight to Radial Basis Function Neural Network (RBFNN) we utilize bacterial searching streamlining (BFO) that further expands the speed and exactness of the system to recognize and arrange the districts tainted of various infections on the plant leafs. The locale developing calculation expands the effectiveness of the system via looking and gathering of seed focuses having regular characteristics for highlight extraction process. To chip away at parasitic maladies like basic rust, cedar apple rust, late scourge, leaf twist, leaf spot, and early curse. The proposed strategy achieves higher precision in recognizable proof and characterization of infections.

Keywords: Cnn,Bfo,Knn, Rbfn, disease prediction

Abstract: Neural Networks (NN) are a subset of Machine Learning that is increasingly being employed in pre-processed image analysis. The CNN (Convolutional Neural Network) algorithm is a common NN technique that outperforms ANN in this project. The existing CNN models are Inception V3, ResNet50, MobileNet, and Xception [1], although they have been proven to be less accurate and time expensive. The H5 model is a new CNN model developed in our Project. A model that was originally created for facial detection and differentiation is currently being utilised to detect all objects with greater accuracy, focusing on five zones with variable pixel intensity scheme. The encouragingly high classification accuracy of our proposal implies that it can efficiently automate Pneumonia Detection in COVID-19 patients from radiograph images to provide a fast and reliable evidence of Pneumonia related COVID-19 infection in the lung that can complement existing COVID-19 diagnostics modalities.

Keywords: H5 Convolutional Neural Network model, Convolution Neural Network (CNN) architecture, COVID-19, Severe Acute Respiratory Syndrome corona virus 2 (SARS cov-2), deep learning based chest radiograph classification (DL-CRC), Tensorflow, Haar Cascade Classifiers, different pixel Intensity scheme, facial detection and distinction.

Abstract: Pothole is a depression in the normal surface of the road. Lack of bond between the bituminous surfacing and the base course below due to improper application of prime coat and track. Larger potholes sometimes cause breath holding accidents and loss of lives as they are not visible at night. Pathetic condition of roads is a boosting factor for traffic congestion and accidents. The driver must manually look for potholes on the road while driving sometimes, the driver encounters many risks such as he will be at a constant speed and suddenly there will be a pothole on the way. At these times, the risks of accidents are more. To ensure road surface quality it should be monitored continuously and repaired as necessary. Thus, we have developed a proposed design using Deep learning. Here, we have used image processing to detect the road potholes. The process is done by proposing an image - processing to detect potholes from satellite images. By using the algorithm mentioned above, the system can detect whether the road has potholes or not. Once the system finds the potholes, the system will send the data to micro controller received on the GPS location and it is sent via mail and SMS.

Keywords: Potholes, Transportation safety, Deep Learning, Image Processing, GPS

Abstract: Questions such as "How to make x-y?" should have answers like "x-y is made how...", even though we only have steps on how to create x in the database. These are called AI Information Retrieval documents. Recommendation engines are a line of ML, usually concerned with steps or assessment of products. In a broad sense, a referral system is a system that guesses the category a user might give to a particular data. RecipeHub is an interface that hosts recipes and allows users to create, maintain, plug in and track new recipes. We explained the information already available to answer the question.

Keywords: Information Retrieval, Ranking, QnA,Bidirectional Encoder, Fuzzy string matching, Bitmap algorithm, Levenshtein distance.

Abstract: Now a days, demand for horticultural crops greater specifically those bearing end result and plants and decorative functions is increasing in both urban and rural regions in India. Heavy call for decorative and flowering vegetation is discovered in the course of festive seasons and seasons of festivals and melas. A nursery is a place where flowers are propagated and grown to a favored age. typically, the flora involved are for gardening, forestry or conservation biology, instead of agriculture. They consist of retail nurseries, which promote to the majority, wholesale nurseries, which sell handiest to companies such as different nurseries and to commercial gardeners, and personal nurseries, which deliver the wishes of institutions or personal estates. Facts from numerous research reviews and different assets, we observed that many persons desired to shop for plant and get in touch with the nursery directly, but lacked specific statistics approximately the plant life. Additionally, on occasion the vendor has not acquired any technical training because of which customers do not get perfect information about particular plant. Ordinarily, customers do no longer examine plant charges with other keep at same spot and at identical time. Customer support could be very essential to us. Our intention is to make every and every client's buying smoother, given that many plant fans are eager to beautify their homes with a ramification of flowers, they need in order to provide that range to get the preferred plant, you need to go to a few nurseries. So, we decided to create a web website for small plant dealers to promote their plant list to our clients on our internet website. This lets in small plant sellers to sell plants to clients whose flora are listed on our platform. Clients also can reconfirm and pass check the same plant charge with different shopkeepers.

Keywords: Online selling, Flower garden, E-commerce, Nursery, Garden Centre.

Abstract: In developing countries like India, the poor people meet their fundamental needs through subsidy provided by the government for basic domestic commodities. The prevailing public distribution structure in Ration shops involves labour intensive measurement of quantity. This current system also requires transaction record maintenance. Numerous difficulties are met through this prevailing system. Some of the major issues are ration distribution to unauthorized card holders, excess time spent by the public in the queue for collecting the ration, involving in the transgressions like hoarding, overcharging and black marketing by the authorities and human interference in transaction updating and ledger maintain process. In order to overcome such issues, Internet of Things based smart card system is proposed in which automatically dispenses the basic commodities to genuine card holders after verifying the card holder details. This system also helps in maintaining the transaction details in a separate database in order to prevent any transgression.

Keywords: Internet of Things, Smart Card System, Biometric System, Raspberry Pi, Android Application.

Abstract: Blockchain is a decentralized ledger that may be used to safely exchange digital currency, make deals, and complete transactions. Each network member has access to the most recent encrypted ledger copy in order to validate a new transaction. The blockchain technology has a number of benefits, including decentralization, trustworthiness, track ability, and immutability. This paper describes the blockchain architecture and explains the concept, characteristics, and importance of blockchain in security, as well as how Bitcoin works and how to improve IoT security. It tries to emphasize the importance of Blockchain in defining the future of cyber security, cryptocurrency, and IoT adoption. This article discusses the importance of blockchain technology in a variety of technological domains, as well as its advantages over traditional systems.

Keywords: Blockchain, Network Security, Bitcoin, Decentralized server, Transactions.

Keywords: Machine Learning, Medical Image Analysis

Abstract: The use of machine learning (ML) in medical image analysis has shown great promise in aiding clinical decision making and improving patient outcomes. The ability of ML algorithms to automatically detect patterns and features in medical images has led to advancements in diagnosis, prognosis, and treatment planning. In this paper, we review the state-of-the-art techniques in ML for medical image analysis, including supervised, unsupervised, and deep learning methods. We discuss the challenges and opportunities in the field, such as data privacy concerns, the need for large annotated datasets, and the interpretability of ML models. We also provide examples of successful applications of ML in medical imaging, such as the detection of tumors in mammograms and the segmentation of brain structures in MRI scans. Finally, we discuss the future directions of ML in medical image analysis, including the integration of multimodal data and the use of reinforcement learning for personalized treatment planning. Overall, ML has the potential to revolutionize medical imaging by providing more accurate and efficient diagnostic tools and improving patient outcomes.

Abstract: Now a days the obtainability of smart Phones, cameras and sensors are highly increased and becomes the important part of our daily life. Due to the usage of these devices huge data is produced and is placed on local platform. Local platforms are not able to perform exhaustive calculations. Cloud services are used for storing huge data that is produced from mobiles, sensors and cameras. Advances in machine learning and computer vision provide huge cloud services with ability of content analysis and many other facilities. But suffers from unwanted privacy risks to users or individuals. In this paper our major focusing point are the privacy preserving techniques we proposed a hybrid framework also feature extractor and classification approaches for machine learning. Noise addition feature is also use to enhance security. Our proposed solution reduced the privacy ricks.