VOLUME 13, ISSUE 3, MARCH 2024

Abstract: Gold's price is always fluctuating, either rising or falling. Given that gold is a major element of the financial market, gold price prediction is an essential area of finance. Many machine-learning methods have been used in published studies to anticipate gold prices. Several classification techniques, including random forest, decision tree, logistic regression, and linear regression, are used in this work. This article's topic originates from study done to understand the worth of gold. There is currently a constant market for gold. The gold price trend shows that gold is one of the best investment strategies. It is, therefore, prudent to forecast the direction of the gold rate. Numerous statistical models can be used to forecast and model data. The price of gold is consistently shown to be nonlinear. Price prediction is key to sound financial and investing strategy. The price fluctuation of gold can be represented as an exponential curve. Convolutional neural networks are among the best tools for resolving nonlinearities in data, and RNNs are especially useful for time series forecasting and estimation. Using data from the World Gold Council, it is found that the suggested design is among the most effective financial forecasting techniques.

Keywords: Regression, linear regression, logistic regression, decision tree, random forest, Machine Learning and l Prediction. Cite: Dhanush N, Raghavendra R, "Historical Data-Based Gold Price Prediction using Intelligent Algorithms", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13302.

Abstract:  With its inherent volatility and complexity, the BitCoin market poses a significant obstacle to precise price prediction. The purpose of this survey study is to examine and compare the effectiveness of two popular prediction approaches—Decision Tree and Regression techniques—with more sophisticated Machine Learning techniques. We provide an in-depth analysis of these various methods' success in predicting cryptocurrency prices, highlighting their advantages, disadvantages, and ability to produce accurate forecasts. By conducting a thorough investigation, we hope to offer insights that further the current discussion on successful prediction techniques in the ever-changing cryptocurrency markets. Keywords: BitCoin market, Price prediction, Regression techniques, Machine learning technique, Analysis. Cite: S. BAKYALAKSHMI, D. BHUVANESHWARI,"Cryptographic Applications for BitCoin Prediction", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13303.

Abstract:  Artificial intelligence (AI) has grown to be a cornerstone in present day recreation design, profoundly impacting participant reports. This paper investigates the complete affect of AI, encompassing its outcomes on Creativity, gamely dynamics, and personalization in recreation improvement. It delves into AI-Pushed procedural content, material generation, adaptive trouble adjustment, and participant conduct analysis. Furthermore, the paper explores AI’s contribution to practical non-participant character (NPCs), dynamic storytelling, and herbal language processing, raising participant interactions to new heights. Ethical issues and demanding situations surrounding AI integration are addressed, emphasizing the need of accountable improvement for making sure honest and charming participant reports. This study underscores AI’s pivotal position with inside the evolution of interactive entertainment, promising diverse, immersive, and socially attractive reports for gamers whilst pushing the bounds of recreation design.

Keywords: security, data collection, CIA Triangle. Cite: D. AMIRTHAVARSHINI, S. DEEPALAKSHMI, D. SUBHASHINI,"AI ENHANCED GAME DESIGN AND PLAYER EXPERIENCE", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13304.

Abstract: Fog is a layer between the cloud and end users and it extends the services provided by the cloud computing to the network edge. Fog computing follows the distributed network architecture and closely associated with IOT (Internet of Things). Security is the main challenge in the fog due to the password compromise. To overcome the password compromise additional authentication credentials are needed to login.  Round Trip Latency (RTL) based scheme increases the protection of traditional password authentication between clients and authenticators and extra profiling features are needed to defense against password compromise. In this paper, extended latency based authentication is proposed that includes the keystroke dynamics along with the latency to effectively protect from the same location attacks

Keywords: Fog, Cloud, Keystroke, authentication, RTL. Cite: E.P. Priyadharshini, S. Jothipriya,"A Survey of FOG Computing", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13305.

Abstract: There isn't enough time for our daily activities in the fast-paced world of today. Everyone struggles to maintain their mental stability while carrying out daily obligations. Robots have been developed to make human labour easier, and we have similarly offered the idea of a "Automatic Lawn Mower with Obstacle Detection and Avoidance" Robot. Without any assistance from humans, our robot maintains the beautiful, green lawns by evenly cutting them. The sensors built into an autonomous lawn mower robot operate as the robot's eyes and guide it. The system is stable and application-specific due to the microcontroller-based programmed operation. A lawn mower is a tool used to trim the grass on a lawn. The lawn mower's blades are typically propelled ahead by pushing the machine forward. Several factors are used to categorize lawn mowers. For instance, reel lawn mowers, which have a horizontal axis of rotation, and rotary lawn mowers, which have a vertical axis of rotation. There is a reel (cylindrical) lawn mower. It is discovered that the reel (cylindrical) lawn mower is superior. They are made of blades on a rotating cylinder ground that the revolving mower blades come into contact with as it advances. The mower may be set to different cutting heights. Rarely is the blade sharp   enough to provide a clean cut. The grass is simply chopped by the blade and brown tips are the outcome. Nonetheless, it is simple to remove, sharpen, or replace the horizontal blades. Again depending on the energy source, we may have a hand-powered, gasoline-powered, or electric lawn mower. To put it simply, robotics is nothing more than managing the group of motors put together to carry out the predetermined tasks. This system is controlled by physical sensor inputs, and the microcontroller unit, which is always the brain of any kind of automation, establishes the required output depending on the inputs collected by the sensors.

Keywords: Lawn mower, Microcontroller, Robot, Ultrasonic sensor. Cite: KARTHI S P, POOJASREE T, JENIKSHA EPZIBA J, PONVARSHINI PRIYA U G, MOURIYA M, "AUTOMATIC LAWN MOWER WITH OBSTACLE DETECTION AND AVOIDANCE", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13306.

Abstract: The proliferation of mobile users has led to a significant increase in mobile messaging, resulting in a rise in SMS (Short Message Service) spam. Unlike other messaging platforms such as Facebook and Whats-app, SMS does not necessitate an active internet connection. Spam SMS messages, which are unwanted and potentially harmful to users, pose a substantial challenge in mobile communication. These messages are primarily aimed at distributing electronic messages for commercial or financial gain. Consequently, combating SMS spam is crucial for preserving the integrity of mobile communication channels. However, existing email filtering algorithms may underperform due to factors such as the lack of real databases for SMS spam, limited features, and informal. This study proposes an approach utilizing Machine Learning techniques to address SMS spam. The approach encompasses various components, including data-set combinations, data cleaning, exploratory data analysis, and feature engineering. Additionally, several machine learning algorithms, such as Naive Bayes and Support Vector Machine, are assessed for model building. The ultimate aim of SMS spam detection is to protect users from spam-related issues.

Keywords: Spam SMS, Facebook, Whats-app, Internet Connection, Financial gain, Data-sets, Data cleaning, Feature engineering, Naive Bayes, Model building. Cite: Shreya Menthe, Kanish Rawal, Mrudula Hirave, A. J. Patil,"SMS SPAM DETECTION USING MACHINE LEARNING", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13307.

Abstract: Sentinel is an AI-powered visual inspection system designed for automatic detection of anomalies and defects in manufactured products, with a particular focus on steel surfaces. Leveraging computer vision and deep learning, Sentinel offers real-time defect detection during manufacturing, identifying anomalies like roll printing, iron-oxide scales, inclusions, scratches, holes, and cracks. By integrating with production line camera feeds, Sentinel provides continuous quality evaluation and improvement. Our approach, utilizing the YOLO (You Only Look Once) model, streamlines the detection process, reducing computational complexity and achieving faster inference speeds. Through extensive experimentation and evaluation on real-world steel defect datasets, our system aims to enhance the efficiency and accuracy of defect detection, paving the way for improved steel quality control, production efficiency, and safety.

Keywords: Manufacturing quality control, YOLO object detection, Early defect identification, Product quality assurance Cite: B V Suresh Reddy, Kandula Haripriya, Budda Sivaparvathi, Mutchintala Renuka, Narne Venkata Nagalakshmi, Puvvula Sarayu,"Sentinel - Intelligent Defect Detection System", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13308.

Abstract: The "Verify Plate AI: Smart Vehicle Identification" system utilizes cutting-edge computer vision algorithms to facilitate real-time detection and recognition of license plate numbers. Tailored for implementation in parking areas, toll booths, security checkpoints, and diverse sites, its notable features encompass multi-angle detection, precise recognition of license plate characters via Optical Character Recognition (OCR), and identification of vehicle attributes such as color, type, make, and model. Moreover, the system facilitates instant license lookup from databases and offers a user-friendly cloud-based monitoring dashboard, thereby enhancing overall efficiency in vehicle identification and management. This project signifies a significant leap in automated license plate recognition technology, offering a comprehensive solution for security and surveillance applications.

Keywords: License plate recognition, Computer vision, Optical Character Recognition (OCR), Vehicle attributes identification, Cloud-based monitoring, Security, Surveillance, Automated systems. Cite: Dr A Sandeep Kumar, Avuluri Venkata Madhavi, Bhavya Sri Aakuraathi, Koya Hema Satya Sri, Laghumavarapu Komali, "Verify Plate AI: Smart Vehicle Identification", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13309.

Abstract: Cloud security has become a critical concern as organizations increasingly rely on cloud computing services. This paper delves into the concept of Cloud Security Threat Intelligence Sharing as a pivotal strategy for bolstering the security of cloud environments. The document starts by examining the evolving threat landscape within the cloud, emphasizing the unique vulnerabilities and challenges it presents. It stresses the importance of proactive threat intelligence to counter sophisticated cyber threats targeting cloud resources. The primary focus is on exploring various mechanisms and frameworks for sharing threat intelligence in the context of cloud security. This includes discussing the advantages of collective defense through real-time threat data sharing among cloud service providers, enterprises, and relevant security entities. The paper also dissects the technical, operational, and legal obstacles associated with sharing threat intelligence. Moreover, it investigates the role of emerging technologies like machine learning and artificial intelligence in automating the collection, analysis, and dissemination of threat intelligence in cloud environments. These technologies offer the potential to enhance incident response and mitigation. To illustrate the practical impact of threat intelligence sharing, the paper provides case studies and examples of successful initiatives within the cloud ecosystem. It underscores the necessity of establishing trust among participants in threat intelligence sharing networks and outlines best practices to safeguard the confidentiality and privacy of shared information. In conclusion, this paper underscores Cloud Security Threat Intelligence Sharing as a vital strategy for fortifying the security of cloud-based systems. It offers insights into the challenges, benefits, and technologies associated with threat intelligence sharing in the cloud, advocating for increased collaboration to combat evolving cyber threats.

Keywords: Cloud security, Critical concern, Cloud computing services, Cloud Security Threat Intelligence Sharing, Cloud environments, Threat landscape, Threat intelligence, Cyber threats, Cloud resources. Cite: V Mounika, Yedupati Yaswanth ram, Sk Mohammad Irfaz, Y Revanth,"Cloud Security Threat Intelligence Sharing", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13310.

Abstract: Transmission lines play a crucial role in the power system by transmitting a significant amount of electric power from the source area to the distribution network. With the exponential growth in power demand, minimizing power losses has become a paramount concern. These losses encompass transmission losses, physical losses, and various technical losses. Additionally, reactive power and voltage deviations pose significant challenges in long-range transmission lines. Fault analysis is pivotal in power system engineering to swiftly clear faults and restore the power system with minimal interruption. However, detecting faults in transmission lines remains a challenging task, necessitating research to enhance system reliability. This paper provides a comprehensive review of transmission line fault detection methods.

Keywords: transmission lines, power system, fault detection, power losses, reliability, fault analysis Cite: Gaurav Jichkar, Rahul Mohurle, Vikas Kalambhe,"Electrical Fault Detection in Overhead Transmission Line", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13311.

Abstract: Women safety is a critical concern worldwide and leveraging technology to address. This issue is becoming increasingly imperative. This abstract introduces an innovative initiative focused on app development for women safety, the primary objective of this initiative is to harness the potential of a mobile application to enhance safety, security and well being of women in various setting. Iris the comprehensive women support app is a beacon of empowerment and assistance for women in all works of life. This innovative application serves as a safety haven fostering a thriving online community where women can connect share experience and access a wealth of resources tailored to their unique needs. This multi-faced application offers a range of essential features including Self-defence techniques, access to female driver numbers, information on the nearest police station and helpline number for immediate assistance. For moments of relaxation Iris includes mini games to help user unwind and destress. With its Holistic approach Iris aims to be and indispensable companion for women for steering safety, health, education and empowerment in their daily lives.

Keywords: Women Safety, Assistance, Empowerment, Security, Online Community, Helpline numbers. Cite: Nilakshi Sharma, Maria Shaikh, Siddhi Vaste, Payal Kale, Dr. V.S. Phalke, "IRIS: A Comprehensive Women Support App to Address Diverse Needs of Women", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 2, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13312.

Abstract: This research delves into the realm of Explainable Artificial Intelligence (XAI) through a comparative analysis of interpretability metrics. Focusing on Local Interpretable Model-agnostic Explanations (LIME), Shapley additive explanations (SHAP), and traditional feature importance, the study employs a decision tree classifier on the Iris dataset. LIME emerges as a standout performer, demonstrating superior precision, recall, and F1 score, emphasizing its efficacy in providing locally accurate explanations. SHAP exhibits balanced performance, offering versatility in understanding feature contributions on both local and global scales. Traditional feature importance provides valuable insights into overall feature significance. The study contributes nuanced considerations for selecting interpretability tools based on specific application requirements, fostering transparency in machine learning models.

Keywords: Explainable Artificial Intelligence (XAI), Interpretability, Local Interpretable Model-agnostic Explanations (LIME), Shapley Additive Explanations (SHAP), Feature Importance, Decision Tree, Iris Dataset, Precision, Recall, F1 Score, Machine Learning Transparency Cite: Jhilik Kabir, Adrita Chakraborty, Abdullah-Al Mahmood, Aditi Chakaraborty,"Exploring Explainable Artificial Intelligence: A Comparative Analysis of Interpretability Techniques", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13301.

Abstract: This article describes about the project implementation of "Recommendation System for Validating code and Optimal Refactoring" and its outcomes for the problems mentioned. This project enhances coding practices by suggesting clean code snippets and with enhanced scoring mechanism. Initially, it identifies code issues using static code analysis APIs in languages like Java, Python, HTML, CSS and JavaScript. And then uses natural language processing techniques and libraries like NumPy and scikit-learn to recommend context-specific code solutions. This innovative system integrates with popular IDEs, supports multiple languages, can be customizable and developed on huge dataset training, significantly improving code validation and refactoring processes.

Keywords: Static code analysis APIs, Programming language linters, NumPy, Pandas, Scikit-learn, Collaborative Filtering Algorithm, NLP techniques (Stemming), Vector embeddings, Cosine similarity, TF-IDF algorithm. Cite: Koteswara Rao Velpula, Hema Pavuluri, Poojitha Neeluri, Anushka Pappala, Mounika Narra,"Recommendation System for Code Validation and Optimal Refactoring", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13313.

Abstract: This study delves into the realm of sentiment analysis techniques with a focus on unraveling customer opinions and reviews concerning products. In an era where online shopping and digital engagement have become ubiquitous, understanding customer sentiment is paramount for businesses to thrive. The project employs a Random Forest Classifier model integrated into a web application for real-time sentiment analysis. Through preprocessing text data and utilizing natural language processing tools, the model discerns between positive and negative sentiments expressed in customer reviews. The findings of this investigation shed light on the efficacy of sentiment analysis techniques in deciphering product sentiment, thereby aiding businesses in making informed decisions to enhance customer satisfaction and product quality.

Keywords: Sentiment Analysis, Customer Reviews, Product Sentiment, Natural Language Processing (NLP), Machine Learning, Random Forest Classifier, Text Preprocessing, Real-time Analysis. Cite: Mrs. N. Malathi, T. Dhana lakshmi, M. Praisy Rivritha, K. Pujitha Krishna Priya, M. Tulasi, G. Mani Deepthi, "UNMASKING PRODUCT SENTIMENT: AN INVESTIGATION INTO SENTIMENT ANALYSIS TECHNIQUES FOR UNVEILING CUSTOMER OPINIONS AND REVIEWS", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13314.

Abstract: Around the world, machine learning is utilized in a wide range of areas. The medical field is not an exception. Predicting whether there is a risk of heart diseases, issues with the loco motor system, and numerous other conditions can be significantly assisted by machine learning. Like that so information is predicted well in advance, it may offer physicians valuable insights that allow them to customize their diagnosis and treatment for each patient. We use machine learning techniques and methods for early prediction heart diseases in humans. In this project, we used machine learning techniques Logistic Regression & Decision Trees. We also suggest performing hybrid classification, as it can have numerous samples for both training and verifying the data.

Keywords: Machine learning, supervised learning, logistic regression, decision tree, python programming. Cite: Dr. Umesh Akare, Prof. Umme Ayeman Gani, Anushri Bhongade, Dhanashree Mure, Madhulika Chatterjee, Vanzuli Ramteke, "Heart Disease Prediction System Using Machine Learning", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 2, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13315.

Abstract: Tricholoma matsutake (T. matsutake) is a special type of fungus known as “the king of bacteria”, and has a very high economic value. However, it is also very difficult to transport due to its corruptibility. Therefore, tracing and tracking the quality and safety of T. matsutake in the cold chain is very important and necessary. Based on changes in the cold chain, environmental parameters determine the safety of T. matsutake is a viable option. This paper developed and tested a real-time monitoring traceability system (RM-TM) using emerging Internet of Things (IoT) technologies for monitoring the cold chain logistics environmental parameters of T. matsutake. Finally, system testing and evaluation have shown that RM-TM can track and monitor temperature, humidity, oxygen and carbon dioxide fluctuations in the cold chain in real-time. In addition, the collected data can be used to increase the transparency of cold chain logistics and to more effectively control quality, safety, and traceability. In general, the system evaluation results show that it is reliable and meets the requirements of users. In the Energy Management system, the main constraints are accurate data, energy monitoring and implementation of visual data for consumers. This Project is intended in designing a system at home or industry which monitors the temperature consumption of cold storage, which is designed to calculate the total energy consumption. A server will be created with appropriate channels to monitor the energy consumption from each of the devices respectively. These data will be uploaded to the server at the monitoring end. Considering all this data, an individual energy load profile for each of the devices is displayed on the web-page.

Keywords: Transmitter, Receiver, Antenna, Fading, Peak to average power ratio (PAPR), Bit error rate (BER), Symbol error rate (SER), Frame error rate (FER), Inter carrier interference (ICI), Inter symbol interference (ISI), Cyclic prefix (CP), Maximal ratio combining (MRC), Maximum sum rate and Minimum error rate etc. Cite: Ambika Nanwatkar, Sahil Jawade, Sagar Hivarale, Vijay Gaikwad, Lalita Patle, Sneha Parbat, Nikita Paul, Prof. Diksha Khare, “IOT BASED FOOD COLD STORAGE MONITORING AND CONTROLLING SYSTEM”, IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 2, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13316.

Abstract: Career advice has a significant role in the development of both product markets and educational institutions. Because selecting a career is undoubtedly among the most crucial choices a person can make. Ironically, a decision this important is sometimes made without much thought and frequently quite early in a person's life. You should give your profession choice the utmost thinking, consideration, and planning. People have different intrinsic skills and capabilities, which affects their aptitude for different types of jobs. Finding the ideal match between a person and a profession for both parties is the aim of career coaching. Additionally, it promotes equity. Recent research indicates that social mobility requires a broader acquisition, including not just having the requisite knowledge and skills but also knowing how to apply them. Supporting lifelong learning is a broad objective of career coaching in this context. The needs for, significance of, and suitable implementation of career counselling are discussed in this essay. And we know how to improve C.G. so that it works better for everyone, including the kids. Although it deviates from the typical paradigm of conducting occupational interviews with children who are about to graduate from high school, this service is currently provided and changed in numerous parts of our country.

Keywords: Career Guidance, Innate capacities, Social Mobility, Life Learning, and Traditional Model. Cite: Adit Kulshreshtha, Ankit Sharma, Shameem Ahmad, Shubhanshu Pandey, "CAREER GUIDANCE SYSTEM", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13317.

Abstract: With the exponential growth of the online food delivery industry, ensuring timely deliveries has become paramount to customer satisfaction and business success. However, the persistent challenge of delayed delivery continues to plague food delivery companies, resulting in customer dissatisfaction and potential revenue loss. This project delves into the domain of food services to investigate the complexities surrounding the accurate estimation of delivery times. Through the exploration of predictive models and the analysis of various factors influencing delivery time estimation, including geographical variables, traffic patterns, order complexity, and operational dynamics, the study aims to develop robust forecasting mechanisms. By leveraging historical data and employing advanced analytical techniques, this research seeks to uncover insights that can enhance operational efficiency and mitigate delivery delays effectively. Ultimately, the outcomes of this study are poised to contribute valuable insights to the online food delivery industry, fostering improved customer satisfaction, retention, and sustained growth in this dynamic market landscape.

Keywords: Delivery time estimation, Customer satisfaction, Predictive models, Geographical variables, Traffic patterns Cite: Dr. Ayyappa Chakravarthi M, Shaik Eesa Ruhulla Haq, Madapakula Venkata Anil, Bathula Venkata Vamsi, Gogireddy Venkata Reddy, "Forecasting Food Delivery Time: An Exploration of Predictive Models and Factors Impacting Delivery Time Estimation", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13318.

Abstract: In the modern digital age, the proliferation of social media platforms has led to the spread of negative content, especially through images containing bad words or text containing bad content. To address this problem, our project aims to develop an intelligent system designed to detect illegal content in images. Using advanced machine learning techniques, including deep neural networks such as CNNs, we aim to create powerful models that can identify and classify illegal content and enable our model to recognize patterns in images embedded with text through extensive training, tackling the critical issue of cyberbullying by building intelligent system to detect illegal messages on social media posts. We build our website using the Python-based Django framework for efficiency and ease of use. Our plan is to create a safer online environment by combining technology and a user-centric approach.

Keywords: Cyberbullying detection, Convolutional neural networks (CNNs), MobileNet, Python-based Django framework, Optical character recognition (OCR), Machine Learning. Cite: Mr. M. Kishore Babu, K. Jayasri, K. Saran, K. Adithya, K. Harsha,"An Approach for Cyberbullying Detection on Social Media", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13319.

Abstract: This article explores an innovative methodology for credit card fraud detection, employing Autoencoder Neural Networks as a powerful tool. This study focuses on enhancing anomaly detection systems. Leveraging TensorFlow and Keras, the Autoencoder model is trained in an unsupervised manner, concentrating exclusively on normal transactions. This approach allows the model to learn the inherent patterns of legitimate transactions, enabling effective identification of potential fraud. The training dataset, encompassing two days of credit card transactions (284,807 instances with 492 labeled as fraudulent), reveals a highly imbalanced distribution. Through meticulous data exploration, insights into transaction amounts and timestamps are gained, informing the subsequent model architecture. The Autoencoder, comprising four fully connected layers with L1 regularization, demonstrates its efficacy in capturing the underlying structure of normal transactions. By evaluating the reconstruction error as a key metric, this project showcases the promising potential of Autoencoder Neural Networks in significantly improving credit card fraud detection mechanisms.

Keywords: CNN Autoencoder Neural Networks, Anomaly Detection, Credit Card Transactions, Fraud Detection, Deep Learning Cite: Mr.A Vishnu vardhan, Muppiri P V S N M L Ankitha, Pasupuleti Divya Sri, Mohana Battula, Muppuri Venkata Triveni Sai Priyanka," Anomaly Detection in Credit Card Transactions using Autoencoders ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13320.

Abstract: Over 3.9 billion people worldwide get affected by dental cavities. Barriers such as dento phobia, limited dentist availability, and lack of dental insurance prevent millions from receiving dental health care. To address this, an Artificial Intelligence system will be developed that can detects cavity presence on photographs. For preventing further damage of teeth, it is necessary to detect cavity as soon as possible. This is particularly significant as it addresses issues related to accessibility, affordability, and convenience in the domain of dental healthcare. By using the widespread availability of smartphones, this innovative approach has the potential to change oral health assessments, reaching a greater number of people and promoting proactive dental care. The "Oral Cavity Detection" project aims to revolutionize dental diagnostics through the application of deep learning techniques. Using the TensorFlow API for object detection, this system will operate seamlessly on a web-based platform, providing a user-friendly interface for the detection and prediction of oral cavities within images of teeth. For training of this cavity detection model, the custom dataset will be required. Comprehensive analysis of this study reveals positive results that can be improved in the future and can be implemented on a commercial scale.

Keywords: Healthcare, Artificial Intelligence, TensorFlow, web-based platform, User friendly Cite: Vaibhav Bhagat, Dr. Vaishali Phalke, Soham Kate, Yogesh Algude, Tanmay Bhosale,Ms. Punam Desai, "Early Cavity Detection Using Image Processing Approach", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13321.

Abstract: With its increasing occurrence, diabetes has become a major global health concern that presents serious difficulties for healthcare systems everywhere. Diabetes must be identified early and managed proactively to improve patient outcomes and lessen the disease's toll. This initiative offers an original method for predicting diabetes using cutting-edge machine learning algorithms.

Keywords: Diabetes Prediction, Machine Learning, Early Detection, Healthcare, Model Interpretability, Feature Engineering, Ethical Considerations, Chronic Disease Prevention Cite: Tushar Kanti De, Prathipati Likhitha, J Vamsi, T Krishna Sai, S Jaswanth,N Sai Krishna Teja, P Narasimha Raju, "Diabetes Prediction using Machine Learning", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13322.

Abstract: In this research, we present a novel approach to enhance the personalization of movie recommendations by incorporating age, gender, and emotion analysis. The proposed system utilizes deep learning models for age and gender prediction, along with emotion detection. We employ a YOLO based face analysis module for real-time face detection in images and video streams. The system then leverages these insights to recommend movies tailored to the user's demographic characteristics and emotional state. The age predictions are further refined into age ranges, providing a more user-friendly representation. The effectiveness of the recommendation system is demonstrated through comprehensive evaluations, achieving a high accuracy rate. The integration of age, gender, and emotion analysis adds a layer of personalization to movie recommendations, catering to the diverse preferences of users. This research contributes to the evolving field of recommendation systems, offering a more nuanced and individualized approach to movie suggestions. Keywords: Movie Recommendation, Age Prediction, Gender Classification, Emotion Detection, Deep Learning Cite: Mr. M. Kishore Babu, Deevi Dharani Satya, Akula JyotheswarKumar, Budda prasanna kumar, Chilaka likith manoj,"Age, Gender and emotion-based movie recommendation using facial recognition", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13323.

Abstract:  " Real-Time Stress Detection and Analysis using Facial Emotion Recognition" is an innovative system designed for real-time stress detection and analysis through facial emotion recognition. Leveraging the power of machine learning and computer vision techniques, the system can accurately identify and analyze emotions exhibited by individuals in live video streams. By utilizing a pre-trained deep learning model, the system detects facial expressions associated with various stress levels, including "Bursted," "Irritated," "Anxious," "Relaxed," "Neutral," "Broked," and "Shocked." The project integrates with a web application interface where users can visualize comprehensive stress analysis reports generated from the detected emotions over time. Through detailed graphs and charts, users can explore trends such as emotion distribution over time, average stress levels, and daily stress variations. Additionally, the system provides personalized recommendations based on the user's emotional patterns, aiming to improve overall well-being.

Keywords:  Real-Time, Stress Detection, Analysis, Facial Emotion Recognition Cite: Hari Prasad Chandika, Bulla Soumya, Baireddy Naveen Eswar Reddy, Boda Mohana Sri Sai Manideep,"Real-Time Stress Detection and Analysis using Facial Emotion Recognition", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13324.

Abstract: At this stage, technology play a significant role in meeting human requirements. The democratic process is facing new challenges as a result of the growing use of technology. Since the majority of people do not trust their leaders, elections are crucial. in a contemporary democracy. Elections are crucial in deciding who will lead a country or organization, or one could argue that they are a momentous occasion that determines the destiny of any given nation.The widespread mistrust that a sizable section of the populace has for modern democracies' electoral processes is one of their greatest obstacles. There are still problems with elections in well-known democracies like India and the United States. Cite: Gajendra Asutkar, Gargi Tiwari, Shreya Musale, Giteshwari Soni, Dikshant Dhude, Nishad Dhawane, "D-Smart voting System using Blockchain", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 2, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13325.

Abstract: Personality prediction from text data, particularly from social media posts, has gained significant attention due to its wide- ranging applications in various fields such as psychology, marketing, and personalized recommendation systems. This study presents a machine learning approach for predicting personality types based on text data extracted from social media posts, focusing on Twitter. The study employs a state-of-the-art natural language processing (NLP) technique, namely BERT (Bidirectional Encoder Representations from Transformers), to encode and understand the textual content. BERT is a transformer-based model known for its effectiveness in capturing contextual information from text data. The Twitter API is utilized to retrieve a user's recent tweets, which serve as input for the personality prediction model. The preprocessing pipeline involves text cleaning steps to remove noise such as special characters, URLs, and punctuation marks.... Cite: P.R. Krishna Prasad, Naga Sai Ajay Kumar Abburi, Pavan Sai Ganesh Cherukuri, Dheeraj Kumar Bhattu, Jaswanth Gadde, "Unveiling Personality Traits through Social Media Language Analysis: A Novel Approach using Language Models", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13326.

Abstract: Diabetes mellitus, a prevalent global health issue, demands early detection and effective management. For deeper analysis and diabetes prediction, this study uses ML methodologies. A large dataset including clinical, sociological, and biological features is meticulously processed. A wide range of ML methods are used to initiate predictive models. This study enhances the science of diabetes prediction by giving effective tools for early risk assessment, personalized medications, and optimal healthcare management. These breakthroughs have the potential to improve public health outcomes and help combat the diabetes epidemic.

Keywords: Diabetes, prediction, analysis, e-Health, data processing, machine learning Cite: Dr. P.V.R.D. Prasada Rao, Asritha Musunuru, Subhash Alapati, Abhinava Kamireddy, Venkatesh Jajula,"Diabetes Analysis using Machine Learning with KNN", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13327.

Abstract: Due to an increase in crime during big events or in isolated, suspicious areas, security is always a top priority in every field. Computer vision is widely used in abnormal detection and monitoring to address a variety of issues. The need for video surveillance systems that can identify and analyze scenes and anomalous events has grown due to the increased demand for the protection of personal property, safety, and security. These systems are essential for intelligence monitoring. This project uses Faster RCNN techniques and a convolution neural network (CNN) based YOLO Module to provide automatic gun (or) weapon detection. Two kinds of datasets are used in the suggested implementation. There was one dataset with pre-labeled photos and another with a collection of manually labeled images. The algorithms yield tabular results with good accuracy; however, the trade-off between speed and precision may determine how these algorithms are applied in practical scenarios.

Keywords: Weapon detection, convolutional neural network, image classification, object detection, computer vision. Cite: K. Mohan Krishna, A. LikhithaReddy, G. Sri Sai Meghana, Ch. Rohith Varma, G. Velugondaiah, "WEAPON DETECTION In A CRIME SCENE USING CONVOLUTION NEURAL NETWORK", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13328.

Abstract: This project presents a novel approach for accurately classifying medicinal plant species based on leaf characteristics, utilizing advanced artificial intelligence (AI) techniques. By integrating deep learning models and classic machine learning algorithms, the system offers precise estimations of medicinal plants from leaf images. Users can conveniently upload images through an intuitive web interface, enabling the system to predict the corresponding plant species promptly. The primary focus of this project is to streamline the process of identifying medicinal plants, addressing the challenges associated with manual classification methods. Traditional approaches often entail significant time and effort, leading to potential errors and inconsistencies in classification outcomes. In contrast, our system leverages the power of AI to automate and enhance the classification process, ensuring accurate and reliable results. The core component of the system is a deep learning model, utilized for feature extraction from medicinal plant leaf images. These extracted features serve as input to both a classic machine learning classifier and the deep learning model itself, facilitating robust classification of plant species based on their unique leaf characteristics. Upon image upload, the system swiftly processes the images, extracting relevant features and predicting the corresponding plant species. Additionally, users receive supplementary information about the predicted plant species, including medicinal properties, geographical distribution, and potential applications. By harnessing AI technologies, this project aims to democratize access to accurate medicinal plant classification, benefiting various stakeholders such as healthcare professionals, researchers, and individuals interested in herbal medicine. Moreover, the system empowers users with informed decision-making capabilities regarding the utilization of medicinal plants for various health conditions.

Keywords: Medicinal plants classification,Artificial intelligence,Deep learning,Herbal medicine ,Image-based analysis,Plant species identification,Machine learning,Healthcare applications. Cite: Sanjay S M, Praviksha, Sooraj S Bhat, Neha B S, Ms. Radha E G, "Harnessing AI For Precise Estimation of Medical Leaf Characteristics", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13329.

Abstract: Many organizations and institutions manage attendance manually. Faculty record student participation in a log. As the world moves to the modern system, there is a need to track participation in the database. The use of attendance tracking and access control is essential to ensure high security in facilities such as schools. Physical access control systems are important for protecting internal systems. The system has a number of features designed to simplify and optimize the onboarding process. Teachers and administrators benefit from the simple method because they only have to sign the attendance of absent students, thus reducing the amount of money management involved. The system not only makes it easier to keep attendance records, but also helps manage student statistics and create reports for teachers and students to use. The attendance management program featured in this book is a versatile and effective tool that ensures accurate attendance records, encourages student participation, and improves overall learning management techniques in the school environment. Attendance management with this book is a solution designed to increase efficiency, reporting and communication in schools and ultimately create a quality education. This system is a Web-based developed to reduce the human work and will perform attendance in a more modern way.

Keywords: Attendance, Access Control, Tracking, Attendance Records, Database, Security. Cite: Siya Shah, Dr. Vaishali Phalke, Shreyansh Gandhi, Omkar Pawar, Kushal Prajapati, "AttendEase: Simplyfing Manual Attendance Tracking", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13330.

Keywords: Artificial Intelligence, Deep Learning, Machine Learning, Culinary Assistant, Image Recognition, Recipe Retrieval, Culinary Exploration. Cite: Hitha U Karkera, Sripada Adiga, Subramanya K, Srujana J, Mrs. Radha E G,"AI CHEF: AN INTELLIGENT CULINARY EXPERT USING DEEP LEARNING", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13331.

Abstract: Cervical cancer represents a significant global health challenge, particularly in underserved regions where access to conventional screening methodologies is limited. In this study, we investigated the efficacy of deep learning models, including Densenet 201, Vgg16, and Vgg19, trained on the International Agency for Research on Cancer (IARC) Colposcopy Image Bank dataset. The dataset was partitioned into training and validation subsets, and the performance of each model was evaluated on the validation data. Our findings reveal that Densenet201 exhibits superior validation accuracy compared to Vgg16 and Vgg19. The primary objective of this research is to develop a robust and accessible tool for early detection and intervention, with the ultimate aim of alleviating the burden of cervical cancer screening in resource-constrained settings.

Keywords: Colposcopy, Cervical cancer screening, Deep learning. Cite: Karthik Pai, Athmika C Jain, Chirag, Greeshma Jain, Maryjo M George*, "Cervical Abnormality Detection with Deep Learning Powered Colposcopy Analysis", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13332.

Abstract: This project presents an innovative intrusion detection approach that utilizes the combined capabilities of deep neural networks (DNN), multilayer perceptron (MLP), long short-term memory (LSTM), convolutional neural networks (CNN), and fuzzy logic within a unified deep neuro- fuzzy framework. The key differentiator of this system lies in its strategic integration with Principal Component Analysis (PCA) during the training phase, which aims to increase feature representation and overall model performance. A distinctive feature of this system is the incorporation of PCA, a critical pre-processing step that plays a key role in extracting significant features from the CICIDS2017 and CICIDS2019 dataset. By using PCA, the dimensionality of the data set is substantially reduced, allowing the system to focus on the essential information necessary for effective intrusion detection. This dimensionality reduction leads to a remarkable improvement in feature representation, resulting in excellent model performance. PCA integration acts as a catalyst in the training phase, facilitating the extraction of relevant information and optimizing the deep neuro-fuzzy system for increased accuracy and robust generalization capabilities. The results show that this innovative approach not only improves the accuracy of intrusion detection, but also improves the system's ability to adapt to diverse and dynamic threats. Overall, the strategic use of PCA coupled with a unified deep neuro-fuzzy framework sets this system apart, making it a promising advancement in intrusion detection.

Keywords: Intrusion detection, Deep neural networks (DNN), Principal Component Analysis (PCA) Deep neuro-fuzzy framework Cite: Vignesh A Palan, Rathika Ramesh Gaunskar, Prashanth, Pruthviraj, Dr. Amirthavalli.M, "DEEP NEURAL FUZZY SYSTEM FOR INTRUSION DETECTION", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13333.

Abstract: Frame interpolation is a computational technique used in video processing to create additional frames between existing frames, thereby enhancing the smoothness and visual quality of motion in the video.Existing techniques for frame interpolation in videos include path-based and phase-based conventional methods, convolutional neural network (CNN)-based flow-based methods, kernel-based methods utilizing convolution operations over local patches, and recent advancements such as deformable convolution-based approaches like AdaCoF. Addressing the challenges in frame interpolation is essential for developing more efficient and versatile techniques applicable across various platforms and applications. High computational costs, particularly prevalent in methods reliant on deep neural networks (DNNs), hinder deployment on resource-constrained devices or real-time applications. Complexity arises from intricate model architectures or multi-stage processes, complicating both understanding and implementation. Additionally, limited generalization restricts the practical utility of certain techniques, as they may excel on specific datasets but struggle with diverse or unseen data. Methods relying solely on pixel-wise information or local kernels may falter in accurately interpolating frames with complex motion, occlusion, or fine details. Furthermore, the large size of state-of-the-art models poses challenges for storage, training, and deployment, especially on mobile or embedded devices. Addressing these issues is paramount for advancing frame interpolation methods towards greater efficiency, practicality, and applicability across a broad spectrum of contexts and platforms. Our Compression-Driven Framework for Video Interpolation (CDFI) addresses key challenges as follows: Reduced Computational Cost, Simplicity and Efficiency, Improved Generalization, Enhanced Motion Handling, Compact Model Size.

Keywords: Video frame interpolation, Optical flow-based, Real-time solutions, Visual quality, Real-time applications, Stakeholders, Video processing. Cite: Dhruva Kumar Shetty, Pramith A Naiga, Sidhvin P Shetty, Yash Karunakar Shetty, Dr. Maryjo M George, "Frame Interpolation Using FILM", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13334.

Abstract: Using creative approaches, this paper focuses on roles of brain and mind in the use of external and interoceptive senses in human health, stress and longevity related to human survival. The mind is the decision maker for everything that a human does also including dangerous activities. The brain oversees survival. Human decisions based on emotions/logic are controlled by the mind. This paper uses MUSE-2 to study human health focusing on external and interoceptive senses. Cite: Dean M. Aslam,"Brain and Mind Roles and Study of External and Interoceptive Senses Using MUSE-2", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13335.

Keywords: Snellen chart, E chart, Visual acuity test, Speech recognition. Cite: Karthik Raj Shetty, Shreya Bhat, Swasthik, Thrisha, M. Anuburajam,"VisionVue: Remote Visual Acuity Testing", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13336.

Abstract: The concerns rise in driver fatigue-related vehicle collisions has made drowsiness detection in drivers a significant area of study. Experts say that drivers who drive long distance without taking regular rests are at a high risk of experiencing fatigue. Research shows that exhausted drivers in need of rest account for around 25% of all major highway collisions. The purpose of our systems is to spot early indicators of driver exhaustion before they impact one’s ability to drive. This system is a novel approach utilizing deep learning techniques, specifically 2D convolutional neural networks (CNNs), to identify signs of drowsiness in drivers face by analysing facial and eye features. The idea is aimed to use traditional models of multi-layer 2D CNN with multi-label classification and Haar-cascade algorithm. Multiple face signs like eye closures and yawning are considered through the input images to improve the detection accuracy under various driving conditions.

Keywords: Drowsiness detection, Facial recognition, eye detection, yawn detection, multi-label classification, Image-based analysis, Deep learning. Cite: Tejas Rao, Aajna Shyam, Brijesh J S, Yashvi D, Radha E G, "Enhanced Driver Vigilance System", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13337.

Abstract: This project is an innovative web-based application that uses advanced AI techniques for image inpainting, a process of filling in selected regions of an image based on a user-provided text prompt. The application utilizes two powerful models: Stable Diffusion and Segment Anything. The Stable Diffusion model is used for the inpainting process, while the Segment Anything model is used to identify and select regions in the image for inpainting. The user interface, built with Gradio, is intuitive and user-friendly. It allows users to upload an image, select regions on the image, and provide a text prompt that guides the inpainting process. The selected regions are then filled in with content that is generated based on the text prompt, creating a unique and personalized result. In addition to the image inpainting feature, the application also includes a vulgarity speech detection mechanism. This feature uses a trained SVM model to analyze the text prompt and detect any offensive or vulgarity speech. If such speech is detected, the application does not proceed with the inpainting process and instead displays a warning message to the user. The application demonstrates the potential of AI in digital art and content creation, providing a tool that is not only functional but also encourages creativity and personal expression. It also underscores the importance of ethical considerations in AI applications, with its inclusion of a vulgarity speech detection feature. Overall, this project represents a significant contribution to the field of AI-powered digital art, offering a unique tool that combines advanced image inpainting techniques with a user-friendly interface and ethical safeguards.

Keywords: Stable Diffusion, Segment Anything Model (SAM), Gradio, Support Vector Machine (SVM), Vulgarity speech, Text prompts, Image inpainting Cite: Sahan G Kotian, Shreyas Shettigar, Sharan BS, Vishal M Shettigar, Mrs. Anuburajam.M, "VULGARITY DETECTION IN STABLE DIFFUSION INPAINTING WITH SAM ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13338.

Abstract: The widespread circulation of counterfeit currency poses a significant threat to global financial stability and integrity, necessitating effective detection measures. In response to this challenge, this project aims to develop a robust and efficient system for automated counterfeit currency detection, utilizing deep learning methodologies. This research presents a comparative analysis focusing specifically on Indian 500 rupee notes, employing machine learning techniques such as Simple Neural Network (NN) and Deep Learning Convolutional Neural Network (CNN). Diverse datasets comprising images of Indian 500 rupee notes sourced from various outlets are utilized for this study. Performance metrics including accuracy, precision, recall, and F1-score are systematically computed for each technique to evaluate detection effectiveness. Results demonstrate the superiority of the CNN-based approach over the NN method, showcasing higher accuracy and robustness in identifying counterfeit Indian 500 rupee notes. This research significantly contributes to the advancement of automated counterfeit detection systems, particularly within the context of Indian currency. By enhancing detection capabilities and strengthening fraud prevention mechanisms, this work aims to bolster financial security measures on a global scale.

Keywords: Indian fake currency detection, simple neural network, convolutional neural network, image classification, counterfeit detection, financial security. Cite: Mr. K Bhushanm, M.Asritha, P.Rafiya Sultana, P.Anil Kumar, S.Mahesh Babu, "Fake Currency Detection using Deep Learning", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13339.

Abstract: Enterprise Resource Planning (ERP) systems offer significant benefits, but data migration poses a major challenge during implementation. Converting legacy data accurately into the ERP environment is critical, as data quality issues can disrupt operations, financial reporting, and decision-making. This paper provides a comprehensive analysis of ERP data conversion strategies and best practices to help organizations plan and execute successful migration projects. The research evaluates the pros and cons of prevalent conversion methodologies, including Big Bang, phased and parallel approaches. While Big Bang migration appears faster and cheaper, it is highly risky for most organizations. Phased conversion is widely seen as the optimal approach, especially for larger firms with complex legacy landscapes. Incrementally migrating data by module or location constrains the scope of potential issues. Selective parallel runs of old and new systems provide a valuable safety net for critical data. Automated conversion tools are also essential to handle today's data volumes efficiently. However, algorithms must be combined with human oversight and robust testing to validate conversion logic. The most successful migration initiatives invest heavily upfront in data profiling, cleansing, mapping, and governance. Proactive planning avoids disruptive legacy data issues from cascading into the ERP system. Ultimately, the right conversion approach aligns with the overall ERP strategy and balances transformation goals with risk mitigation. By prioritizing data quality, organizations are better positioned to realize the full potential of their ERP investments. The findings provide a valuable framework for managers to assess conversion trade-offs and make informed decisions in planning ERP data migration projects.

Keywords: ERP, data conversion, data migration, legacy systems, phased implementation, automation Cite: Tirumala Rao Chimpiri, "Ensuring Data Quality in ERP Implementations: Key Conversion Considerations", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13340.

Abstract: In today's fast-paced world, effective communication and collaboration are important, as meetings become the core for productive discussion and decision-making. Nevertheless, the manual transcription method continues to plague meetings and be a time-consuming error-prone torture. To overcome this challenge, our project, 'AutoMeet,' presents an innovative solution: a real-time automated meeting minutes generation system, including real-time speech detection, and a summarized meeting summary. AutoMeet operates live during the meeting. Our integrated system relies on the most advanced speech recognition systems to convert spoken words into transcribed text while maintaining the nuances and meaning of the conversation. It then uses text-to-speech technology to intelligently parse the notes into a transcript containing conclusions, key points, and content discussion. Automatic Meeting also includes real-time audio detection and recording of speakers participating in the conversation. This further enhances the system's ability to capture and rate what the speaker is saying, even in a dynamic conversational environment. AutoMeet revolutionizes the traditional meeting recording process, streamlining these critical tasks, saving organizations time, and increasing productivity. Most importantly, it makes the outcomes of the meeting more effective and efficient, thus making the meeting more efficient, effective, and collaborative across the business and the environment. AutoMeet offers new features to simplify workflows, giving organizations cutting-edge tools to harness the true power of meetings.

Keywords: Automated meeting minutes generation, Meeting summarization, Speech recognition, Text summarization, Real-time speech detection, Artificial intelligence, Deep learning, Machine Learning, Natural Language Processing. Cite: Mohammed Rumaan, Salwa Imthiyaz Ahamed, Muhammed Sinan, Brinda Shetty, Mrs. Vasudha G Rao,"Automeet: AI-Powered Automated Meeting Transcripts", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13342.

Abstract: A Distributed Denial-Of-Service (DDoS) assault is a hostile activity that aims to overload a server, service, or network with excessive network traffic, rendering it unusable. The fact that attack patterns are constantly shifting, cyber offense techniques are developing quickly, and cyber offense materials are freely available on the dark web have made this a difficult task. DDoS assaults have the potential to seriously impair online services, resulting in lost profits, harmed reputations, and dwindling client confidence. Additionally, it may lead to overheating or power outages, which could harm infrastructure. Taking into account all of these factors, this research focuses on predicting and classifying DDoS attacks through the analysis of network traffic data using a deep learning technique to automate the manual process. In the end, this can reduce human error in the detection process and save time and effort. This project trains the "DDoS Evaluation – CICDDoS2019" dataset using the power of the Long Short Term Memory(LSTM). To improve the accuracy of anomaly detection, the LSTM is trained in an unsupervised environment to recover encoded data. In a monitored setting, the LSTM is trained to categorize network traffic data into DDoS attacks. Keywords: Distributed Denial-Of-Service (DDoS), Deep Learning, Long Short Term Memory(LSTM) Cite: Sharan K R, Shreekavya C H, Rony Dominic, Soniya A Gunagi, Vasudha G Rao, "Detection of DDoS Attack Using Deep Learning", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13343.

Abstract: The rise of deepfake technology poses a significant threat to the authenticity and integrity of multimedia content, including audio recordings. In response to this challenge, this project proposes a deep learning-based approach for detecting deepfake audio. Leveraging advancements in machine learning and signal processing, the proposed system aims to distinguish between genuine and manipulated audio recordings with high accuracy.The project begins with a comprehensive exploration of existing deepfake detection techniques, focusing on their limitations and strengths, particularly in the context of audio manipulation. Subsequently, a novel deep learning architecture is designed and implemented to effectively capture the subtle cues and patterns indicative of audio manipulation.Key components of the proposed system include feature extraction modules tailored to the unique characteristics of audio data, as well as deep neural network models trained on large-scale datasets of both genuine and deepfake audio samples. Through extensive experimentation and evaluation, the effectiveness and robustness of the developed system are assessed across various types of audio manipulation techniques and levels of sophistication.

Keywords: Deepfake, Audio manipulation, Deep learning, Detection, Feature extraction, Neural networks Cite: Ankith Shetty, Hanzala Karani , Shreya K H, Raheeza Khan, Mr. Amruth A G,"Deepfake Audio Detection using Deep Learning", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13344.

Abstract: In today's era of rapid growth across all sectors, including agriculture, meeting future food demands necessitates the adoption of new techniques. To address this need, this project focuses on the "Design and Fabrication of a Solar Seed Sprayer Machine." This innovative approach involves spraying seeds from a hopper onto the land using a fan or blower, eliminating the need for human effort during seeding. By streamlining the process, seeds are efficiently sown during ploughing, reducing both time and labor. Notably, this machine operates solely on solar power, eliminating the need for additional energy sources. Overall, this system offers a sustainable and efficient solution to enhance crop production while preserving soil texture and minimizing human involvement. A seed sprayer machine is a piece of agricultural equipment used for sowing seeds onto fields. It operates by dispersing seeds evenly across the soil surface, ensuring optimal seed-to-soil contact for germination and crop growth. These machines come in various sizes and configurations, ranging from handheld seed spreaders for small-scale farming to large tractor-mounted seed drills for commercial agriculture. Seed sprayer machines typically consist of a seed hopper, which holds the seeds, and mechanisms for seed distribution, such as pneumatic systems, augers, or seed plates. Some modern seed sprayer machines may also incorporate precision technologies, such as GPS guidance systems and variable rate seeding, to optimize seed placement and maximize crop yield.

Keywords: Seed Sprayer Machine, Relay, Bluetooth Module, Robot, Solar Panel, DC Motors. Cite: Prof. R. B. Khule, Kundan Gahukar, Bhawar Ninawe, Sourabh Balbudhe, "Development and Manufacture of Solar Power Seed Sprayer Machine", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13345.

Abstract: Artificial intelligence (AI)-generated images intended to incite social and economic unrest have become more widely shared since the introduction of advanced AI tools. AI-generated images using Generative Adversarial Networks (GANs) are frequently used to create content that makes it difficult to discern between real and artificial content. As a result, false information is spread along with an increase in cybercrimes. The goal of this proposed work is to detect these AI-generated images by building a Convolutional Neural Network (CNN) model. This CNN model will be trained to distinguish between real and AI-generated images. This strategy will support the preservation of social and economic stability, which may be jeopardized by improper use of images produced by artificial intelligence in informational campaigns. It will also aid in the prevention of cybercrimes like image forgery and impersonation that are caused by AI-generated images.

Keywords: Generative Adversarial Networks (GANs), Convolutional Neural Network (CNN), AI-Generated Images Cite: Akshatha Nayak, Harsha, Prajeet Chendekar, Shreevatsan A, Sunil Kumar S*, "Detection Of AI Generated Images Using Machine Learning and Deep Learning Models", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13346.

Keywords: Text Extractor, OCR-NER, Form Filling, Automation, Software Solution, Optical Character Recognition, Named Entity Recognition, Data Extraction, Document Management, Data Processing. Cite: Prajwal U, Shodhan Kumar Shetty, Sujan J Acharya, Swapnil Shetty, Maryjo M George, "TEXT EXTRACTOR: OCR-NER FORM FILLING AUTOMATION", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13347.

Abstract: In today's technology, most of the customers have to make an appointment in supermarkets to shop because it is a time-consuming process. Due to the barcode payment system, large crowds in supermarkets during discount periods or holidays can cause long queues. Smart stores with RFID data modules are a revolution that improves traditional products using radio frequency identification (RFID) technology. The aim is to simplify and improve the purchasing process, making it more efficient, convenient and personal for retailers and customers. All products are equipped with an RFID tag containing personal information, allowing tracking and management of the entire supply chain. The project offers a smart way for people to pay for items while shopping and provides an Android app-based smart trolley assistant for people walking in supermarkets. Keywords: RFID reader; RFID tags; Arduino Micro-controller; Bluetooth Module; Switch; LCD Display etc. Cite: Prof. S. A. Bagal , Rohini J. Bisen, Prajakta N. Ramteke, Yash U. Mate,"Development of Smart Shopping Trolley Using RFID Data Module", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13348.

Abstract: Stuttering, a complex speech disorder, presents significant challenges in both diagnosis and treatment. In this study, we propose a novel approach for predicting stuttering severity in Kannada speech, aimed at enhancing therapeutic interventions for individuals affected by stuttering. Leveraging a dataset comprising video recordings of therapy sessions, our methodology involves the extraction of acoustic features from 3-second audio segments, including mean pitch, intensity, speech rate, and MFCCs. These features, along with annotations for disfluency types such as prolongation, repetition, and block, form the basis of a comprehensive dataset. Through the application of a CNN-LSTM hybrid neural network, we demonstrate promising results in predicting stuttering severity, with implications for personalized therapy strategies. Our research underscores the potential of machine learning techniques in improving the diagnosis and treatment of stuttering, paving the way for more effective interventions and improved outcomes for individuals with this speech disorder.

Keywords: MFCCs, CNN-LSTM, Kannada speech, stuttering. Cite: Hemanth RangeGowda S P, M Chinmaya Rao, Nishanth S Raj, Rakshitha Jain, Mr. Amruth Ashok Gadag, Mr. Sunil Kumar S, Dr. Rakesh C V, Dr. Shubhaganga D, Dr. Santosh M,"STUDS, Speech Therapy Utility for Detection and Analysis of Stuttering", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13349.

Abstract: Brain stroke prediction is a critical task in healthcare, as early detection can significantly improve patient outcomes. In this study, we propose an ensemble learning framework for brain stroke prediction using convolutional neural networks (CNNs) and pretrained deep learning models, specifically ResNet50 and DenseNet121. The ensemble model combines the strengths of these architectures to enhance predictive performance. Firstly, the CNN extracts relevant features from brain imaging data. Then, ResNet50 and DenseNet121, renowned for their efficacy in image classification tasks, further refine these features through deep learning-based feature extraction. The ensemble model integrates the predictions from these individual models to make a final prediction.

Keywords: Ensemble learning, Classification, CNN, Resnet50, DenseNet121 Cite: Nandu Krishna G, Neha Mashoora, Nisar Ahamed P, Dr.Amirthavalli. M,"BRAIN STROKE PREDICTION USING ENSEMBLE LEARNING", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13350.

Abstract: Heart disease remains a significant global health challenge, contributing to substantial morbidity and mortality rates. Early identification of individuals at risk of developing heart disease is crucial for implementing preventive measures and improving patient outcomes. In recent years, machine learning techniques have emerged as powerful tools for predicting heart disease risk by analysing various clinical and demographic factors. In this study, we investigate the efficacy of the Random Forest Classifier, an ensemble learning algorithm, in predicting heart disease risk. The study leverages a comprehensive dataset containing demographic information, clinical measurements, and lifestyle factors collected from diverse sources such as electronic health records and surveys. Keyword: Heart disease, Risk prediction, Random Forest Classifier, Machine learning, Ensemble learning, Predictive modelling, Feature engineering, Data preprocessing, Clinical decision-making, Healthcare Cite: Vijay V. Chakole, Dimple Bhave, Srushti Choudhari, Prathamesh Chaudhari,"HEART DISEASE DETECTION USING RANDOM FOREST", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13351.

Abstract: Writing lengthy lines is a bit tedious, but the text prediction feature on the keyboard makes things easier. In the field of the study of natural languages, Next-Word Prediction (NWP), Often referred to as language modelling,is a machine learning tool that has the ability to anticipate the word that will come after a letter in a phrase or sentence. Users may select a word at will from the list of suggested words provided by the system and it offers many different word substitutions. The long short-term memory (LSTM)formula can recognize previous text and predict words, which can be helpful to users in sentence construction. This approach uses letter-by-letter prediction, meaning it predicts a word when a letter forms a word.

Keywords: Machine Learning, Next-Word Prediction(NWP), LSTM,.NLP Cite: Allamsetty Krishna Teja, Bathula Srinivasa Reddy, Talagadadeevi Jyothish Sai,Padala Bharath vamsi, Lavanya Kongala, "Revolutionizing Sentence Completion: Pioneering a Machine Learning Paradigm for Next Word Prediction", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13352.

Abstract: The project targets flaws including blur, haze, scratches, color fading, and absence of color in an effort to recover old and damaged photos using a deep learning paradigm. The three GAN frameworks are integrated in a certain order to enable complicated regeneration. After patching or restoring scratches, a partial image is restored using an inpainting technique based on OpenCV. By using effective deep learning techniques, the ultimate objective is to improve the quality and accessibility of restored photos. By using deep learning and cutting-edge approaches to solve issues including blur, haze, scratches, color fading, and lack of color, the project seeks to restore old and damaged images. Three separate GAN frameworks, each with a unique function in the restoration process, are sequentially integrated to enable complicated regeneration. After scratch patching, a OpenCV-based inpainting method is used to fill in the gaps in the image and restore a portion of it. Furthermore, certain GAN frameworks are used to manage the rest of the restoration process, making use of their individual advantages in image creation and enhancement. In the meantime, thorough restoration is ensured by the efficient detection and identification of scratches. The initiative hopes to increase the quality of recovered pictures and make them more accessible for a greater variety of uses by utilizing these advanced deep learning techniques.

Keywords: Generative Adversarial Networks (GAN), Artificial intelligence, Deep learning, OpenCV, Convolutional Neural Networks (CNNs). Cite: Dr. Dinesha L, Harsh Shetty, Mandira Hegde, Nesara G S, Anusha, "Regeneration Of Scratched Images Using Deep Learning", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13353.

Abstract: The process of tendering is generally utilized by governments and businesses to source goods or services from manufacturers or service providers. Nonetheless, with e-tendering being the most commonly employed procurement method, there exist various security concerns. Blockchain technology offers a potential solution to address these security issues by emphasizing information decentralization and incorporating robust encryption within an immutable block-based framework for managing transactions. This article delves into the utilization of smart contracts (built on ethereum blockchain) in developing a decentralized e-tendering system. The paper is segmented into four key phases: 1.Tender Creation and Publication 2.Bid Submission 3.Bid Evaluation and Negotiation 4.Bid Selection . Diverse algorithms are harnessed to execute each step. The security and transparency challenges are assessed and juxtaposed against the existing tendering process. The primary objective of this study is to establish an impartial, transparent, and publicly accessible tendering model. At the end of the bid selection we will add an Escrow account between two parties , where authorized work will be done between them . both parties can review their work . This will results in trust between two parties.

Keywords: Blockchain, Fair and Open Tendering Scheme, Smart Contract, E-Tender. Cite: Sri Venkat Chennu, Aneesh Gonu, Kiran Manukonda, Babu Naik Mudavath, "Distributed e-Tendering System using Escrow-Account", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13354.

Abstract: Millions of people are suffering from mental illness due to unavailability of early treatment and services for depression detection. It is the major reason for anxiety disorder, bipolar disorder, sleeping disorder, depression and sometimes it may lead to self-harm and suicide. Thus, it is a very challenging task to recognize people who are suffering from mental health disorders and provide them treatments as early as possible. In this proposed system, we are developing a hybrid model for depression detection using deep learning algorithms, by analysing textual features and audio features of patient's responses. Proposed system consists of a textual CNN model in which a CNN model is trained with only text features and an audio CNN model in which CNN model is trained with only audio features. System uses model parameters such as precision, F1-score, recall and support are found for evaluation of models.

Keywords: Depression Detection, Deep Learning, Hybrid Model, Textual Features, Audio Features, Convolutional Neural Network (CNN), Early Intervention, Mental Health Disorders, Machine Learning, Data Collection, Feature Extraction, Precision, F1-Score, Recall, Support, Mental Health Support, Text Analysis, Audio Analysis, System Architecture, System Requirements Cite: Arencheruvu Dinesh, Arsh Ahmed, Hasan Shifan, Ms. R Lalitha, "HYBRID MODEL FOR DEPRESSION DETECTION USING DEEP LEARNING", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13355.

Abstract: The extent, width, curvature, and branching pattern of the retina’s blood vessels, among other structural character- istics, plays a major role in the assessment of diseases related to diabetes and heart, hypertension. Through our research, we offer a procedure for segmenting the retinal vascular system firm FCNs. From every retinal image, thousands of patches are gathered, and these patches are rotated before being sent via the network for Data Augmentation. For vessel segmentation, two FCNs are used: LadderNet Architecture and U-Net Architecture. Three well-known datasets: STARE, CHASE_DB1, and DRIVE are used to evaluate our methodology. When compared to the other previously mentioned methodologies, our strategy indicates better performance.  Keywords: Retina, Vessels, Convolutional, U-Net, Ladder-Net, Opthalmology. Cite: Bhupathi Rayudu Inaganti, Prasanth Yenumula, Selvam K, Jahnavi Bandaru,Varaha Varshini Naidu Polamarasetty, "Retinal Vessel Segmentation Using CNN And U-Net Architecture", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13356.

Keywords: Natural Language Processing, Next.js, RNN Cite: Ajit Poddar, Amogha Kumar Shetty,Ankith M Rao, Danish M Rehman, Ashwin Kumar M, "HEALTHCARE VIRTUAL ASSISTANT", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13357.

Keywords: Hepatocellular Carcinoma detection, Cirrhosis detection, Multi-modal data integration, Blood biomarkers data analysis, Image based analysis, Random Forest, Convolutional Neural Network. Cite: Raksha Nayak, Sankalp S Naik, Sannidhi B M, Tejaswini Peeru Gouda, Mr. Vijayananda V Madlur, "A Deep Learning Approach to Detect Cancer in Cirrhotic Liver", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13358.

Keywords: Deep Learning, Deepfake, Neural Network, Artificial Intelligence, InceptionResnetV1, InceptionResnetV2 Cite: Mr. H.M. Gaikwad, Aryan Sonawane, Manavaditya Rathawa, Ratnali Pawar, Uday Talele, "Deepfake Face Detection System ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13359.

Abstract: The rising demand for advanced healthcare solutions has driven the development of innovative technologies aimed at improving patient care. This project introduces a Real-Time Patient Health Monitoring System, which utilizes cloud technology to its full potential. By incorporating cloud infrastructure, data science, and real-time analytics, the system offers continuous monitoring and analysis of crucial health metrics such as heart rate (ECG) sensor, temperature, pulse rate and blood oxygen saturation (SPO2) sensors. Designed with wearability in mind, the system's architecture ensures uninterrupted monitoring and instant feedback for both patients and healthcare professionals. Cloud technology enables seamless data storage, retrieval, and real-time analysis, thereby providing comprehensive insights into a patient's health status. The project's scalability guarantees its suitability for various healthcare environments, rendering it a versatile tool for hospitals, clinics, and remote health care scenarios.

Keywords: IOT, Smart Monitoring, Health Remote, Communication etc. Cite: Prof. Vijay. V. Chakole, Nutan Amru, Anshul Ganorkar, Khushbu Bihone, Ankit Dhote, "A Methodology On Real Time Patient Health Monitoring System Using Cloud Technology", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13360.

Abstract: The art of music transcription, transforming fleeting audio recordings into the permanence of sheet music, holds immense potential for musicians, educators, and historical preservationists. This project embarks on an exploration of Recurrent Neural Networks (RNNs) as a powerful tool for automated music transcription. The focus here is on meticulously converting MP3 audio files into MIDI files, subsequently translating them into comprehensive and expressive musical notations. The proposed RNN model aspires to achieve groundbreaking accuracy in capturing the very essence of music – pitch, rhythm, and duration – directly from audio recordings. This feat, if achieved, would transcend mere note recognition and delve into the heart of what makes music so captivating. By effectively translating the intricate language of audio into the symbolic language of musical notation, the model paves the way for a more profound understanding and appreciation of music.

Keywords: Music notes classification,Artificial intelligence,Deep learning,Musical Transcription ,Frequency based analysis, Machine learning,Pitch identification. Cite: Harshitha, Prabhanjan Hippargi, Shobith R Acharya, Shreya S Poojary, Ms. Amrutha, "Automatic Music Transcription To Music Notes Using Artificial Intelligence", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13361.

Abstract: Venomous snakebites are a significant public health concern in India, where numerous venomous snake species coexist with humans. Prompt and accurate identification of venomous snakes is crucial for effective medical treatment and wildlife management. In this study, we propose a Convolutional Neural Network (CNN)-based approach for venomous snake detection, specifically focusing on the classification of Indian snake species. Our methodology involves assembling a diverse dataset comprising images of various venomous and non-venomous snake species found in India. Through rigorous preprocessing and augmentation techniques, we train a CNN model capable of accurately distinguishing between venomous and non-venomous snakes. Leveraging the deep learning capabilities of CNNs, our model automatically extracts intricate features from snake images and learns discriminative patterns for classification. Evaluation of the model's performance using standard metrics demonstrates its effectiveness in venomous snake detection. These findings underscore the potential of CNN-based approaches in aiding venomous snakebite mitigation efforts and contributing to wildlife conservation endeavours in India and similar biodiversity-rich regions.

Keywords: Venomous snakes, Deep Learning, Classification, Indian snake species. Cite: K Ankith, Manoj, Mohammed Nihal, Mohinuddin Razi, Ms. Shwetha CH, "Venomous Snake Detection: A CNN-Based Classification of Indian Snake Species", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13362.

Abstract: Rainfall forecasting is essential for a few industries, including agriculture, water resource management, and flood forecasts. Rainfall prediction is most important, but now-a- days rainfall forecasting has grown to be a difficult issue. The ability to take safeguards is made possible by accurate rainfall predictions. To anticipate the dependent variables temperature, humidity, location, wind speed, and direction the rainfall prediction is dependent on a few constantly shifting factors. The weather calculation also varies according on the location's geographic characteristics and atmospheric variables. Cite: Divya Sri.M, Venkata Sai Bhargav.K, Chandra Kireeti.K, Lahari Priya.M, K. Rajeshkumar , "Rainfall Prediction using Hybridized Genetic Algorithm-Based Artificial Neural Network (GA-ANN) and Genetic Algorithm-Based Support Vector Machine (GA-SVM) Models.", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13363.

Abstract: This project is about technique or approach in finding anomalies, which represents deviations from expected patterns, can signify critical events of irregularities, malfunctioning of sensors, demanding accurate detection. Internet Of Things (IoT) represents a framework that links physical devices to the internet, allowing them to communicate and exchange data. The quality of IoT services usually depends on the integrity and accuracy of the data. Time series is a common type of data found in everyday situations like traffic flow, network performances, financial records, etc. Detecting anomalies in time series IoT sensor data is very much needed because of the possibility of noise and unavailability of labels in the sensor readings and it’s also an important research topic with practical uses such as spotting intrusions in networks, monitoring traffic, and identifying errors in sensor data. In this project  the Inter-Berkeley Research Lab dataset is used for unlabeled anomaly detection technique and UNSW-NB15 IoT weather board sensor dataset is used for labelled anomaly detection, which is suitable for testing and validating different anomaly detection methodologies. This project is proposed to work on  hybrid models such as , LSTM – Autoencoder +Isolation Forest, Bi – LSTM + OneClass SVM, an Ensemble model of DBSCAN, LOF, SVM, and a Statistical approach for anomaly detection in IoT sensor Time Series Data, using the results to understand better about the performance of these proposed models.

Keywords: Internet Of Things (IoT),Bidirectional Long Short-Term Memory( Bi-LSTM),One-Class Support Vector Machine( One-Class SVM),Density-Based Spatial Clustering of Applications with Noise.(DBSCAN),Local Outlier Factor (LOF). Cite: Shibzan Shahanas, Afnaj Akthar, Saanna Anand, Rakshitha, Dr. Amirthavalli.M, "ANOMALY DETECTION IN TIME SERIES DATA IN IoT ENVIRONMENT", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13365.

Abstract: The importance of plant disease detection in contemporary agriculture is emphasized in this paper, along with how it can reduce crop losses and increase food security. The emphasis is on Convolutional Neural Networks (CNNs) as a powerful instrument for automating the detection of plant diseases by examining the visual indicators present in leaf photos. The paper explores issues including dataset quality, model generalization, and real-world implementation while highlighting CNNs' outstanding ability to quickly and accurately distinguish between healthy and infected plants. Ethical issues such as responsible data use and model bias are addressed along with the need for large, diverse, and well-annotated datasets. In order to advance the creation and implementation of CNN-based plant disease detection systems, the abstract ends with a strong argument for cooperative research. Keyword: CNN, automation, dataset, real-world, prediction, ML model. Cite: Namrata, Niya Rani, Shivani, Pooja Tripathi, "PLANT DISEASE DETECTION USING ML REVIEW PAPER", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13366.

Abstract: Dermatology remains one of the foremost branches of science that is uncertain and complicated because of the sheer number of diseases that affect the skin and the uncertainty surrounding their diagnosis. The variation in these diseases can be seen because of many environmental, geographical, and gene factors and the human skin is considered one of the most uncertain and troublesome terrains particularly due to the presence of hair, its deviations in tone and other similar mitigating factors. Skin disease diagnosis at present includes a series of pathological laboratory tests for the identification of the correct disease and among them, cancers of the skin are some of the worst. Skin cancers can prove to be fatal, particularly if not treated at the initial stage. The idea behind this project is to make it possible for a common man to get a sense of the disease affecting his/her skin so they can get a head start in preparing for its betterment and the doctor in charge can get an idea about the type of cancer which helps them in the diagnosis. Users are greeted with a login page, and when they log into the home page, users can upload an image of the diseased part of their skin. The trained model gives a prediction, following which the users can take the necessary steps to contain the disease. Cite: Aishwarya Tamse, Annapoorna Pai, Arundhathi Nayak, Mithali Prashanth Rao, Shreejith K B*, "A DEEP LEARNING APPROACH TO DETECT SKIN CANCER USING DERMOSCOPIC IMAGES", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13367.

Abstract: The use of electroshock weapons such as Tasers is already common among police officers and prison officers, as well as defence agencies. It is a way to immobilize and control a person. Despite their efficiency, these devices have a long history of accidents, some resulting in serious injury or death. Knowing these risks, it is necessary to look for alternatives that balance efficiency and safety. The program introduced the concept of "falling" as a potentially less dangerous option designed to offset the negative effects of AI. Tasers provide better safety for officers and trainees while protecting a critical need for law enforcement. This debate provides an in-depth look at the design, function and effectiveness of stun sticks, advocating for a change to stun sticks being considered in regular debates around whether the options are good for authorities.

Keywords: TASERS, Personal Safety Device, Women Safety, Less Lethal, Electroshock Device. Cite: Jyotsna. S. Gawai, Janhavi S. Margoni , Piyush Y. Mohod, Pushkar R. Thakare, "Development of Less Lethal Safety Device Stun Stick", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13368.

Keywords: Ultrasonic imaging, Deep learning, Machine learning techniques, Segmentation, Classification, Early diagnosis, Successful therapy, Breast tumour Cite: Dr. Dinesha L, Deeksha Prabhu, Deepika, Vaibhav R Jadhav, Mohammad Shihabul Faiez, "Breast Tumor Segmentation and Classification Using Ultrasound Images", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13369.

Abstract: Leveraging DenseNet architecture, our novel approach to Parkinson's disease detection focuses on analyzing spiral and wave images derived from handwriting samples, a method proven to capture subtle motor abnormalities characteristic of the condition. By training the model on a dataset comprising annotated samples from individuals with clinically confirmed diagnoses, our system learns to discern distinctive patterns indicative of Parkinson's disease. Through the integration of traditional image processing techniques for preprocessing, we enhance the model's ability to extract relevant features from handwriting patterns. The multi-label classification enables not only the identification of Parkinson's disease presence but also offers insights into its severity and progression. This comprehensive approach empowers clinicians with a reliable tool for early diagnosis and personalized treatment planning, ultimately improving patient outcomes and quality of life.

Keywords: DenseNet architecture, Parkinson's disease detection, Spiral and wave images, Handwriting samples, Motor abnormalities, Early diagnosis Cite: Shikha Ballal, Sourabha Jain, Sweedle Suares, Gururaj, Dr.Rejeesh Rayaroth,"Detection and Risk assessment of Parkinson’s disease : A Machine Learning Approach ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13370.

Keywords: PCOS detection, Manual data analysis [physical symptoms], Image based analysis[ultrasound Image], Random Forest, Convolutional Neural Network. Cite: Gowri N, Jani Kalianpur, Shravya, Thanmayee N Shetty, Dr Babu Rao K,"DETECTION OF POLYCYSTIC OVARY SYNDROME USING DEEP LEARNING ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13371.

Abstract: Diagnosing and monitoring drug use creates important challenges in the medical and social fields. Traditional methods have relied heavily on self-reports, which can be unreliable due to various factors such as social bias and memory bias. In recent years, there has been a growing interest in using machine learning techniques to augment or replace traditional approaches to drug detection. This paper provides a comprehensive overview of the current state of the art in machine learning-based drug use diagnosis. Describes common preprocessing steps for cleaning and preparing data for analysis, including feature extraction and dimensionality reduction techniques. We then take a closer look at various machine learning algorithms and models used for drug detection, including random forests, deep learning architectures, and ensemble techniques. We discuss the strengths and weaknesses of each approach and highlight recent advances and challenges. Additionally, we discuss ethical considerations for using machine learning in this context, including privacy concerns, algorithmic bias, and the impact of false positives and negatives. Finally, we identify potential avenues for future research, including developing more robust and interpretable models, integrating multiple data methods to improve accuracy, and exploring real-time monitoring systems. Overall, this review highlights the potential of machine learning to revolutionize drug use diagnosis and highlights the importance of interdisciplinary collaboration to address the complex challenges inherent in this field. Cite: Ajay Shetty, Chirag V, Darshan U Shetty, Disha P, Dr. Babu Rao K, "DRUG CONSUMPTION DETECTION USING MACHINE LEARNING", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13372.

Abstract: The agricultural industry, pivotal for global food security and sustainability, grapples with a persistent challenge posed by insect pests wreaking havoc on crops. Identifying these pests and discerning their maturity stages are crucial for effective pest management and safeguarding crop yields. Traditional manual identification methods prove imprecise, time-consuming, and often inefficient, even for seasoned agronomists, due to visual similarities among insect species, especially at identical maturity stages. Notably, deep learning emerges as a prominent approach, albeit demanding extensive labeled datasets for effective training, a resource that remains scarce, demanding, and insufficient in addressing the wide-ranging variability within insect classes. Additionally, integrating pesticide recommendation systems could enhance pest management strategies, aiding in the selection of appropriate treatments for specific pests and crop types. This research proposes a solution to this problem using a few-shot learning approach as a solution to this predicament, delving into insect classification for pest management. A few-shot prototypical network is proposed based on a comparison with other state-of-art models and divergence analysis. Experiments were conducted separating the adult classes and the early stages into different groups, and at last recommending suitable pesticides that will help in th yeilding of good crops.

Keywords: Few-shot learning; Insect pest classification; Insect maturity stages; Convulution Neural Network; Prototypical Networks. Cite: Birajdar Siddanna Gurabala, Saloni, Shreya Shetty, Varshitha G V, Ms. Sunitha N V, "INSECT PEST IMAGE RECOGNITION AND MATURITY STAGES CLASSIFICATION USING FEW-SHOT MACHINE LEARNING APPROACH", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13373.

Abstract: Paddy leaf diseases pose a significant threat to global rice production, impacting food security and economic stability. This study explores the application of machine learning, specifically convolutional neural networks (CNNs), for the automated recognition and classification of paddy leaf diseases. The proposed CNN model analyzes leaf images to detect common diseases such as brown spot, leaf blast, and leaf blight. Leveraging advanced image processing techniques, the system achieves high accuracy in disease identification, enabling timely interventions to mitigate crop losses. Key aspects of the project include dataset preparation, model training, and performance evaluation. Through this research, we contribute to the advancement of precision agriculture and sustainable crop management practices.

Keywords: Paddy leaf diseases, Machine learning, Convolutional neural networks, Automated recognition, Crop management. Cite: Divyata J, Amrutha2, Harshitha, Likhitha, Pavana, "Recognition and Classification of Paddy Leaf Disease using CNN", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13374.

Abstract: Effective learning results in modern educational environments increasingly depend on attending to students' different learning preferences and styles. This study describes a complete methodology that builds personalized learning methods for individual students by fusing state-of-the-art machine learning algorithms with well-established educational frameworks. In particular, we suggest combining the VARK model, Glove embedding, and the Long Short-Term Memory (LSTM) method to create a strong foundation for individualized instruction. The VARK approach divides students into four learning styles: kinesthetic, visual, auditory, and reading/writing.

Keywords: Personalized learning, machine learning, LSTM algorithm, VARK model, Glove embedding, learning styles, text classification. Cite: Dr.M.Srinivasa Sesha Sai, Lokireddy Nagalakshmi, Mandadi Poojitha,Lingala Keerthana, LellaVenkata Kavya, "Customized learning strategies for students", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13375.

Abstract: Heart disease persists as a leading global cause of mortality, necessitating effective prevention and treatment approaches. This paper thoroughly examines diverse facets of heart disease, encompassing its various types, etiology, symptoms, and treatment modalities. Emphasis is placed on the crucial significance of early detection and technology-driven diagnostics. Machine learning, a subset of artificial intelligence, emerges as a potent tool for heart disease classification. The paper explores machine learning methodologies, including supervised, unsupervised, and deep learning, highlighting their potential to enhance diagnostic precision. The chosen title is aptly justified by the urgent necessity for early intervention, the promising impact of machine learning, its ongoing advancements, and the potential to bolster awareness and investment. By illuminating this intersection, our aim is to fortify the battle against heart disease, ultimately improving patient outcomes worldwide.

Keywords: Heart disease, prevention, treatment, early detection, machine learning, classification, artificial intelligence, technology, diagnosis, patient outcomes. Cite: Seema S Awathare, Samiksha G Gajbhiye, Diksha K Bambulkar,Simarn S sahare,Mrunali S Shende, Prof.Miss Vaishnavi Ganesh, "Heart Disease Prediction Using Machine Learning ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13376.

Abstract: This project focuses on developing a system for human face and action recognition through CCTV surveillance, leveraging deep learning algorithms. By uploading CCTV footage videos and individual photos of persons of interest, the system aims to detect, track, and recognize faces and actions in real-time. The output provides the identified person's face, recognized actions, and a unique identifier along with timestamps indicating when the action occurred. Key components of the system include the YOLO v8 algorithm for object detection, Deep SORT algorithm for object tracking, and FaceSDK for face detection and recognition. The integration of these advanced technologies aims to provide a comprehensive solution for enhancing security measures and facilitating forensic analysis in surveillance environments. Through the utilization of deep learning techniques, the project contributes to advancing the capabilities of CCTV surveillance systems in recognizing and analysing human activities effectively.

Keywords: Human face recognition, Action recognition, CCTV surveillance, Deep learning, YOLO v8, Object detection, Deep SORT, Object tracking, FaceSDK, Forensic analysis, Security measures, Timestamp, Facial detection.

Abstract: The abstract introduces the pressing issue of Chronic Kidney Disease (CKD) and underscores the importance of early identification to mitigate its progression and enhance patient outcomes. It highlights the increasing utilization of machine learning (ML) algorithms for CKD prediction but identifies a need for more accurate and efficient models. The paper aims to fill this gap by conducting a thorough literature review on CKD prediction using ML techniques, analyzing features, datasets, algorithms, and evaluation metrics utilized in existing studies. Additionally, it proposes a novel approach that combines different feature selection and ML techniques to improve prediction accuracy. The findings demonstrate the potential of ML algorithms such as support vector machines, random forests, and neural networks to achieve high accuracy in CKD prediction, with the proposed approach enhancing accuracy by up to 5%. The implications of this study suggest the development of more effective CKD prediction models that could positively impact clinical practice and patient outcomes.

Keywords: Chronic Kidney Disease (CKD), Machine Learning (ML), Prediction, Feature Selection, Datasets, AlgorithmsEvaluation Metrics, Support Vector Machines (SVM), Random Forests, Neural Networks, Accuracy Improvement, Clinical Practice, Patient Outcomes, Healthcare Management, Early Identification.

Abstract: As a coastal state, Tamil Nadu faces uncertainty in agriculture which decreases its production. With more population and area, more productivity should be achieved but it cannot be reached. Farmers have words-of-mouth in past decades but now it cannot be used due to climatic factors. Agricultural factors and parameters make the data to get insights about the Agri-facts. Growth of IT world drives some highlights in Agriculture Sciences to help farmers with good agricultural information. Intelligence of applying modern technological methods in the field of agriculture is desirable in this current scenario. Machine Learning Techniques develops a well-defined model with the data and helps us to attain predictions. Agricultural issues like crop prediction, rotation, water requirement, fertilizer requirement and protection can be solved. Due to the variable climatic factors of the environment, there is a necessity to have a efficient technique to facilitate the crop cultivation and to lend a hand to the farmers in their production and management. This may help upcoming agriculturalists to have a better agriculture. A system of recommendations can be provided to a farmer to help them in crop cultivation with the help of data mining. To implement such an approach, crops are recommended based on its climatic factors and quantity. Data Analytics paves a way to evolve useful extraction from agricultural database. Crop Dataset has been analyzed and recommendation of crops is done based on productivity and season

Keywords: weather condition, Machine learning algorithms, Types of crops, fertilizer.

Abstract: Deep learning algorithms for blood cell detection, aiming to improve diagnostic accuracy. White Blood Cells also known as leukocytes play an important role in the human body by increasing the immunity by fighting against infectious diseases. The classification of White Blood Cells plays an important role in detection of a disease in an individual. The classification can also assist with the identification of diseases like infections, allergies, anemia, leukemia, cancer, Acquired Immune Deficiency Syndrome (AIDS), etc. that are caused due to anomalies in the immune system. This classification will assist the hematologist distinguish the type of White Blood Cells present in human body and find the root cause of diseases. Currently there is a large amount of research going on in this field. Considering a huge potential in the significance of classification of WBCs, we will be using a deep learning technique Convolution Neural Networks (CNN) which can classify the images of WBCs into its subtypes namely, Neutrophil, Eosinophil, Lymphocyte and Monocyte. In this paper, we will be reporting the results of various experiments executed on the Blood Cell Classification and Detection (BCCD) dataset using Dense Net algorithm.

Keywords: BCCD, blood cells, cancer, classification,Dense Net, Filtering

Abstract: Cross site scripting vulnerability is one of the most widely spreaded and existed vulnerability in today's web application. So this project focuses on implementing cross site scripting vulnerability scanner to find cross site scripting vulnerability in a web application .This paper is useful for security researchers to find cross site scripting vulnerability in less time and to get accurate results. Although a large research effort on web application security has been going on for more than a decade, the security of web applications continues to be a challenging problem. An important part of that problem derives from vulnerable source code, often written in unsafe languages like PHP. Source code static analysis tools are a solution to find vulnerabilities, but they tend to generate false positives, and require considerable effort for programmers to manually fix the code. We explore the use of a combination of methods to discover vulnerabilities in source code with fewer false positives. We combine taint analysis, which finds candidate vulnerabilities, with data mining, to predict the existence of false positives. This approach brings together two approaches that are apparently orthogonal: humans coding the knowledge about vulnerabilities (for taint analysis), joined with the seemingly orthogonal approach of automatically obtaining that knowledge (with machine learning, for data mining). Given this enhanced form of detection, we propose doing automatic code correction by inserting fixes in the source code. Our approach was implemented in the WAP tool, and an experimental evaluation was performed with a large set of PHP applications. Our tool found 388 vulnerabilities in 1.4 million lines of code. Its accuracy and precision were approximately 5% better than PhpMinerII's and 45% better than Pixy's.

Keywords: DenSet, cancer, BCCD, Filtering, blood cells

Abstract: Cold storage facilities play a critical role in preserving perishable goods, such as food and pharmaceuticals. However, ensuring optimal storage conditions, such as maintaining precise temperatures and humidity levels, is essential to prevent spoilage and maintain product quality. Traditional monitoring systems often lack real-time capabilities and intelligent decision-making, leading to inefficiencies and potential losses.In response to these challenges, this paper proposes an innovative IoT-based real-time intelligent monitoring and notification system for cold storage facilities. The system integrates various IoT sensors to continuously collect data on temperature, humidity, and other relevant parameters within the storage environment. These sensors transmit data to a central hub, where it is processed and analyzed using advanced algorithms and machine learning techniques.The intelligent system is capable of monitoring the storage conditions in real-time, identifying deviations from optimal parameters, and generating timely notifications/alerts to relevant stakeholders, such as facility managers or maintenance personnel. Moreover, the system employs predictive analytics to anticipate potential issues and recommend proactive measures to mitigate risks, thereby minimizing product losses and ensuring regulatory compliance.

Keywords: Temperature,Humidity,Light Intensity,Sensors,Random Forest.

Abstract: This work has employed a deep learning strategy to automatically detect and classify white blood cell (WBC) cancers, including leukemia, using histopathology images. This technique analyses histopathological images and uses convolutional neural networks (CNNs) to accurately detect distinct WBC cancer subtypes. When compared to pathologists who manually read cases, our method provides answers more quickly and accurately. Tested extensively on multiple datasets, our method consistently outperforms existing methods in terms of sensitivity, specificity, and overall accuracy. The study has also been made to improve the effectiveness of transfer learning techniques, which allow our model to adapt and perform well on different datasets. Because of its versatility, it can be applied in real-world clinical settings, which has the potential to revolutionize personalized medicine approaches to WBC cancer diagnosis and treatment. Additionally, our method employs explainable AI techniques to give doctors greater assurance and understanding by revealing the model's decision-making process. More informed treatment decisions by healthcare professionals lead to better outcomes for patients with WBC malignancies. By combining advanced deep learning methods with interpretable models, our research provides a significant step toward integrating AI-driven treatments into standard clinical practice. This has the potential to significantly improve patient care and outcomes in the field of oncology.

Keywords: White Blood Cancer Detection, Artificial intelligence, Deep learning, Histopathological Images, Convolutional Neural Networks (CNNs), Benign, Malignant, Rank-Based Ensemble, Inceptionv3, Xception, MobileNet

Abstract: Papaya cultivation faces numerous challenges from various diseases, highlighting the critical need for accurate classification and effective management strategies. Our research introduces an innovative approach using the YOLOv9c model for automated classification of Papaya Diseases, including Anthracnose, Phytophthora Blight, and others. We meticulously trained the model on a diverse dataset, ensuring robust performance across disease types, and developed a user-friendly web application for instant disease diagnosis, facilitating timely interventions. The efficacy of YOLOv9c in revolutionizing precision agriculture for improved crop sustainability is a central focus of our study. Through extensive field trials conducted under real-world conditions, we validated the model's performance, affirming its reliability and practical utility. This validation underscores the potential for integrating YOLOv9c into existing agricultural systems, offering advanced disease management strategies that can significantly enhance yield outcomes and optimize resource utilization. By leveraging cutting-edge technology like YOLOv9c, we empower farmers with accurate and timely disease diagnosis tools, ultimately promoting food security and economic stability in papaya cultivation. This work aligns with broader efforts to harness technology for sustainable agriculture, benefiting both farmers and the environment.

Keywords: Papaya Disease Classification, Machine learning, Disease classification, Deep learning, Papaya, Computer vision.

Abstract: Lightning, a natural phenomenon, poses substantial risks to life and property, necessitating accurate detection and timely alerts. Traditional methods relying on ground-based sensors have limitations in coverage and accuracy. However, recent advancements in deep learning have revolutionized lightning detection and alert systems. This paper introduces the Lightning Prediction and Alert System (LPAS), employing deep learning to enhance response to lightning threats. LPAS utilizes deep learning, particularly convolutional neural networks (CNNs) to process diverse data sources effectively. These models excel in detecting complex spatiotemporal patterns associated with lightning strikes. Furthermore, LPAS enables real-time lightning detection and alerting, delivering instant notifications through mobile apps, SMS, and email. In summary, the Lightning Prediction and Alert System powered by deep learning signifies a significant leap in lightning prediction technology. Its integration of multimodal data, deep learning models, and real-time alerting capabilities enhances public safety and benefits various industries. By mitigating lightning risks and enhancing our understanding of storm dynamics, LPAS promises a safer future for communities worldwide.

Keywords: Convolutional Neural network, Deep learning, Remote monitoring, Alert system.

Abstract: Epilepsy, a severe neurological disorder, is identified by analyzing intricate brain signals generated by interconnected neurons, often monitored through EEG and ECoG. These signals, characterized by complexity, noise, and non-linearity, pose significant challenges for seizure detection. However, recent strides in machine learning have facilitated the development of robust classifiers capable of effectively analyzing EEG and ECoG data. By leveraging these advancements, researchers can accurately detect seizures and extract pertinent patterns, thereby aiding in the diagnosis and management of epilepsy. Machine learning techniques empower clinicians to uncover valuable insights into the condition, ultimately enhancing patient care and treatment strategies.The integration of machine learning with EEG and ECoG analysis holds promise for advancing our understanding of epilepsy and improving patient outcomes.

Keywords: Seizure detection, data preprocessing, training the model, EEG signals, LSTM model, machine learning.

Abstract: Arecanut, commonly known as betel nut, is a significant tropical crop, with India being the second-largest producer and consumer worldwide. Throughout its lifecycle, it faces various diseases, affecting its roots, leaves, and fruits. Currently, disease detection relies solely on visual observation, requiring farmers to meticulously inspect each crop periodically. This project proposes a system utilizing Convolutional Neural Networks (CNNs) to detect diseases in arecanut leaves and trunk, offering corresponding remedies. CNNs are Deep Learning algorithms designed to analyze images by assigning learnable weights and biases to different features, thereby distinguishing between them. To train and validate the CNN model, a dataset comprising healthy and diseased arecanut samples was curated. The dataset was split into training and testing sets in an 80:20 ratio. For model compilation, categorical cross-entropy was employed as the loss function, with adam serving as the optimizer function and accuracy as the metric. Training the model over 50 epochs yielded high validation and test accuracies with minimal loss. The proposed approach demonstrated effectiveness, achieving a remarkable 98% accuracy in identifying arecanut diseases.

Keywords: Arecanut, betel nut, disease detection, Convolutional Neural Networks (CNN), deep learning, image classification, dataset creation, training, validation, optimization, accuracy, remedies, agricultural technology.

Abstract: Mobile edge computing (MEC) is a game-changing technology that has transformed the automotive network environment. Its integration into automotive networks has opened up a new universe of possibilities, dramatically altering how connected and autonomous vehicles operate. We will dig into the principles of MEC, its practical deployment in automotive infrastructure, and its exceptional adaptability to overcome difficulties that the automotive network encounters in this in-depth research. To reduce latency and enhance vehicle-to-vehicle and vehicle-to-infrastructure communications, MEC's fundamental technology leverages the capabilities of edge computing to move computation resources closer to the data source. This architectural revolution has ushered in a new era of car connection and intelligence, enabling real-time traffic management, ultra-low latency communication, immersive augmented reality experiences, and automated, data-driven decision-making. MEC is a crucial technology for the future of transportation because of its enormous potential to revolutionise the automobile sector. Even yet, MEC faces difficulties since tremendous promise also comes with enormous responsibility. Issues that require special attention include effective resource allocation and lowering network congestion. We not only identify these issues in this post, but we also give innovative ideas and practical methods to solve them. Reaching MEC's full potential requires ensuring that it is seamlessly integrated into the vehicle network. We're going to go over a thorough analysis of use cases and actual deployments to demonstrate how MEC can be of assistance. These case studies will demonstrate how MEC may optimise traffic management, increase vehicle safety, and improve the overall driving experience. We seek to offer a clear picture of how MEC might alter the automotive environment by looking at these actual examples. Looking ahead, we will highlight new trends and interesting research initiatives that will help to improve the synergy between MEC and transport networks. MEC's capabilities will expand along with technology, offering up new options for innovation and advancement. In conclusion, this study emphasises Mobile Edge Computing's critical role in altering the automobile network environment. It serves as a road map for academics, practitioners, and policymakers to fully realise MEC's promise, resulting in a safer, more efficient, and smarter automotive environment. connected. MEC's influence on the car industry will undoubtedly be transformative as it grows and matures, ushering in a new era of mobility and connection.

Keywords: Mobile Edge Computing (MEC), Vehicular Networks, Connectivity, Low Latency, Autonomous Vehicles, Edge-based Applications.

Abstract: Dementia, with its intricate cognitive and behavioral aspects, presents significant challenges for patients and caregivers. Rehabilitation is a key component of dementia care, holding potential for improved patient well-being. Recommender systems, driven by advanced algorithms and patient data, could transform the patient experience by offering tailored recommendations. Inspired by their success in e-commerce, where demographic filtering, collaborative filtering, and hybrid systems excel, this survey explores the landscape of recommender systems in dementia therapy. It sheds light on how machine learning technology can provide personalized care, enhance patient outcomes, and lighten the load on caregivers. The findings open doors to patient-centered healthcare strategies for addressing the multifaceted challenges of dementia.

Keywords: Dementia, Collaborative Filtering, Content-based Filtering, Demographic Filtering, Hybrid Recommender Systems. Cite: Pritish Pore, Sharvari Bhagwat, Prutha Rinke, Yash Desai, Arati Deshpande, Soubhik Das,"Revolutionizing Dementia Care: A Brief Survey of Personalized Therapy Recommender Systems", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13389.

Abstract: In India, paddy is one of the most widely grown crops. These days, this crop is facing challenges from diseases that affect its quality and yield. This study presents an effective machine learning and image processing-based analysis and disease detection system for paddy crops. In this work, totally three different disease classes were taken those were brown spot, leaf smut, Bacterial Leaf Blight, and healthy class are taken. The proposed system uses transfer learning from a pre-trained VGG16 convolutional neural network and fine-tunes the model parameters through hyperparameter tuning via grid search to optimize the SVM classifier. By doing so, an accuracy of 98% on the test dataset is achieved. The system also uses image processing techniques, including color thresholding, morphology operations, and contour detection, to analyse and quantify the affected area of diseased leaves. Moreover, the system provides remediation guidance for each disease, utilizing text-to-speech synthesis for multilingual accessibility.

Keywords: VGG16, SVM, Grid Search, Hyperparameter tuning, OpenCV2, Scikit-learn, Morphology operations, Contours, Image processing, gTTs. Cite: Siva Parvathi V, Pavan Gopi Chand Pidikiti, Juber Shaik, Nandu Rettapalli, Jayadeep Mothukuri,"Efficient Analysis and Disease Detection System for Paddy Crop Using Machine Learning and Image Processing Techniques", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13390.

Abstract: Emotion-based video playing systems represent a burgeoning field of research aimed at enhancing user engagement and satisfaction. This paper introduces a novel approach to such systems, employing facial recognition technology to detect users' emotional states in real-time. By analyzing facial expressions, the system identifies emotional cues and selects appropriate video content tailored to the user's mood. We present a comprehensive framework that integrates deep learning techniques, particularly Convolutional Neural Networks (CNNs), for accurate emotion recognition. Furthermore, we propose a dynamic recommendation mechanism that continuously adapts to users' changing emotional states during video playback. Experimental evaluations on diverse datasets demonstrate the effectiveness and robustness of the proposed system, outperforming existing methods in terms of accuracy and user experience. This research paves the way for emotion-aware video playing systems that can intuitively respond to users' emotions, offering personalized and immersive viewing experiences.

Keywords: Haar Cascade, Convolutional Neural Networks (CNNs), Emotion-based, real-time. Cite: Asma Attar, Namratha N Murthy, Rakesh Sharma, Yashaswini K P, Mr.Shivaprasad T K"EMOTION DETECTION BASED VIDEO PLAYING SYSTEM USING ARTIFICIAL INTELLIGENCE", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13391.

Abstract: Animal assaults that cause crop damage are one of the main factors lowering agricultural yields. Crop raiding is turning into one of the most vexing human-wildlife conflicts as a result of the extension of farmed land into former animal habitat. India's farmers face significant risks from pests, natural disasters, and animal damage, which lowers production.  In order to monitor crops and deter wild animals, farmers cannot afford to pay guards and their traditional tactics are not very efficient. Given the equal importance of ensuring the safety of humans and animals, it is crucial to safeguard crops from animal damage and safely redirect animals away from crops. Crop striking is turning into one of the most acrimonious human-wildlife conflicts due to the expansion of cultivated land into former animal habitat.  It is essential to thoroughly and effectively verify that wild animals are allowed to remain in their natural habitat. Therefore, we employ deep learning to identify animals visiting our farm by applying the deep neural network idea, a branch of computer vision, in order to overcome the aforementioned issues and achieve our goal. This suggested system would use a camera to capture the surrounding area all day long and monitor the entire farm at predictable periods. When an animal enters the area, the system uses a deep learning model to recognise it and plays the proper noises to scare it away.

Keywords: Convolutional Neural network, Deep learning, Remote monitoring, Alert system. Cite: Manjunath Hebbagilu, Dhanush, Ramnath Nayak, Sahil Faraz, Sanjay P "WILD ANIMAL DETECTION IN FARMLAND", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13392.

Abstract: Myopia commonly known as near sightedness, is a prevalent vision problem affecting a considerable portion of the global population, particularly among adolescents and young adults. Detecting myopia early is crucial to effectively manage and prevent associated complications such as retinal detachment, myopic macular degeneration, and glaucoma. While traditional methods of myopia detection often rely on subjective evaluations by eye care professionals, which can be time-consuming and require specialized equipment, our study proposes a novel approach using deep learning techniques. By harnessing advancements in computer vision and deep learning, we have developed a convolutional neural network (CNN) model trained on a large dataset of retinal images. This model is capable of automatically identifying signs of myopia, including optic disc anomalies, retinal stretching, and other characteristic features associated with myopic progression. Our experimental findings demonstrate the effectiveness of this deep learning model in accurately detecting myopia from retinal images with high sensitivity and specificity. Furthermore, the model's performance surpasses that of traditional methods, offering a more efficient and objective approach to myopia detection. This system we have developed shows promise for early screening initiatives, telemedicine applications, and assisting healthcare professionals in the timely diagnosis and management of myopia-related conditions.

Keywords: Myopia detection, Deep learning, Convolutional neural networks, Retinal imaging, Healthcare AI. Cite: Anusha, Anusha Sadashiva Lokeshwar, Arpita Sanyal, Deekshitha, Rejeesh Rayaroth "Detection of Pathological Myopia using Deep Learning Techniques", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13393.

Abstract: In an era characterized by rapid urbanization, the efficient management of traffic stands as a paramount necessity. The challenges posed by traffic congestion, road accidents, and the ever-evolving landscape of infrastructure development require innovative solutions. This project introduces an intelligent traffic management and prediction system harnessing the power of Artificial Intelligence (AI) and Machine Learning (ML). It sets out to revolutionize the management and control of traffic, with a focus on streamlining traffic flow, reducing congestion, enhancing road safety, and supplying critical data for informed infrastructure development. Beyond traditional traffic management, this system offers a suite of advanced features, including convoy route planning and dynamic journey optimization, which is designed to benefit both traffic authorities and road users. This abstract encapsulates the essence of a visionary system that aspires to usher in a smarter, safer, and more organized approach to urban traffic management, poised to harmonize the needs of our ever-growing cities with the demands of modern transportation.

Keywords: Deep Learning, Vehicle Detection, Intelligent Traffic Control Cite: Lohit Vishnu Naik, Sanjana Raj, Subeen Hegde, B Shiv Kumar, Ramananda Mallya K, "TRAFFIC MANAGEMENT SYSTEM", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13394.

Abstract: It is now crucial to preserve digital data in our ever-connected environment. Using watermarking, cryptography, sharing, and artificial intelligence (AI) capabilities, this article investigates a unified approach to data security and privacy. covert. These technologies are becoming more and more integrated as we create cutting-edge solutions to safeguard private data, maintain intellectual property, and enhance safe data sharing. Our study starts with the use of AI in watermarking, demonstrating how AI-based watermark generation, detection, and removal can improve the security of digital assets. Next, we turn to cryptography, where AI advances secure data transfer, key management, and encryption techniques. Additionally, approaches for sharing secrets are included, showing how AI optimisation enhances collaborative machine learning, safe multi-party computation, and distributed data sharing. Use cases and real-world examples that demonstrate the possible integration of AI with watermarking, cryptography, and secret sharing bolster the suggested unified approach. Among the real-world applications being investigated are multi-factor authentication, blockchain, secure authentication, and privacy-preserving machine learning. The paper discusses the difficulties and moral issues of AI-based data security while outlining these methods. It also offers a roadmap for further study and advancement, emphasising the necessity of constantly adjusting to new risks and technological advancements in the dynamic field of digital security. This study paper adds to a thorough grasp of sophisticated data security strategies and offers important insights into the changing cybersecurity scene by combining AI with watermarking, cryptography, and secret sharing.

Keywords: Artificial Intelligence, Data Security, Privacy, Watermarking, Cryptography, Secret Sharing Cite: Guttikonda Prashanti, Tondapu Uma Maheswari, Tadala Sai Prasanna, Gondi Lokesh, Poluri Sudeep Kumar, "Integrating Artificial Intelligence for Enhanced Data Security and Privacy", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13395.

Abstract: While reducing the inherent dangers. To maintain the integrity and confidentiality of their data in the cloud, organizations must prioritize user interface security. Validation and access control are two major difficulties in user interface security. Cloud systems frequently deal with many users, making it critical to establish strong procedures for verifying user identities and granting appropriate access privileges. Multi-factor authentication, such as using passwords in conjunction with biometric or token-based identification, adds an extra layer of protection. Organizations may use role-based access control to establish user roles and allocate rights appropriately, limiting the risk of unauthorized access to critical resources. Another critical feature of cloud user interface security is data encryption. Organizations can secure information from unauthorized access or interception by using encryption at rest and in transit. To safeguard data stored in the cloud, encryption technologies such as the Advanced Encryption Standard, or AES, are extensively utilized. Furthermore, secure communication routes, such as SSL/TLS protocols, allow for the safe movement of data among users and cloud services. Identity management is a vital component of cloud user interface security. Organizations must have solid processes in place to manage user identities, such as providing and deprovisioning accounts, implementing strong password restrictions, and assessing access privileges on a regular basis. IAM systems enable centralized control over user identities and access entitlements, resulting in increased security and convenience. Because of the increasing reliance on cloud-based applications and services, user interface security is a major problem in cloud systems. To handle the security concerns associated with user interfaces, organizations must be aware and proactive. Businesses may increase their cloud security posture and exploit the benefits of the cloud while preserving their operations and data by employing different security procedures and tactics.

Keywords: Access Control, Cloud Security, Identity Management, User Authentication, User Interface Security. Cite: Malladi Srinivas, Bandlamudi Meghana, CH. Gowtham Sai, K. Anusha, "Securing the Cloud User Experience: A Comprehensive Examination of Interface Risks", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13396.

Abstract: Alzheimer's disease (AD) is a progressive neurodegenerative disorder characterized by cognitive and functional decline. Early detection is critical to help patients and caregivers better manage symptoms and plan future care. However, current clinical evaluations alone cannot reliably identify AD at pre-dementia stages. Multi-modal neuroimaging provides complementary biomarkers that may aid more accurate machine learning-based diagnosis. This review discusses machine learning methodologies for developing an early AD diagnosis system using integrated data from multiple neuroimaging modalities. Feature extraction, selection, scaling and fusion techniques are described to synergistically combine correlated characteristics from different modalities. Challenges in designing such a system are also outlined. A thematic analysis compares machine learning workflows and their potential for computer-assisted diagnostic solutions. The report aims to advance the field by highlighting strategies that leverage multi-modal neuroimaging data through machine learning for improved early Alzheimer's detection. Automated tools incorporating biomarkers across modalities may help identify candidates for disease- modifying interventions prior to symptom onset.

Keywords: Alzheimer's disease, before symptoms, machine learning, extracted, fused features, multiple neuroimaging modalities Cite: Lakshmana Phaneendra Maguluri, Koneru Mahendra Krishna, Yerra Brunda, Alla Poojan Reddy, Chava Kavya Sree, "Leveraging Multi-Modal Neuroimaging Data and Machine Learning for Early Detection of Alzheimer's Disease", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13397.

Abstract: Neural Machine Translation has surpassed many limitations of rule-based and statistical machine translation systems and is the current state-of-the-art. Though the success of Neural Machine Translation is indisputable, still many improvements are awaited when it comes to expecting the same level of quality for translation to/from low resource languages. In this work, we tried to develop a One-To-Many Multilingual Neural Machine Translation system, which is capable of translating text from English Language to two low resource Indic languages, viz., Assamese, Bengali. We used publicly available parallel corpus. Along with the public corpus, we also used synthetic data for Assamese as the target side. We got better results in terms of BLEU, chef and TER for English to Bengali and direction English to Assamese translation direction in multilingual settings as compared to their bilingual NMT counterparts. In this paper, we have shown that both multilingualism and use of synthetic data can enhance the translation quality of languages where gold standard parallel data is very low.

Keywords: Low resource language MNMT, Multilingual Neural Machine Translation, Indian languages MT, Indic NLP, Assamese NMT, Bengali NMT. Cite: Kishore Kashyap, Shikhar Kumar Sarma, "Multilingual NMT system for English to Low Resource Indic Languages - Assamese and Bengali", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13398.

Abstract: News apps have become an integral part of the digital era, providing users with a convenient and personalized way to access and consume news content. This research paper delves into the evolution and impact of news apps, focusing on their design, features, and user behaviour. The paper explores the utilization of various features such as navigation drawer, fragments, view pager with tab layout, loaders, intents, Guardian API integration, JSON parsing, Glide image loading library, card view, recycler view, and shared preferences. The project overview entails the development of a News Feed app that fetches and presents regularly-updated news from the internet, pertaining to specific topics, individuals, or locations. The Guardian API is employed as a reliable source, providing news information in a JSON format. The paper examines the significance of each feature in enhancing the app's functionality, usability, and user experience. Through a comprehensive analysis of design principles and best practices, this research paper sheds light on the importance of intuitive navigation, modularization using fragments, efficient content presentation with view pager and tab layout, data loading and management using loaders, interactivity through intents, integration of the Guardian API for accessing news data, JSON parsing for extracting relevant information, seamless image loading with Glide library, optimized content display with card view and recycler view, and personalized settings management using shared preferences. Furthermore, the paper investigates user behaviour patterns and preferences in the context of news app usage. It examines factors that influence user engagement and satisfaction, such as content relevance, personalization, ease of use, and visual appeal. Insights gathered from user behaviour analysis contribute to enhancing the design and features of news apps, ensuring they meet the evolving needs and expectations of users in the digital era. In conclusion, this research paper provides a comprehensive exploration of the evolution and impact of news apps. By understanding the design principles, features, and user behaviour associated with news apps, developers and stakeholders can create compelling and user-centric news experiences that cater to the ever-changing landscape of digital news consumption.

Keywords: Flutter Frame-work, Dart Programming Language, NEWS API, JSON, Glide Library. Cite: Mrs. P. Jayasutha , Mr. Stanly jayaprakash, Anuj kumar, Kundan kumar, Manoj Kumar, Md Firoz Alam, "Personalized Trending Stories in Real Time System - News Hub", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13399.

Abstract: In response to the hectic pace of modern life, there's a growing need for a smartphone web app that streamlines meal preparation. Our project aims to address this need by developing a sophisticated recipe recommendation system powered by technologies such as computer vision and machine learning. The primary objective is to simplify the culinary experience for users who often find themselves uncertain about what to cook with the ingredients they have on hand. By leveraging computer vision techniques, our system can accurately identify the ingredients available to the user. This information is then processed using machine learning algorithms to generate tailored recipe suggestions. This approach eliminates the need for extensive meal planning or manual recipe searches, saving users valuable time and effort. To tackle this, we prepared an ingredient dataset containing image 12,558 images across 15 food ingredient classes. The YOLOv8 object detection model was used to detect and classify food ingredients. Additionally, the recommendation system was built using machine learning. In the end, we achieved an accuracy of 96%, which is quite impressive.

Keywords: Object Detection, YOLOv8, FastAPI, TF-IDF, Word2Vec. Cite: Hency Jostan Dsouza, K Sthuthi Nayak, Krishii Kirti Karkera, Melan Varghese, Mr. Shreejith K B, "Ingredient Detection and Recipe Recommendation Using Deep Learning", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133100.

Abstract: This introduces an innovative approach to enhancing the security of smart vehicles by combining Machine Learning (ML) and the Internet of Things (IoT). The system utilizes IoT sensors to collect real-time data from the vehicle's environment and keyless entry system, which is then analyzed using ML algorithms to detect anomalies and potential relay attacks. To strengthen security, the system incorporates multi-factor authentication with biometric recognition such as fingerprint and facial recognition. Continuous learning and adaptation mechanisms ensure the system remains resilient to evolving threats, offering a robust defense against cyberattacks in smart vehicle environments. Through experimentation and validation, the system demonstrates its efficacy in accurately identifying and mitigating security threats, making it suitable for integration into existing automotive security frameworks.

Keywords: Keywords for securing smart vehicles from Relay attacks include IoT sensors, machine learning models, real-time monitoring, response mechanisms, Relay attacks, smart vehicles, security, detection, adaptability, resilience, continuous improvement, cyber threats, transportation, and digital age. Cite: Kumar Madar , Sweedal Flora Dmello, Yashwanth S, Anusha , Mr. Vijayananda V Madlur, "Using ML Models and IOT to Secure Smart Vehicles from Relay Attacks", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133101.

Abstract: Glaucoma is a term used to describe the cumulative loss of retinal cells in the optic nerve or permanent vision loss due to optic neuropathy. Glaucoma is a disease of the human eye. This disease is considered an irreversible disease that causes deterioration of vision. They have no early warning signs of glaucoma. You may not notice a change in your vision because the effect is so subtle. Many deep learning (DL) models have been developed to improve the diagnosis of glaucoma. Therefore, we present an architecture for accurate glaucoma detection based on deep learning using convolutional neural networks (CNN). The distinction between glaucoma and non-glaucoma patterns can be made using CNN. CNN provides a hierarchical structure for image differentiation. Using the current method, the disease is detected. It determines whether the patient has glaucoma or not, the relationship between the eye and the disc. Improved diagnosis by combining image data generator techniques to augment data. The results show that the proposed model outperforms existing algorithms, achieving 98.47% accuracy.

Keywords: Feature Extraction, Machine Learning, CNN, Image Data Generator,Glaucoma,keras,streamlit Cite: Akash Ashok Nayak, A Ashitha, Akshatha, Alan Raji Mani, Dr.Ravinarayana B, Mr.Shreejith K B, "Detection Of Glaucoma Eye Disease Using Retinal Fundus Images", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133102.

Abstract: The dairy industry faces persistent challenges in evaluating milk quality due to labor intensive and subjective processes. This project proposes a transformative solution integrating hardware and software technologies to revolutionize milk quality assessment and management. The system employs advanced sensors including pH, temperature, color and fat content sensors seamlessly integrated into a cost-effective device tailored for dairy farmers. This device facilitates real time monitoring of milk quality, empowering farmers to make data-driven decisions and optimize production efficiency. Complementing the hardware, an intuitive mobile application provides farmers with instant access to milk quality data, enabling proactive management of dairy operations. Transparent billing mechanisms ensure fairness and accountability in the dairy supply chain, generating precise invoices based based on objective milk quality metrics using a machine learning model. By enhancing transparency and efficiency, this solution promises to elevate milk quality standards and foster trust among consumers, thereby strengthening the dairy industry's competitiveness and sustainability.

Keywords: IOT, Microcontroller, Transparency in billing, Machine Learning, Model Integration, Application development. Cite: Shivaraj Shetty, Mrs. Amrutha, Ranjith Shetty, Rao Suraj Nagesh, Shiva Patankar, "Effective Milk Grading and Billing Solution for Dairy Industry", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133103.

Abstract: The most prevalent type of head and neck cancer is oral or mouth neoplasm, namely oral squamous cell carcinoma (OSCC).Despite its impact on mortality, it is invariably diagnosed late due to the ineffectiveness of early detection screening techniques. Early detection and treatment of oral squamous cell carcinoma (OSCC) is crucial for improved patient outcomes. Deep learning (DL) offers a promising approach for automated OSCC detection and classification. DL models can extract complex features from histopathological image dataset, achieving high accuracy in OSCC detection and classification. Studies have demonstrated DL is effective in distinguishing OSCC from benign lesions and classifying OSCC into different stages. DL-based OSCC detection and classification can improve diagnostic accuracy and efficiency, leading to earlier detection and treatment. However, further research is needed to validate DL models' clinical performance and ensure data quality and model interpretability. Overall, DL holds promise for revolutionizing OSCC diagnosis and management, enabling more accurate and personalized patient care.

Keywords: Deep learning(DL), Convolutional Neural Networks (CNNs), Oral Squamous Cell Carcinoma (OSCC), Histopathological Cite: Ravinarayana B, Ananya , Aparna P, Divija, Eeksha Jain, "ORAL SQUAMOUS CELL CARCINOMA DETECTION USING DEEP LEARNING ON HISTOPATHOLOGICAL IMAGES", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133104.

Abstract: Analysing behavioural biometrics involves examining various user behaviours, such as the dominant hand used on a phone, the angle of device holding, typing speed and style, including keystroke rhythm and pressure applied, along with swipe and scroll patterns. Gait analysis further contributes by assessing an individual's walking pattern. Continuously monitoring these biometric traits and comparing them against established user profiles can significantly bolster security against identity theft and online fraud. However, it's paramount to strike a delicate balance between the security benefits and privacy concerns, ensuring the responsible use and safeguarding of user data. Our multi-modal authentication system harnesses both facial features and typing patterns, employing cutting-edge algorithms and real-time processing to deliver a seamless user authentication experience. Anti-spoofing measures are integrated to enhance system integrity, while comprehensive testing validates its effectiveness across a wide range of applications, from cybersecurity to access control. Continuous monitoring and updates are implemented to maintain optimal system performance, adapting to evolving security threats and user needs. By leveraging the distinctiveness of these behavioural biometrics, our system stands as a pioneering solution in enhancing security measures while prioritizing user privacy and usability.

Keywords: Behavioural biometrics, Keystroke rhythm, Finger pressure, Swipe patterns, Gait analysis. Cite: Rajesh N Kamath, Swathi.K.L., Vijetha Pai, Sneha C M, Lakshitha K Salian, "KEYSTROKE RHYTHM ANALYSIS FOR IDENTITY VERIFICATION", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133105.

Abstract: The Image Caption Generator utilizes cutting-edge deep learning techniques to transform the way machines interact with visual content. By leveraging state-of-the-art Convolutional Neural Networks (CNNs), it extracts detailed features from images, enabling the generation of coherent and contextually appropriate captions. This is further enhanced by advanced language models such as Transformer-based architectures, ensuring accurate linguistic alignment. The project's impact is profound and diverse. It introduces a higher level of accessibility for individuals with visual impairments by providing verbal descriptions of images, empowering them to independently engage with visual content. Additionally, it simplifies content creation, benefiting social media influencers and content creators by automatically adding descriptive captions, saving time and effort. Users across various platforms benefit from enriched interactions as they enhance their posts with meaningful image captions, thereby increasing engagement and communication. Moreover, the Image Caption Generator improves image search and retrieval, enabling users to quickly locate relevant images. Its applications extend to content moderation and educational support, underscoring its versatile utility. With the potential for multilingual support and contributions to assistive technologies, the Image Caption Generator represents a significant advancement in artificial intelligence. By amalgamating images and language, it heralds a future of improved human-computer interaction, establishing a precedent for visual comprehension in the digital age.

Keywords: Image Caption Generator, Deep learning techniques, Convolutional Neural Networks (CNNs). Cite: Sharath Kumar, Pavan H R, Prashith C Hegde, Srajan S Shetty , Suhas S Shetty, "DeepVision Captioneer : Image Caption Generator For Visually Impaired ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133106.

Abstract: This paper introduces an optimized approach for detecting and tracking sperm in phase-contrast microscopy image sequences, with the aim of improving fertility analysis and sperm behavior studies. The proposed method integrates advanced object detection techniques with a modified multi- object tracking algorithm to achieve superior accuracy and robustness. Through comprehensive experimentation, our approach demonstrates exceptional performance in challenging scenarios such as high-density sperm samples, occlusions, and collisions, achieving an F1 score of 96.61% in tracking accuracy. This optimized algorithm holds significant promise for advancing research in reproductive health. Cite: Amod Kumar J, Dhanush, Elvin D’Sa, Shivaraj, Sunitha N V, "MALE FERTILITY DETECTION USING DETECTRON2 & CSR-DCF", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133107.

Keywords: Computer vision, Pose detection, Deep learning model. Cite: Rajesh N Kamath, Disha, Disha Ballal, Medhini Shetty, Rachana Adiga, "ROBOTIC ASSISTANCE FOR ELDERLY CARE", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133108.

Abstract: Recently weather changes result from natural variability and human activities like greenhouse gas emissions, leading to global warming and increased extreme events. IoT facilitates data sharing without human involvement, aiding sectors like healthcare and agriculture. Our cost-effective IoT-based weather monitoring system utilizes the ARIMA algorithm for forecasting. It comprises sensors collecting weather data, an IoT gateway for data transmission, and cloud storage. We address humidity concerns for housewives using sensors like DHT22 and LDR, triggering alarms for high humidity levels. Deployable in remote locations, it aids domestic planning based on weather conditions.

Keywords: ARIMA Algorithm, Barometric pressure sensors, Internet of Things, Light Dependent Resistor, Machine Learning, Rain Sensor, Weather monitoring and forecasting. Cite: Dr. P. Manikandaprabhu, Ms. S. Nivetha, "A Cost-Effective IoT-Based Weather Monitoring and Forecasting using Arima Algorithm", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133109.

Abstract: Communication barriers significantly hinder interaction between the deaf community and the wider world. This paper investigates an automatic system for Indian Sign Language (ISL) detection using MobileNetV2, a transfer learning architecture known for its efficiency. We leverage transfer learning from pre-trained MobileNetV2 weights to extract features from ISL images. To improve model performance for ISL detection, we incorporate linear bottleneck layers and squeeze-and-excitation blocks within the network. Additionally, separable convolutions are used to maintain accuracy while reducing computational complexity. This optimized MobileNetV2 architecture is then fine-tuned on a prepared ISL dataset for robust sign recognition. While limitations exist, this research paves the way for advancements in communication accessibility for the deaf community.

Keywords: Indian Sign Language (ISL),Sign Language Detection ,Deep Learning,MobileNetV2,Transfer Learning ,Linear Bottleneck Layers ,Squeeze-and-Excitation Block ,Communication Accessibility ,Deaf Community. Cite: Ashlesh Shenoy, Shawn Castelino, Shetty Sushank Mohandas, Vaibhav Nayak,Ms.Suma K, "Realtime conversation system for people with hearing and speech impairments", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133110.

Abstract: This study explores the integration of blockchain technology into the crop agriculture supply chain to enhance transparency, traceability, and efficiency. Traditional supply chain systems often face challenges such as authenticity verification, supply chain visibility, and inefficiencies. By leveraging blockchain's capabilities, this initiative aims to address these issues and revolutionize the way crops are supplied, managed, and distributed. The primary goal is to establish a decentralized and immutable ledger that records every transaction and movement of crops, ensuring transparency and accountability among stakeholders. Through collaboration with key participants including crop owners, suppliers, manufacturers, distributors, wholesalers, and transporters, this project seeks to create a seamless and reliable system that benefits the entire supply chain ecosystem. The findings highlight the potential of blockchain technology to drive positive change in the crop agriculture industry.

Keywords: Blockchain, Crop agriculture, Supply chain, Transparency, Traceability, Efficiency, Decentralization, Collaboration, Stakeholders. Cite: Aghav Sandhya, Kadlag Narendra, Lagad Makarand, Madhavai Sapna, Murade Trupti, "Crop agriculture supply chain integration with blockchain", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133111.

Abstract: Bar Bending Schedule (BBS) is basically the representation of bend shapes and cut length of bars as per structure drawings. BBS is prepared from construction drawings. For each member separate BBS is prepared because bars are bent in various shapes depending on the shape of member. “BBS”, the word BBS Plays a significant role in any construction of High rise buildings. It helps to quote for tender the cost incurred by steel. Finding the cutting length and bending length in reinforcement detailing improves the quality of construction and minimize the wastage of steel, so this makes an economic construction. This increases faster construction and reduces the total construction cost for site engineers, It becomes easy to verify the cutting length and bending length of the reinforcement before placing the concrete. The calculation process requires meticulous calculations and analysis to ensure structural integrity, safety, and durability. This paper presents a review of the latest research and developments in automation applied to the BBS Software. The paper first highlights the importance of Software infrastructure and the challenges associated with their design process, including complex calculations, iterative analysis, and adherence to design codes and standards. Then, it discusses the role of automation in addressing these challenges and improving the efficiency and accuracy of the calculation. The benefits of automation in Software are discussed, including reduced human error, improved accuracy, increased productivity, and enhanced design optimization. The paper also discusses the limitations and challenges of automation in Software, including the need for reliable input data. Finally, the paper identifies future research directions and potential areas of improvement in automation for BBS Software. These include the development of more advanced AI models, integration of automation with emerging technologies like Buildings and addressing the challenges related to data reliability and ethical concerns. In conclusion, automation has emerged as a promising approach to improve the design of Software, making the process more efficient, accurate, and optimized. However, further research is needed to overcome the challenges and limitations associated with automation, and to ensure its ethical and responsible use in Bar Bending Schedule. The findings of this review paper can serve as a reference for researchers, practitioners, and policymakers interested in the application of automation in the BBS Software. Key Points: BBS(Bar Bending Schedule), CAD(Computer-Aided Design) Cite: Gowrish G Kamath, K P Venkatesh, Keerthan Hebbar, P Vikhyath Shenoy, Mr. Dinesh Ramakrishna Bhagwat,"Automation of Bar Bending Schedule Software for Building ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133112.

Abstract: Ayurveda, an ancient Indian system of medicine rooted in the Vedas, has gained global attention for its holistic approach to health. India is well-known for offering an optimal environment that supports a wide variety of medicinal plants. The various components of these plants play a crucial role as key elements in crafting natural remedies. Fascinatingly, numerous medicinal plants thrive in our own backyards or along sidewalks. Identifying and differentiating between these plants is nearly impossible for someone without proper training. The manual process of identifying plant species is both challenging and time-consuming, exacerbated by a lack of expertise in the field. This challenge is especially evident in the accurate classification of medicinal plants, where the process can be intricate and perplexing. To overcome these challenges, this project aims to harness the capabilities of machine learning for the automatic detection of medicinal plants. This approach aims to streamline the identification process, minimizing the reliance on manual labor. The automation of this crucial task not only targets improved efficiency and accuracy but also strives to make it more user-friendly for individuals with diverse levels of expertise. Incorporating Convolutional Neural Networks (CNNs), identified as optimal for the project, the AI algorithm specializes in image classification, particularly suitable for the diverse shapes, colors, and textures of plant leaves. CNNs not only identify the plant but can also extract crucial information on its medicinal properties and practical applications through training on labeled datasets. This innovative fusion of AI and Ayurveda holds immense potential to revolutionize healthcare. Empowering individuals to actively engage in their well-being, the project aims to provide access to the expertise of Ayurveda practitioners, fostering a healthier and sustainable future for all.

Keywords: Medicinal plants, Machine learning, Image processing, Convolutional neural Network, feature extraction, plant recognition Cite: K Shramitha Shetty, Lahari Acharya, Riya Miranda, V Lahitha, Dr.Sreeja Rajesh ,"AI IN MEDICINAL PLANT DISCOVERY AND HEALTH CARE ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133113.

Abstract: In response to the imperative of universal accessibility in today's fast-paced technological landscape, this project is committed to empowering visually impaired individuals by devising a comprehensive system to tackle their daily challenges. Leveraging cutting-edge real-time image processing techniques, our initiative is centered on creating a robust framework that addresses key obstacles faced by the visually impaired. This encompasses the development of sophisticated algorithms for object classification, accurate distance estimation, precise person identification, and auditory feedback integration. By prioritizing the creation of an efficient object classification model and a precise distance estimation algorithm, our system aims to deliver effective support to visually impaired users. Additionally, we are pioneering advancements in person identification accuracy and plan to seamlessly integrate audio models for accessible feedback. Rooted in considerations of technical feasibility, market demand, user input, cost-effectiveness, and ethical standards, our project follows a systematic methodology. This entails clearly defined objectives, meticulous hardware and software selection, data acquisition protocols, and rigorous image processing procedures. Designed with adaptability and scalability in mind, our system endeavors to continuously meet the evolving needs of visually impaired individuals, thereby significantly enriching their daily lives.

Keywords: Image processing, Computer vision, Machine learning, Deep learning, Convolutional neural networks (CNNs), Object detection, Distance estimation, Auditory feedback, Assistive technology, Accessibility solutions, Visual impairment, Camera input. Cite: Ananya B Hegde, Gautham Jain, Karthik A, Kartik Mehta, Mr Annappa Swamy D.R, "Image-Based Object Classification and Distance Measurement for the visually Impaired", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133114.

Abstract: The Enhanced Mobile Learning Platform presents an innovative approach to education on mobile devices, aiming to transform traditional learning methods by utilizing the flexibility and accessibility of smartphones and tablets. Mobile learning (M-Learning) is increasingly recognized as vital among today's youth, offering benefits such as fostering critical thinking and driving deeper engagement, ultimately leading to the meaningful acquisition of knowledge. Among its advantages, M-Learning serves as a supplementary learning resource accessible anytime, anywhere, on any network, through various wireless devices. It stimulates students' interest in learning and facilitates communication by providing learning materials in diverse formats, accessible at their convenience. Furthermore, M-Learning introduces novel learning avenues through mobile devices like smartphones and MP3 players. This chapter aims to explore the current landscape of mobile learning, its advantages, characteristics, and challenges in sustaining effective learning, while also discussing various mobile applications designed for learning purposes. A mobile application, in this context, refers to software application developed for educational activities specifically tailored for smartphones and tablets, diverging from traditional desktop or laptop computers.

Keywords: Mobile learning, Critical thinking, Smartphones, Software application. Cite: Pooja, Sameeksha Shetty, Thanushree C J, Vighnesh, Dr. Ramananda Mallya,"ENHANCED MOBILE LEARNING PLATFORM", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133115.

Abstract: Researchers have focused on edge computing to improve and maximise the information application performance and reliability of the V2V communication network. In the present study, cloud computing is employed for message-related job execution, which boosts reaction time. We present a Software-defined Fault Tolerance and QoS-Aware (Quality of Service) V2V communication using Edge Computing Secured by Blockchain to minimise overall communication latency, message failure fault tolerance, and secure service provisioning in a V2V communication network. Block chain and edge computing have an intriguing interdependence. Edge computing/distributed computation architecture may offer a platform for block chain nodes to store and validate transactions. On the other side, blockchain may allow a fully open distributed cloud marketplace. If the message delivery fails, the fault tolerance mechanism resends the error message. The results demonstrate the performance of the suggested model, which reduced the total message transmission time by 55% for routine and emergency messages by using the edge server SDN controller. Furthermore, the suggested approach uses edge servers, cloud servers, and blockchain infrastructure to minimise execution time, security risk, and message failure ratio. Keywords- Vehicular computing, autonomous vehicles, edge computing, task partitioning Cite: Tanushri Raut, Siddhi Thakur, Sania Chorge, Sheetal Sapate,"Vision based architecture of Home Security System", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133116.

Keywords: Glaucoma diagnosis Choroidal Neovascularization (CNV) Diabetic Macular Edema (DME) Drusen Early detection Machine learning Image analysis. Cite: Sharath Kumar, Athik Rehaman, Lathesh Kumar, Mayur S Karkera, Mohammed Muneef,"Glaucoma Detection using Machine Learning with OCT", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133117.

Keywords: Subject comprehension, Immersive Education, 3D model, Animations, Metaverse. Cite: Deepthi S Nayak, Hithesh Suvarna, Mahesh Bhat, Varun Raj, Narendra U P,"METAVERSE FOR IMMERSIVE LEARNING EXPERIENCE", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133118.

Abstract: Our novel system, Enhancing Vision Care: Detection of Eye Diseases and Prediction of Refractive Errors, employs a deep learning architecture trained on a dataset of diverse fundus photographs encompassing various eye diseases, including  diabetic retinopathy, glaucoma and cataracts and prediction of refractive errors like myopia, astigmatism and hypermetropia. The system employs multi-task learning and attention mechanisms to simultaneously detect and localize distinct disease signatures within each image. This project represents a significant step towards automated, multi-disease eye disease detection with high accuracy and generalizability. Its potential lies in enabling early intervention, improving individual prognosis, and reducing healthcare costs associated with vision loss. Future work will focus on integrating Enhancing Vision Care: Detection of Eye Diseases and Prediction of Refractive Errors into clinical workflows and exploring its application in underserved communities.

Keywords: Artificial intelligence, deep learning, multi-disease detection, eye diseases, retinal imaging, early diagnosis, healthcare Cite: Ananya, Manojna P Jain, Nidah Shabbir Shaikh, Vinayashree, Dr.Sreeja Rajesh,"Enhancing Vision Care: Detection of Eye Diseases and Prediction of Refractive Errors", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133120.

Keywords: Lumpy Skin Disease (LSD), Machine Learning (ML), Prediction, Feature Selection, Datasets, Algorithms Evaluation Metrics, Support Vector Machines (SVM), Random Forests, Neural Networks, Accuracy Improvement, Clinical Practice, Patient Outcomes, Healthcare Management, Early Identification. Cite: Anusha Ramdas Mogher, Shivaraj B G, Neha C Suvarna, Poornima, Sakshi P Bhandary,"Lumpy Skin Disease Detection", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133121.

Abstract: In a world that values personalized, interactive, and easily accessible learning, our project stands at the intersection of art and technology, offering an innovative solution. We aim to revolutionize the understanding and teaching of complex movements by providing a tailored and immersive learning experience, departing from traditional tutorials. In the domain of Motion Knowledge, where movement's beauty meets learners' enthusiasm, our project represents a groundbreaking approach. Driven by the belief that tutorials should be inclusive, we leverage cutting-edge technology like PoseNet and CGAN to deconstruct tutorials into digestible steps, simplifying the learning journey. Our primary objective is to empower individuals of all skill levels to explore, learn, and excel in the art of movement without unnecessary complications. Our project provides dynamic and highly personalized learning experiences accessible to individuals from diverse backgrounds, whether they're novices or seasoned practitioners. Users actively shape their motion education narrative, fostering creativity, skill mastery, and a profound connection with their movements. Our unique solution marries art and technology to meet the demand for engaging and personalized learning experiences

Keywords: PoseNet, CGAN, Motion Knowledge, personalized learning experiences, immersive learning experience. Cite: Mr. Annappa Swamy D.R, Akshira, Arghyashree, Ashvitha Shetty, Gajesh Naik,"MOTION TUTOR: ANIMATED MOTION USING DEEP LEARNING", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133122.

Abstract: The AUTOMATIC SOLAR TRACKING SYSTEM WITH OVERCHARGING PROTECTION System project aims to develop a solar tracking system that enhances the performance of photovoltaic modules in a solar energy system. By continuously aligning the photovoltaic modules with the sun's rays, the system maximizes their exposure to sunlight, thereby increasing power generation efficiency. The project involves the design, implementation, and programming of hardware components, including servo motors, LDRs, and an Arduino UNO microcontroller. The system utilizes an ATmega328P microcontroller to control the movement of two servo motors, which adjust the orientation of the solar panel in two axes. The microcontroller receives inputs from four photo sensors located near the solar panel to accurately determine the angle of rotation. At the conclusion of the project, a fully functional solar tracking system is designed and implemented, capable of aligning the solar panel with the sun or any light source repeatedly. Furthermore, the study compares the energy conversion efficiency of photovoltaic modules with and without solar tracking systems. The analysis demonstrates that a dual-axis solar tracking system generates 31.3% more power than a fixed photovoltaic module, highlighting the effectiveness of solar tracking technology in maximizing power output.

Keywords: Dual Axis, LDR, Microcontroller, Servomotor, Solar Tracker, Solar energy, Automatic solar tracking system, Arduino microcontroller, maximum illumination, reduction in cost, maximum efficiency. Cite: Pankaj Gujwar, Sagar Chandurkar, Dipak Banker, Yogini Khubalkar, Prof. Akashi Palawan,"AUTOMATIC SOLAR TRACKING SYSTEM WITH OVERCHARGING PROTECTION", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133123.

Abstract: Forests are part of the important and indispensable resources for human survival and social development that protect the balance of the earth ecology. In recent years, the frequency of forest fires has increased considerably due to climate changes, human activities and other factors. Currently, Forest Fire prevention methods largely consist of Patrols, Observation from watch towers, Satellite Monitoring. To restrict smuggling of forest resources and to save the forests from fires around the globe some preventive measures need to be deployed. Although observation from watch towers is easy and feasible, it has several defects. In the first place, this method requires many financial and material resources and a trained labor force. Second, many problems with fire protection personnel abound, such as carelessness, absence from the post, inability for real-time monitoring and the limited area coverage. We are developing such a system using WSN which can be used to restrict this smuggling and to help our natural vegetation form forest fires. animal detection have been an important field in order to have a better understanding on animal behavior and to restrict the damages done to humankind when they are outside the forest by reporting to authority immediately. In this project we propose a wireless sensor network paradigm for real-time forest fire and conservation detection. The wireless sensor network can detect and forecast forest fire, increase in carbon-dioxide, decrease in soil moisture and also falling of trees more promptly. This project mainly describes the data collecting and processing in wireless sensor networks for real-time forest fire and conservation detection. In this project to the neck of animal this light weight designed system is attached such that spark generating sensor will be very close to the body of that animal. Thus, if it goes over boundary line it is sensed and sends to micro controller properly. Uses ZIGBEE modem to send signals and from there it will be sent to Server Room.

Keywords: Wireless Sensor Networks (WSN), Forest Monitoring, ZIGBEE, Spark Generating Sensor, Forest Fires. Cite: Renita Pinto, Pramith Aithal, Pratheek, Sagar K C, Shreyas P, "Forest Monitoring using WSN", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133124.

Abstract: India is agricultural country where approximately 18% of crop yield is lost worldwide due to pest attack every year which is valued around Rs. 90,000 million. Large use of pesticides harms the soil, has acute toxicity to humans and animals, changes in pest status in agro-ecosystems, high cost of control practices, residue problems in environment, etc. Whiteflies are well-known harmful insects present on leaves of plant, excrete sticky honeydew, cause yellowing or death of leaves and harm the crop yield. The increase of whiteflies has been mostly relied on visual judgment by farmers. The visual judgment by farmers for density of whiteflies has been less accurate because of the different levels of identification skills. Also, it takes long time for detection of Whiteflies present on leaves in laboratory. Due to economic importance of crops and strong impacts of damage levels, detection of whiteflies at early stages has become important.In proposed solution, using android application, we are calculating affected area of plant and based on affected area we are calculating severity of disease. Also we will suggest treatment in Hindi for detected disease. Detection of plant diseases is an important research topic as it may prove benefits in monitoring large field of crops, and thus automatically detect diseases from symptoms that appear on plant leaves. Thus automatic detection of plant disease with the help of image processing technique provides more accurate and robot guidance for disease management. Comparatively, visual identification is less accurate and time consuming.

Keywords: Image Processing, Plant Disease, HSV(Hue Saturation Value), Machine Learning. Cite: Divesh.B.Patil, Shubham.R.Darekar, Atul.R.Gaikwad, Tejas.S.Ugale, Prof.Y.S.Gite,"A Plant Disease Detection System Using Image Processing ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133125.

Abstract: Counterfeiting of currency has become a real threat to the livelihood of people as well as the economy of our country. Though fake currency detectors are available, they are restricted to banks and corporate offices leaving common people and small businesses vulnerable. So, in this project, we will investigate the various security features of Indian currency and then, prepare a software-based system to detect and invalidate fake Indian currency by using advanced image processing and computer vision techniques. This currency authentication system is designed completely using Python language in Jupyter Notebook environment. Keywords: Fake currency, counterfeit detection, image processing, feature extraction, Bruteforce matcher, ORB detector Cite: Ms. R Lalitha, Saikrishna Satheesan, Nandana Kevees, Gaurav Prashant Kalgutkar, Humbrekhail Fawaz Ahamed,"Fake Currency Detection Using Image Processing", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133126.

Keywords: YOLOv7 , YOLOv8, Ensemble learning, nutrition monitoring system. Cite: Krishnaraj S, Prashanth D, Prasiddhi Nayak, Sathwik Rao K, Jyothi V Prasad," WELLWISE: ADVANCED NUTRITION MONITORING SYSTEM", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133127.

Abstract: "CROP CARE" is an online application that uses machine learning to provide personalized suggestions on crop selection, fertilizer use, and disease control. It truly transforms crop farming. Users may optimize yields and sustainability by entering their location and receiving personalized advise based on the local climate and soil characteristics. From user-uploaded photographs, its image recognition quickly detects crop diseases, providing a prompt diagnosis and treatment advice. Additionally, the website makes it easier to share illness data with specialists and Krishi Bhavan, as well as to sell to vendors. Farmers obtain competitive rates by putting suppliers to the test through manual bidding. This easily navigable tool advances food security and sustainability on a single, easily accessible platform by encouraging sustainable practices, boosting production, and strengthening resilience in agriculture.

Keywords: Machine Learning, Crop Selection, Image recognition, Instant diagnosis, Resilience . Cite: Sreeja Rajesh, Smruthi Poojary, Sumanth Shetty, Wasif Ahmed,"CROP CARE-A WEB APPLICATION FOR CROP MANAGEMENT", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133128.

Keywords: Check truncation system, online banking, remote check deposit, digital check forgery, forgery detection, image forensics, expert system, JPEG artifacts. Cite: Anvitha Jain, Niha Kauser, Shravya KS, Sinchana Venugopal, Mr.Narendra UP,"Automated Bank Cheque Verification System", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133129.

Abstract: The Crop Management System (CMS) is an innovative web application designed to revolutionize agricultural practices by integrating advanced technologies. This project encompasses four essential modules: Crop Prediction, Disease Detection, and Government Forum Dashboard. Leveraging the power of Python, the CMS aims to provide a comprehensive solution for modern farming. The Crop Prediction module employs machine learning algorithms to forecast optimal crops based on factors such as soil type, climate, and historical data. This feature empowers farmers to make informed decisions, enhancing crop yield and profitability. The Disease Detection module employs image processing techniques to identify and diagnose diseases affecting crops, allowing for timely intervention and reducing yield loss. The Government Forum Dashboard acts as a central hub for stakeholders to exchange information, policies, and best practices, fostering a collaborative ecosystem. Implemented as a web application, the CMS ensures accessibility across devices, providing a user-friendly interface for farmers and stakeholders. The backend is built using Python, leveraging its versatility and robust libraries for data processing, machine learning, and web development. In conclusion, the Crop Management System addresses critical aspects of modern agriculture, ranging from crop selection to disease management, marketing, and policy advocacy. By harnessing the power of Python and cutting-edge technologies, this project stands as a pivotal tool for advancing agricultural practices, ultimately contributing to sustainable and efficient farming practices.

Keywords: Data Mining, Crop Recommendation system, Resource Optimization, Prediction. Cite: Prof. Narode. Priyanka. P., Shelke Kirti R., Salunke Ashlesha V., Nanekar Tejaswini N., Deokar Aditi R.P,"Advancement in Integrated Crop Management System for Sustainable Agriculture", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133130.

Abstract: In the realm of online education and artistry, the limitations of conventional mice for digital drawing and illustration have posed challenges for educators, students, and artists. The impracticality of a mouse hinders the fluidity and precision crucial for effective teaching and learning, particularly in visually dependent subjects. Additionally, the high cost of specialized drawing tablets has restricted access, limiting creative expression in the digital realm. The "AirInk Studio" project addresses these challenges by introducing an innovative desktop application. Powered by Python, OpenCV, Mediapipe, and Tkinter, it utilizes computer vision and hand tracking for a seamless drawing experience. Boasting diverse brush styles, an undo feature, and an extensive color palette, the project caters to varied artistic preferences. Not only does it redefine online education, but it also empowers artists with an affordable and versatile digital canvas, democratizing creativity in the virtual space. Furthermore, the project expands its capabilities with features like drawing shapes, including circles, rectangles, and lines, as well as a text box feature for annotations and labels. The integration of a chat web application, developed with React.js and Firebase, enables real-time collaboration and connection among users. Moreover, a community showcase web app, leveraging React.js and Firebase, provides users with a platform to share and exhibit their creations, fostering a vibrant digital art community. Together, these enhancements elevate the "AirInk Studio" project, enriching the digital art experience and promoting collaboration and creativity among users.

Keywords: Python, OpenCV, Mediapipe, Tkinter, React.js, Firebase, Computer vision and Hand tracking.. Cite: Prof. Archana Dirgule, Shreyas Shinde, Amey Ashtankar, Mandar Terkhedkar, Vedant Ingale, "AirInk Studio: A Virtual Drawing Model", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133131.

Abstract: As COVID-19 spread worldwide, many major grain-producing countries have adopted  measures to restrict their grain exports; food security has aroused great concern from various parties. How to improve grain production has become one of the most important issues facing all countries. However, crop diseases are a difficult problem for many farmers so it is important to master the severity of crop diseases timely and accurately to help staff take further intervention measures to minimize plants being further infected. In this paper, a restructured residual dense network was proposed for tomato leaf disease identification; this hybrid deep learning model combines the advantages of deep residual networks and dense networks, which can reduce the number of training process parameters to improve calculation accuracy as well as enhance the flow of information and gradients. The original RDN model was first used in image super resolution, so we need to restructure the network architecture for classification tasks through adjusted input image features and hyper parameters. Experimental results show that this model can achieve a top-1 average identification accuracy of 95% on the Tomato test dataset in AI Challenger 2018 datasets, which verifies its satisfactory performance. The restructured residual dense network model can obtain significantimprovements over most of the state-of-the-art models in crop leaf identification, as well as requiring less computation to achieve high performance.

Keywords: Residual dense network, leaf disease identification, agricultural artificial intelligence,tomato leaf diseases. Cite: Prof. Aghav S.E., Gunjal Vicky D., Mahale Shubham R., Rajude Rohit D., Avhad Abhishek N., "Tomato Leaf Disease Identification by Restructured Deep Residual Dense Network ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133132.

Abstract: In Bangladesh potato is one of the major crops. Potato cultivation has been very popular in Bangladesh for the last few decades. But potato production is being hampered due to some diseases which are increasing the cost of farmers in potato production. However, some potato diseases are hampering potato production that is increasing the cost of farmers. Our main goal is to diagnose potato disease using leaf pictures that we are going to do through advanced machine learning technology. This paper offers a picture that is processing and machine learning based automated systems potato leaf diseases will be identified and classified. Image processing is the best solution for detecting and analysing these diseases. In this analysis, picture division is done more than 2034 pictures of unhealthy potato and potato's leaf, which is taken from openly accessible plant town information base and a few pre prepared models are utilized for acknowledgment and characterization of sick and sound leaves. Among them, the program predicts with an accuracy of 99.23% in testing with25% test data and 75% train data. Our output has shown that machine learning exceeds all existing tasks in potato disease detection.

Keywords: Machine learning,VGG16, CNN, potato leaf Cite: R.Arthi, H.Mohammed Haarish, "Potato Disease Detection using Deep Learning ", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133133.

Abstract: The world of electrical and electronics is witnessing a daily increase in the use of DC-DC converters. The higher-frequency DC-DC converters reduce system bulk and increase power density; they are widely used in various applications. By Introducing the Resonant Converter, it reduces the switching loss and improves the system performance. The growing trend of industries relying more and more on machinery makes it necessary to conduct a thorough analysis in order to comprehend and compile information on the different isolated topologies and the most widely used resonant switching layout. This will optimize design and development of converter. It has able potential to enhance the performance and reduce the energy consumption of systems, contributing to a more sustainable and cost-effective industrial landscape. The main objective is to develop a compact and reliable converter that takes a single 230V DC input and provides two distinct output voltages: 100V DC for the spindle motor and 42V DC for powering various essential components.

Keywords: DC-DC Converter, Dual Output, LLC, ZVS. Cite: Athishwaran N, Sarigha Sriram G, Sribalaji S, Maithili P, "Dual Output DC-DC Isolated Resonant Converter", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133134.

Abstract:  Chronic kidney disease (CKD) is a prevalent and serious health condition that necessitates accurate and timely diagnosis for effective management and treatment. In this study, we explore the application of machine learning algorithms, specifically K-Neighbors Classifier, Decision Tree Classifier, Random Forest Classifier, and Extra Trees Classifier, for predicting chronic kidney diseases. The research encompasses a comprehensive analysis of a dataset containing relevant medical information such as age, blood pressure, blood glucose levels, and serum keratinize. The dataset undergoes meticulous preprocessing, including handling missing values, encoding categorical variables, and scaling numerical features. Feature selection techniques are employed to identify the most influential factors contributing to the prediction of chronic kidney diseases. Subsequently, the dataset is divided into training and testing sets to facilitate the training and evaluation of the machine learning models. The selected classifiers are trained on the training set, and their performances are evaluated on the testing set using metrics such as accuracy, precision, recall, F1 score, and ROC-AUC. The model with the highest performance is further fine-tuned through hyper parameter tuning to enhance its predictive capabilities. The outcomes of this research provide insights into the effectiveness of machine learning models in predicting chronic kidney diseases. The results underscore the importance of careful model selection, feature engineering, and hyper parameter tuning in optimizing predictive performance. The developed model holds promise for aiding healthcare professionals in early detection and management of chronic kidney diseases, potentially improving patient outcomes and reducing healthcare costs. However, the deployment of such models in real-world healthcare settings should be approached with consideration of ethical implications and domain-specific nuances.

Keywords: Kidney, Machine learning algorithms, Average accuracy, blood vessels Cite: Dr.V.Suganthi, M.Sabari,"Chronic Kidney Disease Detection Using Machine Learning Algorithms", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133135.

Keywords:     Fingerprint recognition, Biometric access control, Fingerprint scanner , Fingerprint-based door security , Biometric door entry , Electronic door lock Cite: Dr.G.Maria Priscilla, Prithiviraj P.C,"SMART AND SECURE DOOR OPENING SYSTEM USING FINGERPRINT FOR GOVERNMENT ORGANIZATIONS", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133136.

Abstract: A wireless sensor network (WSN) of distributed autonomous sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. and to cooperatively pass their data through the network to a main location. The more modern networks are bi-directional, also enabling control of sensor activity. The development of wireless sensor networks was motivated by military applications such as battlefield surveillance; today such networks are used in many industrial and consumer applications, such as industrial process monitoring and control, machine health monitoring, and so on. In WSN, the sensor nodes have a restricted broadcast range, and their processing and storage capabilities as well as their energy resources are also limited. Routing protocols for wireless sensor networks are responsible for maintain the routes in the network and have to ensure reliable multi-hop communication under these conditions. In this paper, we give a survey of routing protocols for Wireless Sensor Network and compare their strengths and boundaries. Keywords: Wireless Sensor Networks, Routing Protocols, Cluster Head Cite: Dr.P.Kavitha, P.Elamaran,"Secure Data Transfer via Internet cryptography and Image Steganography in Wireless Sensor Networks", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133137.

Abstract: The increasing prevalence of distributed denial of service (DDoS) attacks has highlighted the urgent need for robust protection strategies, particularly at the application layer in the computers. DDoS attacks [2] targeting the application layer exploit vulnerabilities in web applications and services, making traditional network-layer defenses ineffective. This abstract explores effective measures for protecting against application layer DDoS attacks [2], emphasizing proactive strategies for safeguarding web applications, and ensuring uninterrupted service availability. Prominent protection measures include the deployment of web application firewalls (WAFs), which analyze incoming traffic for suspicious patterns and block malicious requests. Rate-limiting mechanisms can be used to reduce the influx of requests from a single source, mitigating the impact of an attack. Application-layer DDoS detection systems [5], supported by machine learning algorithms, enable rapid identification of abnormal behavior and malicious traffic.

Keywords: DDoS attacks, Application Layer DDoS attacks, HTTPS Floods, Slowloris Attack, DNS Amplification. Cite: Bhargavi Nalluri, Viswanadha Phani Koushik, Zunaid Yasir Syed, Kantam Pujitha, Gandi Lakshmi Vara Prasad,"Introduction to Application Layer DDoS Attacks And Protection Against It", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133138.

Abstract: Agriculture is the backbone of nations, and safeguarding crops from diseases is vital for food security. This research focuses on tomato, a quintessential crop present in various culinary forms, emphasizing the importance of disease prevention for maintaining quality. This article presents an innovative approach utilizing Machine Learning algorithms for early prediction and detection of tomato plant leaf diseases. A curated datasets was prepared, and operations such as feature extraction and rigorous testing were performed on it using eight diverse machine learning algorithms

Keywords: machine learning algorithm, disease prevention, feature extraction Cite: N. Veeratharini, K. Swathi, R. Arthi, "Tomato Leaf Disease Detection", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133139.

Abstract: This innovative mobile application tackles road construction and maintenance challenges with three core functions. Real-time construction updates empower users to plan routes effectively, minimizing disruption. Traffic data analysis helps users navigate around congestion hotspots, reducing travel times. Finally, the app serves as a communication hub for reporting road issues, proposing enhancements, and sharing feedback. This collaborative approach fosters community participation in road upkeep, ensuring targeted and responsive maintenance efforts. By bridging the gap between authorities and the public, the app promotes transparency, efficiency, and engagement. This informed and engaged community contributes to a future of cooperation, accountability, and continuous improvement in road infrastructure management. The app not only enhances travel experiences but also contributes to economic growth and road safety. Its user-friendly interface sets a new standard for the sector, and its ongoing development and adoption hold the potential to further refine road construction and maintenance practices.

Keywords: Real-time updates, Route planning, Traffic data analysis,  User-friendly interface. Cite: M. Hemalatha, V. Dharshana, "POINEERING STRATEGIES FOR ROAD CONSTRUCTION AND ONGOING CARE", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133141.

Abstract: Manual colorization of black and white pictures could be a difficult errand and wasteful. It has been endeavored utilizing Photoshop editing, but it demonstrates to be troublesome because it requires broad investigate and a picture can take up to one month to colorize. A practical approach to the assignment is to actualize advanced picture colorization methods. The literature on picture colorization has been an range of intrigued within the final decade, because it stands at the juncture of two arcane disciplines, advanced picture preparing and profound learning. Endeavors have been made to utilize the ever-increasing availability of end-to-end profound learning models and use the benefits of exchange learning. Picture features can be consequently extricated from the preparing information utilizing profound learning models such as Convolutional Neural Systems (CNN). This could be assisted by human mediation and by utilizing as of late created Generative Antagonistic Systems (GAN). We actualize picture colorization utilizing different CNN and GAN models whereas leveraging pre-trained models for way better highlight extraction and compare the execution of these models. Key Words: Deep learning, Pre-trained model, CNN, GAN, image colorization, Pix2pix Cite: Dr.S. Govindaraju, Gowtham T, "COLORIZATION OF BLACK AND WHITE IMAGES", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133141.

Abstract: Customer churn is when customers stop using a particular telecom service and switch to a competitor or cancel their contract altogether. This presents a major challenge in the telecommunication industry, as acquiring new customers is typically more expensive than retaining existing ones. To reduce the churn rate, businesses can analyze large volumes of customer data to gain insightful knowledge about customer behavior, preferences, and potential churn tendencies using machine learning algorithms. By utilizing machine learning models, telecom companies can gain an understanding of their customers' preferences and implement retention strategies that can increase customer satisfaction. In this study, we aim to illustrate the effectiveness of Random Forest, Cat Boost, and XG Boost models in accurately predicting customer attrition.

Keywords: Customer churn, Telecommunication Industries, Machine Learning algorithms, Retention Strategies,  Insightful Knowledge. Cite: V. Chandana, S. Manohari, Y. Lakshmi Prasanna, SK. Feroze Moinuddee, DR. K.Pavan Kumar, "CONNECTIVITY CRISIS: TACKLING TELECOM CHURN WITH MACHINE LEARNING", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133142.

Abstract: In recent years, significant progress has been made in the field of gesture detection and hand tracking, presenting both opportunities and challenges for human-computer interaction (HCI). This research focuses on harnessing these advancements to develop a hand gesture-controlled virtual mouse, particularly in light of the COVID-19 pandemic, where touchless interaction methods have gained prominence. The proposed system utilizes a standard webcam and Python with OpenCV for implementation, aiming to provide users with a seamless and intuitive interface for computer interaction. By interpreting hand movements as mouse actions, the system aims to reduce reliance on physical input devices and minimize direct contact with computer peripherals. Challenges such as ensuring robustness to varying conditions and achieving real-time performance are addressed in the development process, with the goal of supporting user engagement and productivity in virtual environments.

Keywords: OpenCV, Python, hand tracking Cite: M. Hemalatha, V. Sreeja, S. Aswathi, "Hand Gesture Controlled Virtual Mouse", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133143.

Abstract: This project introduces a comprehensive document processing application that encompasses text extraction and file organization functionalities. The application offers a user-friendly interface for uploading documents and provides options for both text extraction and file sorting. Utilizing libraries for PDF parsing and Optical Character Recognition (OCR), the application extracts text from PDF and JPG files. Additionally, it employs file extension-based sorting to categorize files into separate folders according to their types. The backend logic efficiently handles file manipulation tasks, including folder creation and file movement, with robust error handling mechanisms in place. Moreover, the application ensures data security and user privacy during file processing and storage. Through thorough testing and validation, the application guarantees reliability and accuracy in document processing. This project aims to streamline document management processes, enhance user productivity, and provide a seamless experience for users dealing with diverse document formats.

Keywords: DocumentProX Cite: Ms. Devibala Subramanian, Vigneshwaran. J, "EFFICIENT DATA ENTRY AND DOCUMENT CLASSIFICATION USING AI FOR BUSINESS ABSTRACT", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133144.

Abstract: Character Recognition is a technology that enables to convert different types of documents, such as scanned paper documents into editable data. The ability to understand these inputs varies in each person according to many factors. OCR is a technology that functions like human ability of reading. Although OCR is not able to compete with human reading capabilities, it can convert the content from the image files. Automatic text recognition aims at limiting these errors by using image preprocessing techniques that bring increased speed and precision to the entire recognition process. In the proposed system, the written content is converted into text content using the pattern recognition system and the same is stored in file. The proposed method uses the Learning based Spatio-Temporal Algorithm to extract the written contents. The primary objective of this system is to written content recognition system and to create the android based mobile application to save the handwriting in to text file. Robust data capture solutions handle multiple document formats and can be used with both electronic and paper documents, eliminating paper and reducing manual identification and data entry of document content into other systems. Cite: Dr.V. Suganthi, Vasanth.S,"HANDWRITTEN TEXT CONTENT CLASSIFICATION SYSTEM USING ANDROID", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133146.

Abstract: The fake news on social media and various other media is wide spreading and is a matter of serious concern due to its ability to cause a lot of social and national damage with destructive impacts. A lot of research is already focused on detecting it. To avoid fraudulent post for job in the internet, an automated tool using machine learning based classification techniques is proposed. Different classifiers are used for checking fraudulent post in the web and the results of those classifiers are compared for identifying the best employment scam detection model. It helps in detecting fake job posts from an enormous number of posts. Two major types of classifiers, such as single classifier and ensemble classifiers are considered for fraudulent job posts detection. However, experimental results indicate that ensemble classifiers are the best classification to detect scams over the single classifiers. This Paper makes an analysis of the research related to fake news detection and explores the traditional machine learning models to choose the best, in order to create a model of a product with supervised machine learning like random forest algorithm, that can classify fake news as true or false, by using tools like python Scikit-learn. This process will result in feature extraction and vectorization; we propose using Python Scikit-learn library to perform tokenization and feature extraction of text data, because this library contains useful tools like Count Vectorized and Tiff Vectorized.

Keywords: Fake news, random forest algorithm, ensemble classifier, Accuracy, feature extraction Cite: Dr.P.Manikandaprabhu, Loganisha S, "Machine Learning Algorithm for Fake Job Detection Systems", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133147.

Abstract: Image interpretations the art of hiding the fact that communication is taking place, by hiding information in other information. Many different carrier file formats can be used, but digital images are the most popular because of their frequency on the Internet. In the proposed system, the novel channel-dependent payload partition strategy based on amplifying channel modification probabilities is proposed, so as to adaptively assign the embedding capacity among RGB channels. This incorporates the content in the selected image pixels which is used to hold the encrypted message. The delivery system for encrypting messages into ciphertext using a shared key then sends to the receiver device using the server as intermediate devices. Here the multi level security is applied to secure the communication channel. In this first level security layer is created using the end to end encryption system. The next levels are created between sender and server as well as server as receiver device. Additionally, the data security is applied in the server while holding the data when the receiver device connectivity is unavailable.

Keywords: communication, RGB channels, multi level security, device connectivity, different carrier file formats Cite: Ms.R.ARTHI, Christo.P.S, "SECURE DATA TRANSMISSION USING IMAGE INTERPRETATION", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133148.

Abstract: In the rapidly evolving environment of online education, personalized learning experiences have become the cornerstone for improving student engagement and performance. However, the abundance of educational resources available on online learning platforms presents a significant challenge to students in identifying and using content that meets their individual needs and preferences. To address this challenge, this project proposes to develop a new machine learning-based recommendation system specifically adapted for e-learning platforms. Using advanced algorithms and user data, the system aims to provide personalized recommendations that match individual learning goals, skill levels and preferences. By analyzing user interactions and behavior patterns, the system identifies and reveals the most relevant and useful resources for each learner, facilitating more effective and engaging learning. This project represents a pioneering effort to harness the power of machine learning to revolutionize the world of online education, enabling learners to reach their full potential in a dynamic and adaptive learning environment. Cite: Ms.R.ARTHI, SHIYAM GANESH.S,"PERSONALIZED ONLINE LEARNING PLATFORM RECOMMENDATION USING MACHINE LEARNING", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.133149.