VOLUME 10, ISSUE 12, DECEMBER 2021

Abstract: Coronary Heart Disease is a major cause of death in worldwide. It is also called ischemic heart disease or coronary artery disease. As per as the WHO statistical report is concern, 17.9 million people die every year from CVDs, an estimated 32% of all deaths worldwide, and patients die mainly because of inappropriate and non-affordable treatment. Heart disease is a worldwide health crisis in the present scenario. This disease can be curable with early diagnosis and proper treatment. The purpose of this paper is to establish some predictive models using Machine Learning algorithms by taking a real time CHD dataset. In this paper, we have shown some real-time experiments and observations with the help of some Machine Learning algorithms, and also shown a clear picture on the predictive analysis on medical diagnosis of the Coronary Heart Disease (CHD) using Machine Learning algorithms using which patients may get accurate data so as to diagnose better for their early treatment.

Keywords: Algorithm, Classifier, Coronary Heart Disease, Machine Learning, Prediction.

Abstract: Wireless communication channels are a scarce resource shared among multiple users in either scheduled or randomized fashions. We challenge a few design aspects of the widely used IEEE 802.11 MAC in wireless sensor networks (WSNs), such as the use of RTS, CTS, and ACK handshaking and the binary exponential backoff mechanisms, and argue that these key mechanisms incur high channel overhead and cannot effectively eliminate hidden terminal problems in multihop scenarios. Instead, we propose a set of efficient grid-based channel allocation and access scheduling algorithms using Latin squares, called as GAALS, for scalable WSNs with single-radio multi-channel communication capabilities. Using nodal location information and forming grids over the WSN deployment area, GAALS maps Latin squares to the grids, and dynamically assigns multiple channels to the WSN grids for channel access scheduling purposes. The fairness and scalability of GAALS are analyzed and evaluated in multiflow multihop WSNs with multi-channel capabilities. The results show that GAALS achieves much better performance than other multichannel protocols. key words: Internet-of-things, wireless sensor networks, channel resource allocation, latin squares.

Abstract: Recently, deep learning methods have greatly improved the state-of-the-art in many natural language processing tasks. Previous work shows that the Transformer can capture long-distance relations between words in a sequence. In this paper, we propose a Transformer-based neural model for Chinese word segmentation and part-of-speech tagging. In the model, we present a word boundary-based character embedding method to overcome the character ambiguity problem. After the Transformer layer, BiLSTM-CRF layer is used to generate the best tagging results. Experiments on Chinese Treebank show that our model on Chinese word segmentation and part-of-speech tagging outperforms the baseline model and achieves state-of-the-art performance.

Keywords: Chinese Word Segmentation, POS Tagging, Transformer, Word Boundary-Based Character Embedding

Abstract: Agriculture is an important sector in India. We propose developing a simple ML based project which recommends the best crop to grow, fertilizers to use and the diseases caught by your crops. This work aimed to design and develop a testing or we can call it as suitable crop checker system using ML and data management via a web application.

Keywords: Detection Of Crops, Detection Of Fertilizer, Detection Of Diseases, Agriculture

Abstract: In the present work thick film SnO2 sensor was fabricated on a 1˝x1˝ alumina substrate. It consists of a gas sensitive layer (SnO2) doped with PbO, a pair of electrodes underneath the gas sensing layer serving as a contact pad for sensor. Also a heater element on the backside of the substrate was printed. The sensitivity of sensor has been studied at different temperatures (1500C-3500C) upon exposure to methanol, CO and NO2 vapour and gas and found maximum at 3500C for Methanol. The structural analysis of the film was carried out by X-ray diffraction (XRD) pattern.

Keywords: Gas sensor, nanosized, PbO, SnO2, thick film.

Keywords: Computer Vision, Deep Learning, Semantic Segmentation, 3D-Unet, Satellite Imagery.

Abstract: Digital images are highly manipulated without degrading their visual quality and resolution with advanced and easily available software’s. Copy Move Forgery (CMF) is a common manipulation procedure in digital images that involves copying the object or segment of an image and partially pasting it on another area of the same image. Many block-based detection methods are present to identify the copy move forgery in images. However, their performance got deteriorated considerably under the shape of the regions that cannot be exactly identified, and shows limited robustness based on performance metrics like precision and recall. A novel and robust algorithm is introduced in this paper to overcome that problem. The use of non-overlapping segmentation compared to the overlapping method used is to reduce the computational complexity compared to the regular blocks and irregular blocks to obtain better performance to find the forged region accurately. Here, input images are segmented using the SLIC algorithm, and to detect forgery, the key point features are extracted from each block using the Scale Invariant Feature Transform (SIFT) algorithm along with Speeded Up Robust Feature (SURF). Block matching and labelled feature point matching is used to detect the forgery from these extracted results. Block matching process is used to identify the distance between regions of the divided images. Copy move forgery region is identified by the similarities between the features of the image. Precision, Recall and F-measure of the input image are used to assess the performance of proposed scheme. It is observed that 98.97% precision is achieved with the SLIC algorithm on the MICC-F220 database.

Keywords: Image forgery, Copy-move, SLIC, SIFT, SURF, LPF

Abstract: According to the World Health Organization, around 1.5 million people worldwide died due to diabetes in 2019. It is estimated that approximately 462 million people live with diabetes around the globe. According to other sources, about 432 million people worldwide have diabetes, the bulk living in low-and middle-income countries, and 1.5 million deaths are directly related to the disease diabetes annually. The amount of cases, morbidity and mortality rates in a specific time period or over time to time, the diabetes is steadily increasing over the past few decades. No doubt, Diabetes mellitus is a leading cause of deaths world wide and reduced life expectancy. This disease can be curable with early diagnosis and proper treatment. The purpose of this paper is to establish some predictive models using Machine Learning algorithms by taking a real time Diabetes mellitus dataset. In this paper, we have shown some real-time experiments and observations with the help of some Machine Learning algorithms, and also shown a clear picture on the predictive analysis for the detection of the disease Diabetes mellitus in medical science using Machine Learning algorithms using which patients may get accurate data so as to diagnose better for their early treatment.

Keywords: Algorithm, Classifier, Diabetes Mellitus, Machine Learning, Prediction.

Abstract: India with nearly two lakh cases is estimated to possess the second highest number of patients with haemophilia, a lifelong bleeding disorder that forestalls blood from clotting. Hemophilia-A affects 1 in 5,000 male births within the U.S., and approximately 400 babies are born with hemophilia annually. Around 4 lakh people worldwide live with hemophilia. Hemophilia occurs in about 1 of each 5,000 male births. Supported recent study that used data collected on patients receiving care in federally funded hemophilia treatment centers during the amount 2012-2018, about 20,000 as many as 33,000 males within the us live with the disorder. It is very difficult to cure this kind of disease but can be handle with early diagnosis and proper treatment. The purpose of this paper is to establish some predictive models using Machine Learning algorithms by taking a real time Haemophilia dataset. In this paper, we have shown some real-time experiments and observations with the help of some Machine Learning algorithms, and also shown a clear picture on the predictive analysis on medical diagnosis of the Haemophilia using Machine Learning algorithms using which patients may get accurate data so as to diagnose better for their early treatment.

Keywords: Algorithm, Classifier, Haemophilia, Machine Learning, Prediction.

Abstract: The project “Centralization online portal for head of the department.” help to head of the department to list out all the information of departments including students details & performance and staff details & performance. Head of the department have the privileges to assign and remove class-in charge, and also attendance in charges. The project implements RDBMS (stored in multiple tables) and normalization with primary, the projects run in Cloud Linux server for using lakh’s users with centralization of data. The projects run’s in both online and offline mode, no additional software to be installed in client systems, runs in any type of browsers. This is a web-oriented application allows us to access the whole information about the college, staffs, students, facilities etc. This application provides a virtual tour of Campus. Here we will get the latest information about the students and staffs. This generic application designed for assisting the students of an institute regarding information on the courses, subjects, classes, assignments, grades and timetable. It also provides support that a faculty can also check about his daily schedule, can upload assignments, and notices to the students.

Abstract: In the past decade plenty of analysis has gone into Automatic Speech feeling Recognition (SER). The first objective of SER is to boost man-machine interface. It also can be accustomed monitor the psychotic state of an individual in lie detectors. In recent time, speech feeling recognition conjointly finds its applications in drugs and forensics. During this paper seven emotions square measure recognized mistreatment pitch and prosody options. Majority of the speech options utilized in this work square measure in time domain. Support Vector Machine (SVM) classifier has been used for classifying the emotions. Berlin emotional info is chosen for the task. A decent recognition rate of 81 was obtained. The paper that was thought of because the reference for our work recognized four emotions and obtained a recognition rate of 94.2%. The reference paper conjointly used hybrid classifier so increasing complexes however will solely acknowledge four emotions.

Keywords: Speech Emotion Recognition, Machine Learning, IoT Automation, Graphical User Interface

Abstract: In this work, we endeavor to take care of the Hit Song Science issue, which plans to foresee which melodies will become diagram besting hits. We develop a dataset with around 1.8 million hit and non-hit tunes and removed their sound elements utilizing the Spotify Web API. We test four models on our dataset. Our best model was arbitrary woods, which had the option to anticipate Billboard melody accomplishment with 88% exactness. In the current review, we moved toward the Hit Song Science issue, planning to anticipate which tunes will become Billboard Hot 100 hits. We grouped a dataset of roughly 4,000 hit and non-hit tunes and extricated every tunes sound highlights from the Spotify Web API. We had the option to anticipate the Billboard accomplishment of a tune with around 75% precision on the approval set, utilizing four AI calculations. The best calculations were Support vector machine, Logistic Regression and a Deep learning.

Keywords: Machine Learning ,Hit Song Science ,Classification ,Data Mining, Data Collection

Abstract: The purpose of the doctoral study was to find out the differences of personality and of elite level Cricket and Football playersTwo groups were targeted . The 100 Cricket and 100 Football players participated in the study and their age ranged between 18-28 years. The players divided into two age categories between 18-22 and 23-28. The data was collected through questionnaires of 100 Cricket and 100 Football players . The instruction was given by the investigator to the students before filling these questionnaires. To measure competition related anxiety of the players Sport Competition Anxiety Test (SCAT, developed by Rainer Martens in 1977) was used.No significant difference was found out in Anxiety of Cricket and Football Players. no significant difference was found out in Anxiety of Age group ( 18-22) Cricket and Football Players and insignificant difference was found out in Anxiety of Age group ( 23-28) Cricket and Football Players

Abstract: Usually data is quantitative, and the goal is to show it in diagrams, graphically, etc. One of the main ways to create understanding is to make comparisons between data. At its core, data perception is a way of communicating and making sense of information. The novel coronavirus (COVID-19) that was discovered first near the end of 2019 has impacted nearly every factor of existence as we know it. This paper specializes in the occurrence of the virus in India. As people facing a global health crisis that is a major challenge, we look forward to accounting and information that can help us understand what's going on. Visual storytelling is an important skill across the field. We should focus on visual media more now than ever before. We must position our emotions collectively so that we will all be part of the solution, by conveying stories that might be realistic, precise, and genuine. This is why we see the popularity of graphs that compare COVID-19 pandemic data from different states of India. Apart from communication, data Visualisation also plays a role in helping people change their behavior. Once the virus has spread, public health officials need to make critical decisions about how and when to talk. One of the most important things to do is to make sure that people change their behavior if it is not clear what they need to do now. Viewing data was very important for communication and persuasion. We aim to use the inseparable relationship between people and the internet to create a sound understanding of the covid-19 crisis around the world and display it on a website in a sequential form.

Keywords: covid-19, Pandemic, Population, Data, storytelling, Pollution, Visualisation, Internet, Graphically, Website.

Abstract: The phenomenon of Fake news is experiencing a rapid and growing progress with the evolution of the means of communication and Social media. Fake news detection is an emerging research area which is gaining big interest. It faces however some challenges due to the limited resources such as datasets and processing and analysing techniques.In this work, we propose a system for Fake news detection that uses machine learning techniques. We used term frequency-inverse document frequency (TF-IDF) of bag of words and n-grams as feature extraction technique, and Support Vector Machine (SVM) as a classifier. We propose also a dataset of fake and true news to train the proposed system. Obtained results show the efficiency of the system.Index Terms—Fake news, Social media, Web Mining, Machine Learning, Support Vector Machine, TF-IDF.

Abstract: COVID-19 outbreak was first reported in Wuhan, China and has spread to more than 50 countries. WHO declared COVID-19 as a Public Health Emergency of International Concern (PHEIC) on 30January 2020. Naturally, a rising infectious disease involves fast spreading; endangering the health of large numbers of people, and thus requires immediate actions to prevent the disease at the community level. Therefore, Corona Tracker was born as the online platform that provides latest and reliable news development, as well as statistics and analysis on COVID-19 cases. This research paper is written as a project and aims to predict and forecast COVID-19 cases, deaths, and recoveries through an online platform. The model helps to interpret data according to the country wise and as per the date user want to access the data, through charts and on a geographical map on which data of COVID-19 is illustrated. This model will also provide the COVID-19 vaccination details as well as the emergency numbers as per the user location in case if there is a worse health situation. The WHO advice as well as prevention and symptoms of COVID-19 diseases will also be there as an extra information to the users.

Abstract: Nowadays we suffer from distraction and difficulty in the learning process. We focus on problems that some people face in the process of learning. We propose a new learning system based on Augmented Reality that overlays digital objects on top of physical cards/pages captured through camera and rendering them as a 3D object with text-note with information about that object on the mobile devices. We can also provide phrases and sounds related to the object which will improve the learning abilities to make it more interactive and enhanced. We aim to use the inseparable relationship between students and their mobile phones to create new options for education, converting their smartphones into study buddies.

Keywords: Augmented Reality, Education, Learning, Marker-based Augmented Reality, Mobile Device, Android Application, Object Rendering, 3D Objects.

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

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

Abstract: The evolution in the advanced technologies like mobile phones, different wireless and also web technologies given raise to the new applicability that will help to make the voting system easy and efficient. The E¬-voting promises the possibility of serviceable, easy and safe way to capture and count the votes in an election. This research project provides the specification and requirements for E-Voting using web-based platform. The e-voting means the voting procedure in election by using electronic device. This system provides extra security to voter, along with electoral voting card voter must scan his face and thumb for voting in government site.

Keywords: Face and Finger-print, Voting

Abstract: The aim of the research was to determine the effects of physical fitness training programmes on Happiness and Kindness aspect of volleyball players. Only one group was targeted experimental group, there was no control group. The 30 male volleyball players participated in the study and their age ranged between 19-30 years. Training was given to the experimental groups. The data was collected through respondents in the form of different experimental tests. A training program was planned for 12 weeks, 5 days a week and 90 minutes a day. Exercise that use large muscles groups that can be maintained continuously and are aerobic in nature. These exercises include walking, running, jogging, climbing, jumping row and cross country. The result reveals that there was significant effects of Physical fitness training programme was found in Happiness and Kindness aspect on Volleyball players. Key Words: Happiness , Kindness, volleyball, Physical fitness

Abstract: Agriculture plays a predominant role in the economic growth and development of the country. The major and serious setback in the crop productivity is that the farmers do not choose the right crop for cultivation due to lack of information of soil contents and environmental factors. In order to improve the crop productivity, a crop recommendation system is to be developed that uses the classification techniques of machine learning. Agricultural domain has imbibed the machine-learning algorithm to produce efficient, effective solutions to the difficulties faced by the farmers. Some problems that identified in already implemented systems is that they concentrated on a single parameter (either weather or soil) for predicting the suitability of crop growth. However, in our opinion, both these factors should be taken together into consideration for the best and most accurate prediction for the crops. This is because, a particular soil type may be fit for supporting one type of crop, but if the weather conditions of the regions are not suitable for that crop type, then the yield will suffer. Similarly, there may be a case where the weather conditions are favorable but soil characteristics are not matching and, in some cases, farmers may face surplus problem if all the farmers from the region will grow the same crop. To eliminate the above-mentioned drawbacks, we have proposed the system which provides a solution for Smart Agriculture by monitoring the agricultural field which can assist the farmers in increasing productivity to a great extent. We have proposed the system in the form of a website. The system integrated into two techniques. For the first technique, we have made use of 'Crop Features Data Set’, This dataset encompasses rainfall, temperature, soil PH and humidity for particular crop and predicting crop using random forest classifier. For suggestions of crops soil type is vital factor, system is capable to predict soil type using teachable machine technique. To recommend the best crop system considered some other parameters like environmental characteristics, rainfall, soil characteristics (N, P, K, type), location, season etc. so by considering these parameters system provides farmers variety of options of crops that can be cultivated. For appropriate choice of crop user can see the previous prices of crop. Thus, our proposed system would help the farmers to make the right choice of crop suitability.

Keywords: Machine Learning, Random Forest, Teachable Machine, Crop Recommendation.

Abstract: Healthcare is an inescapable task to be done in human life. Cardiovascular disease is a broad category for a range of diseases that are affecting the heart and blood vessels. The early methods of forecasting cardiovascular diseases helped in making decisions about the changes to have occurred in high-risk patients which resulted in the reduction of their risks [5]. The health care industry contains lots of medical data, therefore machine learning algorithms are required to make decisions effectively in the prediction of heart diseases [4]. Recent research has delved into uniting these techniques to provide hybrid machine learning algorithms [5]. In the proposed research, data pre-processing uses techniques like the removal of noisy data, removal of missing data, filling default values if applicable, and classification of attributes for prediction [5] and decision making at different levels. The performance of the diagnosis model is obtained by using methods like classification, accuracy, sensitivity, and specificity analysis [5]. This project proposes a prediction model to predict whether people have heart disease or not and to provide awareness or diagnosis on the same [1]. This is done by comparing the accuracies of applying rules to the individual results of Support Vector Machine, KNN classifier, Decision Tree Classifiers, and logistic regression on the dataset [1] taken to present an accurate model of predicting cardiovascular disease.

Keywords: Heart Diseases; Machine Learning; Support Vector Machines; Decision Tree Classifier; KNN Classifier; Logistic Regression; Model Interpretation.

Abstract: This paper proposes a system that is used for sound level monitoring. The system is totally based on Internet of Things (IoT) highly desirable in the sound pollution control field. In this system, one can detect the level of pollution (Sound) time by time. Also, the realization of the "Smart City" concept is done via this project. The overall design, objectives, performance, and characteristics of the sensing system for continuous measuring sound are discussed.

Keywords: Sound level, Sound level monitoring, Pollution, IoT

Abstract: - The search, collection, analysis, and use of information from open sources, as well as the methodologies and tools used, is referred to as open-source intelligence (OSINT). OSINT arose from a military requirement to acquire relevant and publicly available data. Since its inception, several studies have been conducted suggesting and creating new ways to use OSINT in various situations. SINT Spider attempts to combine the most common and necessary OSINT techniques into one nice convenient package. It is a great toolkit for anyone who does any penetration testing, or just wants a head start on their exploitation. The tool is still in its early stages, however it does everything it sets out to do minus any GUI makers. You can use the toolkit on any system with the necessary dependencies and requirements to install and run the packages. In addition, I would recommend creating your own scripts and adding things on top of this toolkit if you plan to use it in every attack. This is the toolkit to use if you are a newer pen tester and want to get into information gathering and learn new techniques for information gathering. It also provides a reference if you need to run one of these tools outside of Kali (which is sometimes necessary). The tool will be built on a framework which will merge tools with a common command line interface. Each tool will play a role in reducing the effort required to run multiple tools. The initial plan is to merge the following tools - Reverse Image Search - Email Hunting - Username Hunting - IP Tracing Key-words: - Pap smear, Debris, Poisson noise, Image Processing

Abstract: The anomaly detection system gives a solution to detect anomaly in crowd event video and sets alarm for public safety in mass gatherings. This paper presents a novel framework to represent video data by a set of general features, which are inferred automatically from a long video footage through a deep learning approach. Specifically, a deep neural network composed of a stack of convolutional autoencoders was used to process video frames in an unsupervised manner that captured spatial structures in the data, which, grouped together, compose the video representation. Then, this representation is fed into a stack of convolutional temporal autoencoders to learn the regular temporal patterns. Our proposed method is domain free (i.e., not related to any specific task, no domain expert required), does not require any additional human effort, and can be easily applied to different scenes. To prove the effectiveness of the proposed method we apply the method to real-world datasets and show that our method consistently outperforms similar methods while maintaining a short running time.

Keywords: Anomaly Detection; Convolutional Autoencoders, Deep Learning Technique; Convolutional Neural Network (CNN).

Abstract: A method for real monitoring of the heart for depression episodes is described here. We have developed a convolutional neural network (CNN) based machine learning algorithm for classifying into depression episodes of the heart with an accuracy over 92%. Our algorithm is capable of detecting depression episodes of varying duration. The algorithm is evaluated using Database. The best results obtained here are 0.95%, 0.98%, and 0.91% respectively for accuracy, sensitivity, and specificity.

Keywords: CNN, image preprocessing, depression, Depression Detection.

Abstract: In day to day life social networking sites has become one of the most important part of our life. Social networking sites have a large number of users across the world. This public social networking systems have meet communication demand of the student, but there is lack assistance to get connected to the users learning, working, professional life and cultural life on campus with their real activities. In this paper the design of a new social networking site for college is made, it will be available for college students and faculty only. This social networking site is connected with the environment of college and users real activity. It will cover the function of basic communication as well as it will also serve a unique teaching, learning platform and manage several other aspects of cultural life to students and teachers in college.

Abstract: Medication adherence usually refers to whether patients take their medications as prescribed (eg, twice daily), as well as whether they continue to take a prescribed medication. Medication non adherence is a growing concern to clinicians, healthcare systems, and other stakeholders (e.g., payers) because of mounting evidence that it is prevalent and associated with adverse outcomes and higher costs of care. Engaging patients and the healthcare team is essential to success in achieving medical adherence and persistence. Notable interventions include face-to-face counseling, reminders, regimen simplification, providing cost incentives or savings, and maintaining ongoing communication. This paper provides a review on current challenges faced in medication adherence. The current work aims to design an application that improves medical adherence by reading medical prescriptions of patient from prescription image, searching and extracting the information of the medicine from World Wide Web and providing the information, reminders to patient at regular intervals. The application also uses rewarding techniques to encourage the patient to medical adherence.

Keywords: Primary Non Adherence, Secondary Non Adherence, Intentional Non Adherence, Unintentional non-adherence, Google ML Kit, HCI (Human Computer Interaction)

Abstract:

Abstract: Service Oriented Architecture (SOA) is the latest popular paradigm for system integration and interoperation which revolutionized the distribution of applications over World Wide Web. A web service is the current technology used by SOA in the field of business processes. Where the services offered by the organization are overseen through the system called Change Management Framework (CMF). By this system any progressions for the Services offered by the Organization can be included, adjusted or supplanted as the service request offered by either the client or different business parties, hence it is useful for the organization to create itself by fulfilling the client necessities in a self-sufficient way. In order to offer value added service to the customer we need to integrate the different services. While integrating the various services we should be concise in business policy of on organization. In the event that the business policy is violated while integrating the services it will be precluded in the centre from securing the exchange. In this paper, we have displayed a strategy for distinguishing the business policy violation with Total Turing Machine (TTM). Keyword: - Service Oriented Architecture, Service Integration, Change Management Framework (CMF), Business Policy Violations, Total Turing Machine.

Abstract: It’s very difficult to find the solution of Inverse Kinematics (IK) by using the conventional method. The main problem in solving the inverse kinematics by using older method is that it gives multiple solution. Many problems are continuous in the real world and finding the global solutions is difficult. Optimization is one of that solution. In this paper the different optimization techniques are discussed for trajectory planning and the obstacle avoidance for different DOF robot. With the help of different optimization techniques, the artificial robots are made. The capabilities of artificial intelligence techniques are explored in order to find the optimal solution without using much complex mathematics while using this technique. Here forward and inverse kinematics problems, position and joint displacement errors, velocity, acceleration and time are the main variables to be considered for optimization.

Keywords: kinematics, Robotics arm, robotics manipulator, optimization

Abstract: India is a farming country, more than 70% of our people rely on agriculture. A third of our domestic revenue comes from farming. The farmers face failure because of different cultivable diseases, and farmers are reluctant to keep an eye on their crops when the region is enormous (acres). In agriculture, the diagnosis of plant diseases thus plays an important part. In order to achieve loss caused due to crop diseases which adversely affect crop quality and yield, timely and exact identification of diseases is necessary. Early identification and intervention will mitigate plant disease loss and excessive use of medicinal products. Previously, image recognition automatically detected plant disease. We propose machine learning mechanisms and image recognition methods for the identification and classification of diseases. Crop disease is detected in different processing phases including the collection of images, image pre- processing and the retrieval of images & classification of features. And also send Fertilizers as the output. We can use global image extraction techniques for the extraction of image features. Keyword: - Deep Learning, Global Features, Classification, Image Processing.

Abstract: Machine learning is the field, that enables us to predict the outcomes based on past experiences. It has made many updating like one; is of storage capacity and also the processing powers of the computers. Nowadays machine learning techniques are mostly used for biometrics like fingerprint scanning, Eyes detection, etc. It will focus on what is meant by machine learning, the history of ML, then the focus is on some of the commonly used terms of ML, and then point out the types, then focus on ML process and at last differentiate types of Machine Learning in tabular format.

Keywords: Machine Learning, Supervised, Unsupervised, Reinforcement, Checkers, Linear Regression, Logistic Regression, Perceptron.

Abstract: Cloud computing is emerging as a new paradigm of large-scale distributed computing. In order to utilize the power of cloud computing completely, we need an efficient task scheduling algorithm. The Min-Min algorithm is a simple, efficient algorithm that produces a better schedule that minimizes the total completion time of tasks than other algorithms in the literature. However the biggest drawback of it is load imbalanced, which is one of the central issues for cloud providers. In this paper, an improved load balanced algorithm is introduced on the ground of Min-Min algorithm in order to reduce the makespan and increase the resource utilization (LBIMM). At the same time, Cloud providers offer computer resources to users on a pay-per-use base. In order to accommodate the demands of different users, they may offer different levels of quality for services. Then the cost per resource unit depends on the services selected by the user. In return, the user receives guarantees regarding the provided resources. Keywords- Cloud computing, Load Balancing Algorithm, Min-min Algorithm,

Abstract: Title: Use of RFID technology in students ID cards The tags (or students ID card) contain electronically stored information. These tags are powered by and read at short ranges (few meters) via magnetic fields (electromagnetic induction), and then act as a passive transponder to emit microwaves or UHF radio waves (i.e., electromagnetic radiation at high frequencies). Others use a local power source such as a battery, and may operate at hundreds of meters. Unlike a bar code, the tag does not necessarily need to be within line of sight of the reader, and may be embedded in the tracked object. These tags can be used to gain access for transport, attendance, hostel, etc. The biggest advantage of RFID is that it is contactless and safe technology which is very much required in today’s times. There a growing concern to the management officials of any education institute to implement a secured efficient and accurate tracking mechanism for their student’s .These tags will allow them to have a single card that will hold all the information of a particular student and ease their work.

Keywords: - RFID (Radio frequency identification); RFID Reader; RFID Tags; ARM7 controller; GSM and Student Attendance system.

Abstract: Nowadays, due to pandemic, many schools or colleges have switched to remote class via video conferencing. For this situation, a video conference with higher features are to be implemented.In this survey the approach to improve video conference are discussed here.

Keywords: Video Conference, Hand gesture recognition, Air-writing

Abstract: In India, Agriculture is undoubtedly the backbone of the nation. India, is the second-largest producer of agricultural products in the world, produces more than 280 million tonnes, contributing to more than 15% of India’s GDP. Today, about 40% of the projected total yield is lost due to lack of proper care. Decline in the agricultural yield results increased commodity prices, slowing productivity and so on. Smart agricultural techniques using machine learning and deep learning, can help farmers to boost the crop yield and productivity. This paper explores various techniques for the implementation of smart agriculture.

Keywords: Smart Farming, Agriculture, Deep Learning, Machine Learning, CNN.

Abstract: self-attentionFire mode of transportation is a mode of transportation that can overcome traffic jams The mode of transportation in Indonesia is managed by PT Kereta Api Indonesia (KAI). From day PT KAI always improves services to the community. To know how much people comment positively and negatively, a sentiment analysis is carried out against PT KAI. By retrieving data by scraping from the page Google Play website. The data obtained is data from the Google Play website database which has as many as 600 comments in the form of user reviews of KAI Access. From review KAI Access users are classified using a deep neural network. Expected From the results of this sentiment analysis, it will improve PT KAI's services

Keywords: Sentiment Analysis, CNN, PT KAI, Google play

Abstract: This project is an innovative solution to robotics in health care and more important to the management and control of the spread of coronavirus disease (COVID-19). The main facilities of the robots are delivering food and medicine to minimize person-to-person contact and support in hospitals and similar facilities such as quarantine. This is supportive as well as helps to minimize the life threat to medical staff and doctors to an active role in the management system of the COVID-19 pandemic. The main point of this project is to highlight the importance of medical robotics in general and then to connect its utilization with the multipurpose robot of covid treatment. This is improving smart telemedicine. Which is also effective in similar situations.

Keywords: Medical robotics, Service robots, COVID-19 healthcare digitization, Corona-virus pandemic, COVID-19 Delivery Robots

Abstract: In daily operations related to farming or gardening watering is the most important practice and the most laborintensive task. No matter whichever weather it is, either too hot and dry or too cloudy and wet, you want to be able to control the amount of water that reaches your plants. Modern watering systems could be effectively used to water plants when they need it. But this manual process of watering requires two important aspects to be considered: when and how much to water. In order to replace manual activities and making gardener's work easier, we have create automatic plant watering system. By adding automated plant watering system to the garden or agricultural field, you will help all of the plants reach their fullest potential as well as conserving water. Using sprinklers drip emitters, or a combination of both, we have design a system that is ideal for every plant in the yard. For implementation of automatic plant watering system, we have used combination of sprinkler systems, pipes, and nozzles. In this paper we have used ATmega328 microcontroller. It is programmed to sense moisture level of plants at particular instance of time, if the moisture content is less than specified threshold which is predefined according to particular plant's water need then desired amount of water is supplied till it reaches threshold. Generally, plants need to be watered twice a day, morning and evening. Thus, the microcontroller is programmed to water plants two times per day. System is designed in such a way that it reports its current state as well as remind the user to add water to the tank. All this notifications are made through mobile application. We hope that through this prototype we all can enjoy having plants, without being worried about absent or forgetfulness.

Abstract: Software program-described Networking (SDN) is a rising community Standard that has received significant traction from many researchers. Distributed Denial of provider (DDOS) assaults had been a real threat in lots of aspects of computer networks and disbursed applications. The main objective of a DDOS assault is to bring down the services of a target using a couple of sources which are disbursed there are numerous distributed denials of service (DDOS) attack techniques getting used to degrade the performance or availability of focused services at the net This paper presents different type of DDOS attack and Detection of DDOS attack using SDN

Keywords: Overview of SDN, DDOS Attack Type, Famous attack.

Abstract: Design implementation of SRAM cell based on low power consumption technique. In the field of VLSI research in electronic circuitry and memory is the basic demand of most electronic devices. RAM is used as main memory for small value devices that do not have a cache. Therefore, the construction of memory using an optimized SRAM cell in terms of process parameters, i.e. power consumption, quantity, area and delay, is a domain of VLSI research in electronic circuitry and memory. Critical analysis and the same are present circuit like 10T-SRAM in a functional way high power used but the SRAM-10T was found to have better performance in terms of speed but has a higher access time .These memory components are designed specifically using a CMOS transistor. They talk about CMOS power, the area and speed of each transistor is a big deal, but our proposed design knows are three types of design circuit things like LPCT-RD, LPCT-WD and LPCT. Engineers and researchers are still working on these questions. Various methods have been used to reduce power leakage within the designed circuit. As a circuit analysis processing, using memory capacity in design SRAM cell circuit is reduced power and also performance improves memory works like read, write and power saving better as compare existing circuit 10T. It is using simulation micro wind tool and also computing power, when compared to the results obtained in mode CMOS with micro wind tool. The 10T SRAM bit cell are not reduced power and performance not better the designed 10T SRAM bit cell showed in research study, poor performance, more power utilize of the 10T SRAM bit cell. Proposed design read times, write times access to LPCT-SRAM bit cell intended to increase and decrease volume but low power utilize and other side existing circuit 10T-SRAM model components are low performance. Finally our proposed circuits (LPCT) are reliable and efficient.

Keywords: VLSI, Memory, SRAM, DRAM, Power Consumption, Power Reduction, Power Dissipation, CMOS Technology, Read Delay, Write Delay LPCT.

Abstract: Autism or Autisam Spectrum Disorder is a condition related to brain development. We introduce Android application to indentify the disorder and give proper guidance according to the severity of ASD and aims to improve skill development in child. Our system allows the parent to interact with the child in a flexible manner.

Keywords: Behavior prediction, Skill and ability , chat bot

Abstract: At present,palliative care uses file system instead of data base system.In this scenario,an application with palliative services like chat interface,utilities and other services are carried out.In this survey,services of palliative care services are improved using this application.

Keywords: Chat interface, Utilities

Abstract: The increase in availability and popularity of mobile wireless devices has lead researchers to develop a wide variety of Mobile Ad-hoc Networking (MANET) protocols to exploit the unique communication opportunities presented by these devices. Mobile Ad hoc network (MANET) is a set of two or more nodes that is used for wireless communication and networking capacity. Mobile Ad-hoc Network (MANET) consists of wireless mobile nodes that dynamically form a temporary network without depending on any fixed infrastructure. This research uses the AOMDV routing protocol. In this paper we investigate the range of MANET routing protocols available and discuss the functionalities of several such as Ad-hoc On-demand Distance Vector (AODV), Ad-hoc On-demand Multipath Distance Vector(AOMDV) are proposed.

Keywords: Energy Efficiency,MANET, AOMDV,AODV

Abstract: Nowadays there is a huge increase in the number of road accident. Using this to will help pedestrians, drivers, occupants the traffic sign recognition play an important role. Traffic sign recognition reduce the risk of drivers and it is also benefits for the both drivers and pedestrians. So by adding more feature we can implement more accurate autonomous traffic sign recognition system.

Keywords: Traffic sign Recognition, Convolutional Neural Networks (CNN), Support Vector Machine (SVM)

Abstract: Object detection refers to the capability of computers and other systems to locate objects present in an image and identify each of them. It has been widely used for face detection in security systems, for vehicle detection in driverless cars, and so on. Existing system performs numerous simpler and complex tasks like real world object detection from videos, concealed object detection…etc. This project focuses on detecting tools from a toolkit. Output achieved an accurate result up to the expectation.

Keywords: YOLO model, Comparer, Computer vision, Machine learning.

Abstract: Chronic Kidney Disease (CKD) is a slow diminishing in renal capacity over a time of a while or on the other hand years. Diabetes and hypertension are the most well-known reasons for persistent kidney illness. The manifestations of this infection can't be recognized in the beginning phase. Truth be told, exceptionally lesser individuals know about this infection and can foresee the side effects at the prior stage. With the accessibility of organized clinical information, specialists have drawn in scores to concentrate on clinical illness discovery mechanization with machine learning and data mining. The machine takes in designs from the current dataset, and afterward applies them to an obscure dataset to foresee the result. CKD has been such a field of study for a long while presently. In this manner, the framework means to analyze kidney illness utilizing various machine learning techniques and to choose the best one to evaluate the degree of CKD patients. By utilizing information of CKD patients with 21 attributes and 400 records we use different machine learning methods like DT, SVM, DNN. The attributes are inputted naturally utilizing image processing and letter recognition. To construct a model with the most extreme exactness of anticipating whether or not CKD and in the event that indeed, its Severity.

Keywords: CKD, image processing, machine learning, letter recognition, DT, SVM, DNN

Abstract: Communication is an important aspect of every single individual. We are able to express our ideas and thoughts through communication. But this is not the case with differently abled person i.e. person who cant speak or/and hear. For such differently abled people, a mechanism has to be developed to tackle this communication gap. In this survey, different mechanism and procedures to develop a sign language translator are discussed.

Keywords: Sign language, feature extraction ,translator

Abstract: Computer hardware technology has shown tremendous growth from simple uniprocessor to bigger and faster uniprocessors. In the recent past, these uniprocessors are replaced by multi-processor cores. To match these capabilities, the programming paradigms have also shifted from single-threaded sequential programming to multi-threaded parallel programming. But Legacy systems which were developed primarily to run on uniprocessors were left behind. This paper proposes to transform these applications to run on multi-processors at the same abstraction level (Implementation level) using semi-Automatic techniques. Here the legacy program is analysed based on dependency between functions and its signatures. They are then divided into smaller sub-programs (Parallel threads), which are executed on multi-core machines. The execution time of these restructured legacy programs were analyzed and observed ameliorated efficiency.

Keywords: Parallel threads; Re-engineering; Multicore machines; Slicing

Abstract: A system capable of translating the logical activity into messages or commands for reactive applications also commonly called as Brain-Computer Interface (BCI). The project is divided in three phases. First Phase deals with Dataset collection, Binary class dataset analysis and Methodology (includes pre-processing of data, classification model, efficiency evaluation). Second phase discusses about complex dataset analysis (cognitive control, Prediction on finger flexion), Advanced algorithms for feature extraction and classification. Third phase discusses about Fine tuning of Algorithms, develop user Interface, Deploy ML model to interface. Different techniques like PCA (principal component analysis), Statistical Approach, Discrete Wavelet Transform (DWT) is used in extracting feature which is the basic techniques used in binary class datasets. Comparison and authentication between fundamental Machine Learning (ML) procedure using K- Nearest Neighbors KNN is done to give better prediction accuracy than the complicated Machine learning procedures like (Support Vector Machine (SVM), Artificial Neural Network (ANN), or Deep Neural Network (DNN). Results obtained for average efficiency for epilepsy detection using statistical and wavelet as features and SVM as classifier is 98%. Considering eye state detection dataset, obtained an average efficiency of 55%. Similarly for cognitive dataset an average of 95% efficiency was obtained by using PCA as a feature and KNN as classifier. In finger flexion dataset the aim was to find out the correlation between finger moments, by using the N best channel frequency pairs and applying the linear regression for the dataset, an average of 0.38 correlation was obtained. Thus, different method and classifiers have obtained fair predictions and efficiency was used. After training of ML models, the user interface was built using HTML and CSS and the trained models were connected to the interface by means of flask framework. The interface gives the user, freedom to select different combination of datasets and features and predict the class accordingly. The interface is also facilitated with visualization of the input test signal which uses chart for plotting graphs.

Keywords: BCI, Feature extraction, Classifiers, User Interface

Abstract: Nowadays newspapers are getting obsolete and the newer generation is getting more dependent on smartphones and similar digital media. Advertising in newspapers is expensive and does not catch the eyes of younger generation. The proposed system is a platform where the user can view the daily offers, flash deals and other advertisement of nearby shops. In this survey, a new approach to offline and online marketing is discussed here.

Keywords: Digital Marketing, Machine Learning, Promotion

Abstract: Sign language is a visual language that is used by deaf people as their mother tongue. Unlike acoustically conveyed sound patterns, sign language uses body language and manual communication to fluidly convey the thoughts of a person. It is achieved by simultaneously combining hand shapes, orientation and movement of the hands, arms or body. Lot of problems arise when people that are impaired from hearing or speaking try to communicate with normal people. The reason is that they mostly communicate using sign language and normal people generally don't know anything about sign language. The objective of the project is to convert speech & text to sign language using Natural language processing capabilities of people with hearing disabilities or speaking disabilities. Also, to provide a user friendly tool which reduces the amount of effort spent on communication. We are developing a system that converts speech/text to sign language animation. This system is composed of an Automatic speech recognizer. Live uttered input speech is captured through a microphone then it is translated to text through some speech recognition engine. The recognized text will be input to an ASL database on a word basis looking for a match. The database contains a certain number of prerecorded video animation signs where mainly there is one video clip per each basic word. If a match occurred, the equivalent ASL translation will be displayed following the Signed English (SE) manual as a parallel to English rather than following the ASL syntax. Otherwise, the word will be fingerspelled. Finally, both recognized text and ASL translation will be displayed concurrently as a final output.

Keywords: Speech Recognition, Speech-to-text, Natural language processing, Sign language

Abstract: Vehicular Ad Hoc Networks (VANETs) are a completely wireless network connected through the nodes, which usually has dynamic topologies. VANETs are expected to play a key role in the intelligent transportation system (ITS). It can be employed in many applications such as traffic control, safety related message dissemination, and entertainment. With the increasing number of vehicles on the road, a need for an efficient communication and transmission of emergency messages in VANET is required. In this survey, the approach to improve clustering and communication are discussed.

Keywords: VANET, Clustering, Message transmission

Abstract: Algorithm visualization illustrates how algorithms work in a graphical way. It mainly aims to simplify and deepen the understanding of algorithms operations. Within the paper, we discuss the possibility of enriching the standard methods of teaching algorithms, with algorithm visualizations. As a step in this direction, we introduce the Algorithm visualizer platform, present our practical experiences and describe possible future directions, based on our experiences and exploration performed by means of a simple questionnaire

Keywords: Graphical Way, Algorithms Operations

Abstract: - Users benefit from the rapid expansion of computer network systems, but they will also face new security threats. The problem of network security encompasses both network system and data security. Tools and techniques are used to scan the network and its devices for vulnerabilities during network scanning and vulnerability testing. Due to the identification of weaknesses, this aids in the refinement of any organization's security policy. In this project we make use of the portability feature of a Raspberry Pi and configure it as a Network Scanner using Kismet Tool to be able to scan networks wherever possible given the permission. We further add an additional feature to the Raspberry such that the raspberry pi can act as a personal cloud storage. It’s becoming increasingly popular to use online storage with personal cloud providers such as Dropbox, Google Drive, or Amazon Drive. With these services, users can store their files in a cloud. This can be accessed at any time, using nothing more than a computer or mobile device with internet access. However, it’s not uncommon for users to raise concerns regarding the reliability of their cloud hosting provider. A common criticism is that customers don’t know who else has access to the saved data, and whether the files are really removed from the server when they’re deleted. This is particularly important when it comes to the storage of sensitive data. As the protection of your privacy becomes harder and harder, you may be thinking of moving your files to a private cloud storage and in this case, then this Raspberry Pi is perfect for such.

Abstract: In today's modern world, security and safety are major concerns. To be economically strong, a country must provide a safe and secure environment for investors and tourists. Closed Circuit Television (CCTV) cameras, on the other hand, are used for surveillance and monitoring activities. A large number of surveillance cameras are available in various locations, but all of them only record footage. To analyse these videos, a large amount of manpower is required, which is always undesirable due to time and labour waste. As a result, having a system that detects crime in real time and alerts the user is advantageous. This paper proposes a system for automatically detecting crime from surveillance camera footage. The system has been pre-trained to detect crimes in real time and provide both remote and offline alerts, which is useful in reducing the possibility of criminals escaping and quickly arrest them. If the missing person enters the premises, the system detects him or her.

Keywords: IoT, CCTV, CNN, MBF.

Abstract: Users focus upon real-time music played to them, and at the same time, also enjoys making music. We are conducting a group survey attempting to obtain information that can help eradicate wrong assumptions in designing systems involving music-based learning systems. Our main purpose is to present an overall midi system product. In this paper, we exhibit our initial findings and analyses based on the music requests by users we have received to date. This paper also deals with the separation of music into individual instrument tracks which is known to be a challenging problem. We describe two different deep neural network architectures for this task, a feed-forward and a recurrent one, and show that each of them yields state-of-the-art results on the SISEC DSD100 dataset. The accuracy is estimated for each note played by the user.

Keywords: Video Deep Learning, RNN, LSTM, Note Music, Chord Estimation

Abstract: Melanoma is the most lethal kind of skin malignant growth when contrasted with others, despite the fact that people who are analyzed from the beginning have a decent possibility of recuperation. A few creators have examined different ways to deal with programmed location and conclusion utilizing design acknowledgment and AI methods. The significant objective of this exploration is to evaluate the primary designs of Convolutional Neural Networks for the gig of melanoma skin malignant growth analysis. The four most incessant essential skin malignancies are basal cell carcinoma, squamous cell carcinoma, Merkel cell carcinoma, and melanoma. Among all tumors, melanoma is the most deadly kind of skin disease. It is great 100% of the time to anticipate the infection ahead of schedule to not spread all around the body parts and assist specialists with diagnosing it early. Because of the predetermined number of screening communities early identification of disease is profoundly inconceivable. In any event, deciding if it is harmless or destructive will take time. Assume the impacted individual counsels an essential specialist for analyze without realizing it is malignant growth because of the essential specialist's insight. Here is the place where AI and profound learning approaches become an integral factor for an effective mechanized determination framework that can assist specialists with anticipating the infection in a lot quicker way, and surprisingly ordinary people can analyze a particular affliction. Our exploration exertion presents an answer for the issues of expanding clinical expenses related with finding, decreased recognition precision, and the manual discovery framework's transportability. Melanoma malignant growth Detection System is a prescient model that utilizes profound learning thermoscope pictures.

Keywords: Benign, malignant melanoma, Machine learning, Deep learning.

Abstract: Traditional way of fund raising is obsoleted because of getting less attention and delay in gathering funds. Online donation-based crowdfunding has brought new life to charity by soliciting small monetary contributions from crowd donors to help others in trouble or with dreams. Recent years have witnessed the rapid development of crowdfunding platforms among which the donation-based ones are becoming increasingly popular. The proposed System is a platform, which is designed in such a way that recipients can create their own profile, which is verified and displayed to donors. The proposed system offers more attention from donors. So, Fund raising can be done a bit faster.

Keywords: Crowd funding, Machine Learning, Amazon S3.

Abstract: Internet of Things (IoT) advancements have enabled smart home and industrial automation improvements, allowing gadgets in homes to be monitored and controlled remotely. Because appliances are monitored and controlled by small, resource restricted embedded devices, such systems have resulted in energy efficiency and cost savings. Using Message Queuing Telemetry Transport (MQTT) and Node-RED, the article offers a concept for an ESP8266 NodeMCU smart home solution. On the Raspberry Pi 4B, a single board computer development board, a MQTT mosquito broker is used in the smart home system design. A MQ2 sensor is connected to an ESP8266 microcontroller to collect the sensor data, with the Raspberry Pi acting as a MQTT broker to transfer sensor data to a Node-RED dashboard. Key-words: Node-RED, MQTT, Home Automation

Abstract: Computer became integral tool in our lives because it helps in many ways by solving the human problems as and when required but when it comes to the working of computer. It becomes very difficult to understand. In normal and day-to-day scenario, software engineers and computer programmer write the programming or code in high level language, which is understood by human but not by machine and to make that code understable to machine there come the requirement of converting that language to computer understable form and this generates the need of compiler. Compiler is a computer program which translate high level language into the machine understable form. Compiler do this conversion in numbers of phases which will be covered here.

Keywords: Compiler design, compiler phase, syntax analysis, semantic analysis, code generation, code optimization, structure of compiler.

Abstract: Money transactions are plagued by counterfeit notes, which are among the most common problems. In an evolving country like India, it has become a hazard to the economy as a rise in fake notes shoot up counterfeit money in the system, which lowers the value of real money. It also increases inflation, i.e. price of the articles and commodities due to more supply of money in the country Fraudsters can easily print fake notes using the latest hardware machines due to advances in printing and scanning technologies. Recognizing fake notes manually consumes plenty of time and workforce. Hence there is the necessity of a system that would make the counterfeit currency distinction process manageable and effective. This paper is an attempt on creating a system that will take the image of suspicious notes of Rs.2000 & Rs.500 and detct fake notes to give a promising solution for the counterfeit currency problem.

Keywords: Rs. 2000 & Rs.500, Image Processing, MATLAB, Counterfeit notes, manageable, effective

Abstract: Chronic kidney disease, also known as chronic kidney disease, is a featureless disorder of kidney function or kidney function that lasts months or years. Chronic kidney disease is usually found by screening people who are known to be at risk for kidney problems such as: Therefore, early prediction is needed to combat illness and provide good treatment. This study suggests the use of CKD machine learning techniques such as KNN, DT, NB, and SB classifiers.

Keywords: Chronic kidney, KNN, DT, NB, and SB classifiers

Abstract: People use Online Social Networks to build social connections with others who are having similar personal interests or come from the same backgrounds and professions. These social platforms make people’s lives better while generating lots of problems for society. Malicious individuals use social media to clone profiles by obtaining sensitive and crucial information from a target person. These attacks damage the reputation of legitimate users. Detecting these identical fraudulent accounts has thus become a critical aspect of modern social media. Many researchers have attempted to address the issue of detecting fake profiles in online social networks. More solid solutions, on the other hand, must be pursued. In this paper, we report on the investigation of a possible approach to eliminating fake profile creation.

Keywords: Online Social Networks, National Identification Number, National ID, Fake Profile, Profile Cloning.

Abstract: As per as the World Health Organization report is concern, about 10% of the world population is affected by chronic kidney disease (CKD), and millions die only because of inappropriate and non-affordable treatment. Kidney disease is a worldwide health crisis in the present scenario. This disease can be curable with early diagnosis and proper treatment. The purpose of this paper is to establish some predictive models using Machine Learning algorithms by taking a real time CKD dataset. In this paper, we have shown some real-time experiments and observations with the help of some Machine Learning algorithms, and also shown a clear picture on the predictive analysis on medical diagnosis of the chronic kidney disease (CKD) using Machine Learning algorithms using which patients may get accurate data so as to diagnose better for their early treatment.

Keywords: Algorithm, Chronic Kidney Disease, Classifier, Machine Learning, Prediction.

Abstract: The vector generation algorithms generate the line by determine the pixel which should be turned on are sometimes called Digital Differential Analyzer (DDA).

Keywords: DDA, Pixel.

Abstract: In cloud computing, most of the data owners keeps their sensitive data on cloud. With this lot of data files stored in the cloud server, it is important to provide keyword based search service to data user. Now in order to protect the data privacy, sensitive data is usually encrypted before sent to the cloud server, which makes the search technologies on plaintext unusable. The system preserves the high search efficiency inherited from the inverted index while lifting the one-time-only search .limitation of the previous solutions which simultaneously meets a set of strict privacy requirements. A major challenge exposed from the existing efforts is the difficulty to protect user’s query privacy so this challenge is faced and tried to remove in this scheme.

Keywords: Keword,Encription.

Abstract: There The SQL commands that deals with the manipulation of data present in the database belong to DML or Data Manipulation Language and this includes most of the SQL(Structure / sequencial query language) statements. It is the component of the SQL statement that controls access to data and to the database. DCL statements are grouped with DML statements

Keywords: SQL ,DML, DCL

Abstract: Our paper provides detection of Cyberbullying using machine learning. In this project, we aim to build a system that tackles Cyberbullying by identifying the mean-spirited comments and also categorizing the comments as bullied one or not. The goal of this project is to show the implementation of software that will detect bullied tweets. A machine learning model is proposed to detect and prevent bullying on Twitter. Social media is a platform where many people are getting bullied. To identify word similarities in the tweets made by bullies and make use of machine learning and detect social media bullying actions. As social networking sites are increasing, cyberbullying is increasing day by day in today’s world. Cyberbullying is a crime in which a perpetrator targets a person with online harassment and hate. As to detect the cyberbullying a GUI (Graphical User Interface) is created to detect where tweets are used to detect the cyberbullying. Cyberbullying includes insulting, humiliating and making fun of people on social media that can cause mental breakdowns for the victims, it can affect one physically as well to the extent that can also lead to suicidal attempts. We are using classifiers- Naive Bayes, SVM (Support Vector Machine), Random Forest, Decision Tree and Sklearn. As for the classification phase, machine learning will be used. Two classifiers i.e., SVM and Naïve Bayes are used for training and testing the Twitter bullying content. Both Naive Bayes and SVM (Support Vector Machine) were able to detect the true positives with 71.25% and 52.70% accuracy respectively. But Naive Bayes outperforms SVM of similar work on the same dataset.

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

Abstract: Image captioning is a task that tries to generate captions for the given photographs by combing computer vision and natural language processing. It’s a two-step process in which precise image recognition and appropriate syntactic and semantic language comprehension. Due to the rising amount of information accessible on this subject, keeping up with the newest research and findings in the field of picture captioning is becoming increasingly difficult. Current research in the field is mostly focused on deep learning-based methods, with attention mechanisms, deep reinforcement, and adversarial learning appearing to be at the forefront. In this paper we will go through various research papers which focuses on deep learning models and uses COCO dataset or Flicker dataset.

Abstract: Today, a potential alternative known as network-on-chip (NoC) is being used in multicore systems to circumvent the limitations of traditional on-chip networks. NoC designs enable the use of high-capacity wireless connections to significantly decrease the latency associated with multi-hop communications. This article discusses a new technique for increasing the performance and power usage of NoCs. The suggested method makes use of a customized version of the RED algorithm's queue length concerns. A constantly increasing set of cores on the device need a scalable architecture; this is the most essential option. Mesh-based NoCs are the most commonly available topologies in many-core processors today as a scalable alternative to the conventional shared bus. To ensure long-term scalability and performance, the low-latency connection between the cores becomes more important. The delay between endpoints in an ideal network is roughly equal to that of a single cycle. The suggested method was tested using a variety of simulated traffic patterns and the SPLASH-2 trace-driven benchmark suite. The testing findings show that the algorithm significantly lowers latency and power usage when compared to a traditional NoC.

Keywords: Routing algorithm, Power efficiency, Latency, Topology, Interconnection Network, Network-on-chip

Abstract: Semiconductor manufacturing plays a critical role in modern industry. With the rapid growth of this field, semiconductor companies are challenged in both R&D and manufacturing domains. However, the increasing complexities of devices, structures, materials, processes, and even changing physical models pose great challenges for both modeling and computation. In addition, the growing amount of data and the large number of people involved in the R&D, design, and fabrication of semiconductor components complicated the production systems and slowed down the overall throughput. For the R&D and production of semiconductor devices with advanced technology nodes, the integration of Physics-based modeling, Computer Aided Engineering tools, parameter optimization, and Machine Learning methods constitutes a new vector for promoting innovation and productivity in the semiconductor industry. Machine Learning methods empower automated, efficient, and intelligent solutions for semiconductor modeling by modeling data with Non-linear regression, Principal Component Analysis, clustering, classification, and generative methods. Physics-based regression methods such as Fourier Series expansion and Polynomial Chaos are established to establish neural networks for topology optimization, sensitivity analysis of processes with uncertainty quantification, inverse characterization of materials, and accelerated simulation. Reinforcement Learning tools have been successfully developed for the early-stage optimization of processes and design. Meanwhile, Deep Learning-based tools such as Generative adversarial networks and convolutional neural networks have been developed for the design of structures/gate layouts and the qualification of patterns. On the other hand, modern semiconductor manufacturing consists of multiple departments with complex production systems. Significant efforts have been made on modeling layout storages and new equipment selection to optimize the bi-objective cost and yield in extreme scale layouts. Mathematical programming, agent-based models, and Reinforcement Learning methods have been proposed to optimize the scheduling of diverse wafer processing flows and streamline interactions at the Fab level between manufacturing equipment, input/output, and cost. Moreover, after a decade struggle, advanced Process control systems in conjunction with on-line monitoring monitors critical sensors and control actuators to solve quality issues on time. These large-scale systems save resources and improve quality at the cost of higher complexity. Process data analysis and fault detection methods such as Fourier analysis and kernel-based methods have been established to model non-linear propagation of disturbances and forecast machine states for predictive maintenance.

Keywords: Machine Learning, Semiconductor, Research, Manufacturing, Automation, Predictive Modeling, Process Optimization, Defect Detection, Yield Improvement, Data Analytics, AI in Semiconductors, Fabrication, Smart Manufacturing, Quality Control, Industrial AI

Abstract: Fintech is an application of digital technology in the financial services industry, which broadens the financial service landscape. Big data in fintech has become one of the most relevant areas for businesses and researchers alike. All the financial sector tasks are influenced by new solutions based on big data. This paper will reveal how big data is changing everyday decision-making, improving the quality of decisions, and enhancing personalization in payment services. The last conference submission item offers brand-new solution ideas for researchers, professionals, business practitioners, and executives in financial companies, highlighting current research difficulties in fintech, especially big data management and analytics. Today’s clients live in a world of choices and offer products and services to overcome challenges, improve forecasts, and create and exploit fresh market opportunities. Firms’ decisions in this rapidly changing environment play a significant role in experiencing climate change impacts and need sustained analysis and data updating. The general goal of all available financial services is to optimize daily decision-making. Accounting and tracking of inflow and outflow, budget planning, lending, loan application, insurance, payment transactions, investment risk assessment, portfolio selection, etc. would be done every day by everyone from the age of 12 up to 50. As for research requirements, the session seeks novel decision models and processes or methods for analyzing and pre-empirical assessments to help improve the quality of decisions, enhance flexible decision-making, ensure system interpretability, and increase decision compliance.

Keywords: Big Data Analytics,Fintech Innovation,Payment Personalization,Predictive Modeling,Customer Behavior Analysis,Real-time Data Processing,Risk Assessment,Fraud Detection,Data-Driven Decisions,Machine Learning in Fintech,User Experience Optimization,Financial Data Mining,AI-Powered Payments,Transaction Data Analysis,Personalized Financial Services.

Abstract: This paper is intended to present a digital structure able to forecast the demand of articles in a daily time span and form these forecasts an advice of replenishment orders, in such a way that forecasted incoming sales are always satisfied and stock outs avoided. The quality of this system is evaluated through a simulation process that bases its decisions in data coming from a large retail store and through on field operation in a smaller retail store. In both cases, results show a good performance of the proposed model, with substantial sales increase and costs decrease. All the above, plus the estimation of useful theoretical results, leads to a second part to present a choice support tool for replenishment orders. As this second model makes use of pre-existing ones and adjusted results of these two models allied to possible statistical simulations of the incoming orders’ behaviour, it is expected an easy implementation in any retail company at no or low cost. Therefore, despite this later solution doesn’t put forward a huge technological solution with great consequences over the existing job structure in the retailer, it can still be considered an improvement in the forecasting of incoming orders. The digital structure proposed in the first part can significantly increase the accuracy of forecasts with several advantages behind it. However, in spite of the clear advantages of the proposed digital structure, it also represents a huge change concerning the structure and information flow within the retailer, with many risks of instability and huge working effort behind it. The same change brought significant no-forecast problems in the past, with severe consequences. Therefore, it was decided to propose a second part based on the assumption that the proposed model will show desirable results. First targets with this goal are a day to day analysis of the existing filling rate levels, in order to check that the given product supply level is correctly pursued, and of the weeks with bigger tumbles in order to analyze the stock outs and control promotions.

Keywords: Predictive Inventory Management, Machine Learning in Retail, Digital Supply Chain Infrastructure, AI-Driven Inventory Optimization, Retail Demand Forecasting, Smart Inventory Systems, ML-Based Stock Replenishment, Real-Time Inventory Analytics, Retail Data Infrastructure, Cloud-Based Inventory Solutions, Inventory Prediction Algorithms, Retail Forecasting Models, Automated Inventory Control, Big Data Inventory Management, Intelligent Stock Management.

Abstract: A Cloud-Integrated Framework for Efficient Government Financial Management and Unclaimed Asset Recovery abstract. The allocation and usage of government resources have always been a concern for citizens and practitioners. Over the years, various tools and frameworks have been developed to facilitate good government resource management. More recently governments have acquired and created data and information that can be used to analyze spending patterns and reveal hidden treasures such as unclaimed properties, abandoned warehouse sales, and unused accounts, which helps with efficient resource allocation. Additionally, governments can make use of new technologies, including data mining, data management, and cloud computing, to manage and monetize their data pool. This paper presents a framework that integrates various technologies and methods such as a data warehouse, cloud computing, interactive visualization, and data mining techniques to develop an information system that can be implemented by governments to facilitate financial management. Efficient and effective government financial management can direct resources toward projects that support growth and create welfare for citizens. In a world where every activity generates a digital asset, governments have access to and already possess a pool of data that offer opportunity to make more effective government decisions. This paper presents a cloud-integrated framework that combines new data management technologies, including a government cloud, interactive visualization, and data mining techniques, and creates an effective set of services, and presents a solution to the problem of inefficient government financial management. The proposed framework is applied to assist governments in monetary allocation decisions and provides a decision support system for both citizens and government decision makers. Through the proposed framework, governments can track where funds are employed within their organization and compare borrowed funds with allocated budgets, thereby enabling independent researchers to analyze how effectively specific funds are employed. This leads to the proposal of a service that could be designed on top of the framework to do unclaimed property analysis for citizens.

Keywords: Cloud Integration, Government Financial Management, Unclaimed Asset Recovery, Digital Framework, Public Sector Efficiency, Data Analytics, Asset Tracking, Financial Transparency, Cloud Computing, Fiscal Oversight, E-Governance, Automated Reconciliation, Real-Time Data Access, Centralized Systems, Financial Automation, Digital Transformation, Government Accountability, Recovery Systems, Public Resource Optimization, Cloud Infrastructure, Interagency Collaboration, Secure Data Storage, Digital Finance, Policy Enforcement, Intelligent Monitoring.

Abstract: Healthcare systems face the challenge of enabling trust and communication in both patients and healthcare providers during periods of stress. As the COVID-19 pandemic demonstrates, information uncertainty can evolve from rapidly changing knowledge to evolving political narratives that undermine trust. Resource and workforce shortages further impact the quality of trust-building interactions, and communication barriers—both for patients and providers—are amplified. Health systems must proactively plan for these issues and consider their consequences. Patients desire clarity, transparency, empathy, and sufficient time to address concerns, and are forgiving of healthcare providers when patients perceive that they are doing their best under the circumstances. The nature of the translational physicianship spans both clinical communication and risk communication but is not always present among a stressed workforce. Decision-making policies for the responsible use of original language messages, especially granting national truism guards, must focus analysis on information sources and flows rather than geography, with the aim of creating stronger myth-busting communications without eroding trust. As other disasters have shown, part of the solution may lie with building and resourcing health information exchange systems and tools to enable care for remote populations in real time, while also ensuring support and training for those healthcare workers in frontline communication roles.

Keywords: Healthcare Trust, Crisis Communication, Information Uncertainty, Pandemic Response, Patient Provider Communication, Risk Communication, Translational Physicianship, Workforce Stress, Resource Constraints, Information Governance, Myth Busting Strategies, Health Information Exchange, Remote Care Enablement, Transparency And Empathy, Public Health Messaging, Communication Policy Design, Digital Health Infrastructure, Frontline Workforce Support, Trust Preservation, Health System Resilience.

Abstract: Demand for supply chain optimization through industrial data analytics has surged, fueled by lessons learned during the COVID-19 crisis. A systematic review of methods applied in practice in 2021 summarizes how data science and operations research techniques are being adopted to tackle key issues. The review follows the ground-up flow of data in a typical supply chain. Publications describe predictive maintenance; end-to-end supply chain visibility; and inventory optimization. The data sources and processes for these analytics are also considered, echoing the importance of data quality and integration. Organizations are investing in technologies and competencies, yet progress remains slow. Acknowledgment of data quality dimensions is essential to achieve reliable models, yet limited. Moreover, a lack of interoperability hampers integration across factory-level operational systems and, consequently, impact on global visibility. These observations highlight the gap between the theory and practice of supply chain optimization. The study makes a threefold contribution to operations research and data science. It analyzes how pioneering companies are leveraging data science for supply chain optimization, synthesizing methodological applications within the identified analytics. On the data side, it discusses the sources that feed manufacturing and logistics operations, emphasizing critical dimensions of data quality and the requirements for integration across distinct analytical domains. Finally, it translates this body of knowledge into practical insights for managers.

Keywords: Supply Chain Optimization, Industrial Data Analytics, COVID-19 Supply Chain Disruptions, Data Science Applications, Operations Research Methods, Predictive Maintenance Analytics, End-To-End Supply Chain Visibility, Inventory Optimization Techniques, Manufacturing Data Sources, Logistics Analytics, Data Quality Dimensions, Data Integration Challenges, Interoperability Limitations, Factory-Level Operational Systems, Global Supply Chain Visibility, Theory–Practice Gap, Analytics Adoption In Industry, Managerial Decision Support, Evidence-Based Supply Chain Management, Digital Transformation In Operations.

Abstract: The dramatic increase in the adoption of remote education necessitates a corresponding enhancement of the technical infrastructure supporting the process. For this reason, the application of cloud computing technologies in education, such as Software as a Service, Notebooks as a Service, and Infrastructure as Code, increases the quality of the learning experience while reducing the costs of developing and supporting the educational process. The theoretical foundations of the topic are based on an analysis of 2,885 sources from the Scopus bibliographic database, which were processed using modern digital analysis tools. The material is filtered by key terms in the title, abstract, and keywords. Five main aspects are considered: service models, deployment models, quality assurance, identity management, and data security. The service model Software as a Service is explained in the context of cloud-based educational environments.

Keywords: Cloud-based Learning Management System (LMS),Virtual Classroom Platforms,Education Cloud Infrastructure,Scalable Cloud Hosting for Schools,Remote Learning Cloud Services,Cloud Storage for Educational Content,Video Conferencing for Online Classes,Cloud Security for Education,Identity and Access Management (IAM),EdTech SaaS Solutions,Cloud Collaboration Tools for Students,Content Delivery Network (CDN) for E-Learning,Disaster Recovery & Backup for Schools,Hybrid Cloud for Education Institutions,AI-Powered Cloud Learning Analytics.