A switching bi-directional buck-boost converter (SBBBC) has been proposed for integration into a vehicle-to-grid (V2G) system. This topology facilitates bi-directional energy flow between the hybrid energy storage system (HESS), comprising a Li-battery and a supercapacitor (SC), and the grid. The SBBBC offers both buck-boost capability and energy management functionality. Stability analysis of the topology in both boost and buck modes has been conducted using the state-space averaging method. Additionally, a control strategy has been devised based on the state of charge (SOC) of the energy storage system to ensure stable output voltage and current In terms of charging the Li battery, a constant current (CC) and constant voltage (CV) mode are employed. Furthermore, voltage and current controllers have been designed in the frequency domain utilizing bode plots. The overall feasibility of the topology, as well as the adequacy of the designed controller and control strategy, have been assessed to ensure effective operation within the V2G system.

Keywords : Buck Boost converter, FUZZY LOGIC Controller ,MATLAB, Li-Battery , HESS

Authors : S Jaffer shareef , C Sai Prathyusha , S. Shaheen , P Azhar Ali Khan , S Bhuvaneswari , M Reddy Vamsi , B Surendhra

Title : Analysis and Implementation of a Switching Bi-Directional BUCK-BOOST Conerter for the HEV Applications by using FLC

Volume/Issue : 2024;1(4 (October-December))

Page No : 80 - 84

Knee Osteoarthritis (KOA), commonly referred to as degenerative joint disease of the knee, is usually caused by articular cartilage gradually losing its structure due to wear and stress. Worldwide, patients with osteoarthritis (OA), especially those with knee OA, have significant disability as a result of this most frequent form of arthritis. Osteoarthritis (OA) is a prevalent degenerative musculoskeletal condition. This illness impacts about 5% of the global population. Arthritis (OA) most commonly affects the knee, where articular cartilage at the ends of bones permanently deteriorates. Over time, the condition known as knee osteoarthritis (OA) worsens and affects the whole knee joint. Despite their time-consuming nature and sensitivity to user variable, manual diagnosis, segmentation, and annotation of knee joints are still employed in clinical practice to diagnose osteoarthritis. The proposed system effectively detects knee osteoarthritis in the MRI images in which median filter is used in the image pre-processing to reduce the noise, Fuzzy C- Means algorithm is used image segmentation, Fuzzy C-Means algorithm is used for segmentation and Convolutional Neural Network (CNN) is used for disease identification. Contrast, Homogeneity, Energy, Entropy and Correlation features were extracted from the Region of Interest (ROI) of the segmented image for training and testing the CNN classifier. MATLAB (R2021a) software were used to implement the proposed system or method. The performance parameters sensitivity, specificity, accuracy, and precision of the proposed system are obtained as 94.19%, 92.60%, 95.77%, and 93.4%, respectively.

Keywords : MRI, CNN, FCM, ROI,DL, AI, ML, MATLAB

Authors : S Muni Ratnam , D Ragulamma , P Tejaswani , G Swathi , K Vijayalakshmi

Title : Identification of Knee Osteoarthritis Disease using Convolutional Neural Networks

Volume/Issue : 2024;1(4 (October-December))

Page No : 73 - 79

The economic development of any country mainly depends on agriculture. Rice is a staple crop and a significant food source for a large portion of the world's population and rice usage is higher in Asia. But, the rice crop suffers from various diseases that greatly affect yield capacity and have an impact on food security. For the effective disease management and crop detection, the disease need to be detected early and diagnosis to be done at the earliest. By automating the disease detection process, the system can enable early intervention and timely management practices, leading to improved crop yield and reduced economic losses. The proposed system effectively identifies paddy leaf disease, in which a median filter is used to reduce the noise, a Fuzzy C-Means (FCM) algorithm were used for segmentation, and a Convolutional Neural Network (CNN) were uses for classification. Contrast, homogeneity, energy, entropy, and correlation features are extracted from the segmented image for training and testing the CNN classifier. The proposed system effectively detects Brown Spots (BS), Leaf Blasts (LB), and Bacterial Blight (BLB) disease. The proposed system was implemented by using MATLAB (R2021a) software and tested with the help of three data sets with respect to performance parameters: sensitivity, specificity, accuracy, and precision. The maximum achieved accuracy of the proposed system is 98.68%.

Keywords : CNN, FCM, Brown Spots (BS), Leaf Blasts (LB), and Bacterial Blight (BLB).

Authors : S Muni Ratnam , P Bhavitha , P Asma Khanum , S Madhavi , M Bharathi

Title : Identification of Paddy Leaves Disease using Convolutional Neural Networks

Volume/Issue : 2024;1(4 (October-December))

Page No : 66 - 72

The abstract outlines the concept and purpose of a Mental Health Assistant Chatbot, employing advanced Neural Network techniques. This chatbot aims to provide vital support and resources for individuals dealing with mental health challenges. Utilizing Neural Network architectures, the chatbot engages in empathetic conversations, offering users a safe and confidential platform to discuss their emotional well-being. The chatbot employs sentiment analysis and context comprehension to assess users' mental states and emotional needs accurately. It provides personalized coping strategies, resources, and referrals to professional help based on users' inputs. Trained on diverse datasets of mental health information, the chatbot's Neural Network model enables it to generate empathetic and understanding responses. The continuous learning process ensures that the chatbot evolves its understanding of user concerns and keeps up with the dynamic landscape of mental health conversations. This Mental Health Assistant Chatbot, powered by Neural Network techniques, serves as an accessible and stigma-free resource, contributing to early intervention, de-stigmatization, and improved mental health support for users.

Keywords : NLP Techniques, Feed Forward Neural Networks (FNNs), DL, ML, AI.

Authors : T Somasekhar , S Mizba Nawaz , G Harsha Veena , P Nandini , C Akila

Title : Chatbot for Mental Health Support utilizing Neural Network Technologies

Volume/Issue : 2024;1(4 (October-December))

Page No : 61 - 65

An program that reviews written responses and assigns grades in a manner akin to that of a human being is known as an AI-Driven Approach to Verify Subjective Answer. The system is made up of built-in artificial intelligence sensors that, much like a human, validate responses and assign points appropriately. The Microsoft.NET Framework is a new computer platform designed for front end development that makes it easier to create applications in the widely dispersed online world.to offer a code-execution environment that ensures code, including code from unidentified or partially trusted third parties, is executed safely. There are two primary parts of the.NET framework :The runtime for Common Language is: The.NET Framework is built on the common language runtime. The runtime might be compared to an agent that oversees.

Keywords : Microsoft .NET Framework , Active Server Pages Network Enable Technologies, GUI ,HTML.

Authors : B J Priyanka , U Akanksha , D Bhavya , D S Basheerun , K Hemalatha , S Keerthi

Title : An AI Driven Approach To Verify Subjective Answers

Volume/Issue : 2024;1(4 (October-December))

Page No : 57 - 60

The software defect prediction technique yields result that development teams may examine and further contribute to industrial results. It finds all the problematic code portions, helps software developers uncover bugs, and helps them design their testing methods with the help of the model prediction. It is essential to know what percentage of categories yield the accurate forecast for early detection. Moreover, software-defected data sets are supported and at least partially recognized due to their huge dimension. Random forests (RF) and artificial neural networks (ANN) are the machine learning techniques utilized in this research. The forecast for defects is created using historical data. The outcomes showed that the artificial neural network classifier performed better than the random forest classifier.

Keywords : Machine Learning, Artificial Neural Networks, Random Forests, and Software Defect Prediction.

Authors : B J Priyanka , S Reddy Bhavana , K Pravallika , M Sravani , P Navya

Title : Predictive Analytics for Software Defect Forecastig Based on Machine Learning

Volume/Issue : 2024;1(4 (October-December))

Page No : 51 - 56

Bike sharing systems have emerged as sustainable and convenient transportation alternatives in urban environments. Understanding and predicting bike usage patterns is crucial for optimizing system efficiency and enhancing user experience. In this paper developed a machine learning model to predict bike sharing demand based on various factors, such as weather conditions, time of day, day of the week, and other relevant features. The dataset utilized for this paper includes historical bike sharing data, encompassing information on the number of bikes rented at different time intervals, weather conditions, and temporal attributes. The primary objective is to create a robust predictive model capable of forecasting bike demand accurately. The methodology involves preprocessing and cleaning the dataset, feature engineering to extract relevant information, and employing a machine learning algorithm, such as a regression model or ensemble method. The model will be trained on a subset of the dataset and validated using another portion to ensure generalizability.

Keywords : CSV (Comma Separated Values), Seaborn, NumPy, UML, Kernel.

Authors : M Veeresh Babu , A Tejesh Babu , V Sasi Kumar Reddy , S. Sameer Ahamed , K Udaya Kiran

Title : Bike Sharing : A Forecast using Machine Learning Techniques

Volume/Issue : 2024;1(4 (October-December))

Page No : 44 - 50

This study proposes an innovative method for detecting and grading diabetic retinopathy using publicly available fundus images. By integrating image processing and machine learning, it accurately identifies indicators like exudates and microaneurysms, crucial for assessing the condition's severity. Results show high accuracies, with support vector machine and K-Nearest neighbor methods achieving 92.1% for exudate grading, and decision tree model reaching 99.9% for microaneurysm grading. This automated approach holds promise for early detection and precise grading, facilitating timely intervention and improving patient outcomes.

Keywords : Diabetes, Retinopathy, Diabetic Patients, AI , DL.

Authors : Pakala Chandra Sekhar , M Reddy Varun , C Vinay , P Pawan Kalyan , S Prashanth

Title : Early Detection of Diabetic Retinopathy from Fundas Retinal Images using AI

Volume/Issue : 2024;1(4 (October-December))

Page No : 40 - 43

Air pollution is a critical environmental issue affecting numerous countries around the world, and India is no exception. The alarming levels of air pollution in many Indian cities have serious implications for public health, the environment, and the overall quality of life. This abstract presents an analysis of the current state of air pollution in India and a prediction model to estimate future pollution levels. The analysis of air pollution in India involves examining various factors such as industrial emissions, vehicular pollution, biomass burning, and dust particles. Additionally, meteorological conditions, including temperature, wind speed, and rainfall, also play a significant role in air pollution levels. Data from monitoring stations, satellite imagery, and other relevant sources are used to gather information for the analysis. The study utilizes advanced data analytics techniques, including machine learning algorithms, to develop a predictive model for estimating air pollution levels. Historical pollution data, along with meteorological parameters, are used as inputs to train the model. The model's objective is to forecast pollution levels in different regions of India for specific timeframes, such as daily, weekly, or monthly intervals. The abstract concludes by discussing the potential applications of the analysis and prediction model. It highlights the significance of such models in aiding policymakers, urban planners, and environmental agencies in making informed decisions and implementing effective strategies to mitigate air pollution. The predictions can assist in issuing timely health advisories, implementing pollution control measures, and optimizing resource allocation for air quality management.

Keywords : Supervised Learning , Air Pollution, ML, AI, DL.

Authors : D Siva Sankara Reddy ,Yadagiri , Venkatsai , Vinod Kumar , Ravindra

Title : Analyses and Predict the Air Pollution in India using Memory Based Learning Approaches

Volume/Issue : 2024;1(4 (October-December))

Page No : 31 - 39

Our project presents an innovative approach to address the crucial issue of plant disease identification through the utilization of deep learning techniques. Agricultural productivity is significantly affected by plant diseases, leading to economic losses and food security concerns. In this research, a comprehensive dataset comprising images of healthy and diseased plants is collected and pre-processed for training deep convolutional neural networks (CNNs). The proposed system harnesses the power of deep learning to automatically learn intricate patterns and features from plant images, enabling accurate classification between healthy and diseased states. The trained model is evaluated on an independent dataset to assess its classification performance. Various deep learning architectures, such as VGG, ResNet, and Inception, are experimented with to identify the most suitable architecture for achieving high accuracy and robustness. To enhance the model's generalization capability, data augmentation techniques are employed during training. Transfer learning is also explored, allowing the pre-trained models to be fine-tuned for the specific task of plant disease classification. The performance metrics, including accuracy, precision, recall, and F1-score, are thoroughly evaluated to quantify the model's effectiveness. The proposed deep learning-based plant disease classification system holds great promise for real-world agricultural applications. Its automated and accurate nature has the potential to revolutionize plant disease management by enabling early detection and timely intervention. As a result, this research contributes to the advancement of precision agriculture practices, helping to mitigate the adverse impacts of plant diseases and promote sustainable agricultural production.

Keywords : Recycled Deep Learning Techniques, CNN, VGG, ResNet, Inception , Data Augmentation..

Authors : D Siva Sankar Reddy , S Mahammada , R Jyothika , P Deekshitha , K Gowthami

Title : Plant Disease Classification Using Deep Learning Techniques

Volume/Issue : 2024;1(4 (October-December))

Page No : 27 - 30

The Al Virtual Mouse uses computer vision techniques to track hand movements and translates them into cursor movements on the screen. The system is designed to be intuitive and user-friendly, allowing users to interact with their computer without the need for a physical mouse. The virtual mouse is developed using Python and OpenCV libraries. The project includes the implementation of various image processing algorithms, such as hand segmentation, feature extraction, and classification. Moreover, it is robust to various lighting conditions, backgrounds, and hand sizes. The developed system provides an alternative to conventional mouse devices, particularly for individuals with disabilities or those who prefer a more natural way of interacting with their computers. The target of this project is the invention of something new in the world of technology that helps an individual work without the help of a physical mouse. It will save the user money and time.

Keywords : Gesture recognition, CNN algorithm, OpenCV, Mediapipe, Virtual Mouse, AI chatbot.

Authors : T Somasekhar , P Phani Bhushan , O Ravi Kumar, K Vamsidhar Reddy , A Uday Vardhan

Title : Gestured Control Virtual Mouse with AI Chatbot

Volume/Issue : 2024;1(4 (October-December))

Page No : 15 - 18

Water pollution has become a major concern in recent times due to the contamination and pollution of drinking water. The ecosystem's life cycle may be impacted by the diseases that contaminated water might spread to people and animals. Early detection of water contamination allows for the implementation of appropriate controls and the avoidance of dangerous circumstances. Real time monitoring of the water's quality is necessary to ensure a supply of pure water. As sensors, communication, and the Internet of Things (IoT) continue to advance, smart solutions for monitoring water contamination are becoming more and more important. This study presents a thorough analysis of the most recent efforts undertaken in the field of smart water pollution monitoring systems. The idea suggests an inexpensive and effective Internet of Things (IoT)-based hydrological monitoring system that continuously tracks the quality indicators. Water samples are used to evaluate the constructed model, and the parameters are sent to the cloud server for additional processing.

Keywords : pH, Temperature sensor, Water flow, Turbidity, water quality monitoring, IoT, Arduino.

Authors : R Pradeep Kumar , B Sreekanth , R Rohitha , G Shamitha , T Sai Asha , P Neelima

Title : Hydrological Monitoring using Internet of Things

Volume/Issue : 2024;1(4 (October-December))

Page No : 10 - 14

Present-day intensive care units, or ICUs, offer critically ill patients who are susceptible to several problems, including death and morbidity, round-the-clock monitoring. ICU environments produce a lot of data and call for a high staff-to-patient ratio. Making decisions and interpreting data in real time is a difficult task for clinicians. In intensive care units (ICUs), machine learning (ML) tools are advancing the early detection of high-risk events. because of more powerful computers and publicly accessible databases like the Medical Information Mart for Intensive Care (MIMIC). Techniques in ICU settings uses MIMIC data. The ICU patient risk level monitoring system plays a crucial role in improving patient safety, optimizing resource allocation, and enhancing clinical decision-making in intensive care settings. By continuously monitoring and analyzing patient data, it provides valuable insights that help healthcare providers intervene promptly and prevent adverse outcomes.

Keywords : Intensive Care Unit, Critical Care, MIMIC, ML, AI, NLP.

Authors : M Veeresh Babu , R Harshitha , A Keerthana , K Haripriya , N Manisha

Title : ICU Patient Risk Level Monitoring System using Supervised Learning Approaches

Volume/Issue : 2024;1(4 (October-December))

Page No : 5 - 9

The job selection process can be troubling for employees in today's global economy. It involves searching through newspapers, job websites, and human agents for employment opportunities. However, there is often no feedback from employers on the criteria submitted by employees. To address this, we propose the creation of intelligent agents to interact with employers and job search coordinators. These agents will use fuzzy preference rules to make decisions. The agents will also collect feedback from past and current employees to rate employers. The system will use Android 2.2, JADE- LEAP, and the Google API to provide a robust and user-friendly solution.

Keywords : Java Agent Development Environment, Lightweight Agent Platform, UML.

Authors : D Sreenivasulu Reddy , S Touheed , K Rohith Kumar Reddy , C Naveen Kumar, B Vikas

Title : Job Search System in Android Environment

Volume/Issue : 2024;1(4 (October-December))

Page No : 1 - 4