Dr.K.Vanitha

@kahedu.edu.in

ASSOCIATE PROFESSOR, Department of Computer Science and Engineering
Karpagam Academy of Higher Education

Dr.K.Vanitha


                  Download Compact PDF  
https://researchid.co/drvanithak

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Artificial Intelligence, Computer Networks and Communications, Information Systems
9

Scopus Publications

382

Scholar Citations

9

Scholar h-index

9

Scholar i10-index

Scopus Publications

  • Decision Making System for Landslide Monitoring
    K. Vanitha, Deepak S, Mathan J
    Proceedings of 8th International Conference on Intelligent Sustainable Systems Iciss 2026, 2026
    Landslides represent a critical natural hazard in mountainous and hilly terrains, frequently resulting in loss of life, damage to infrastructure, and disruption of essential services. Timely identification of unstable ground conditions is therefore essential for effective disaster mitigation. This work presents a low-cost and scalable IoT-enabled landslide monitoring and early warning framework designed for continuous real-time observation of environmental factors influencing slope stability. The proposed system integrates an Arduino-based sensing unit with soil moisture, vibration, rainfall, and gyroscopic sensors to capture dynamic variations in terrain conditions across landslide-prone zones. Sensor data are transmitted to a cloud platform, where machine learning models analyze temporal patterns and detect abnormal behaviors indicative of potential slope failure. Upon identifying risk conditions, the system immediately triggers local alerts through an on-site buzzer mechanism, enabling rapid awareness among nearby communities and authorities. Experimental deployment demonstrates the system's capability to track critical environmental changes and issue timely warnings under varying conditions. Owing to its modular architecture, affordability, and ease of deployment, the proposed solution can be adapted to different geographical regions, supporting proactive disaster preparedness and enhancing communitylevel safety.
  • Machine Learning and Internet of Things: Smart Decision- Making Applications
    R. Ramya, P. Kumar, K. Vanitha, C. Saranya
    Integration of Internet of Things and Machine Learning Design Models Architectures and Application, 2026
    The combination of machine learning (ML) and artificial intelligence (AI) with Internet of Things (IoT) systems has transformed numerous industries through intelligent decision-making and automation. This chapter introduces integration methods and applications of ML and AI in IoT environments. The convergence of ML and the IoT has revolutionized decision-making systems, but challenges such as data management, computational complexity, and privacy remain. Integration methods like edge computing and federated learning (FL) are being explored. This chapter presents the synergy between ML and IoT with a focus on how advanced algorithms enable real-time data processing, predictive analysis, and self-driving decisions in the IoT ecosystem. The chapter also discusses the increase in the robustness of IoT applications due to transfer learning and ensemble methods. With ML algorithms, IoT networks are transforming into self-learning, autonomous networks capable of making intelligent decisions under dynamic conditions, paving the way for a brighter and more connected future. This chapter explores the application of ML to IoT networks with a specific focus on supervised, unsupervised, deep, and reinforcement learning (RL) algorithms. It explains data preprocessing, feature engineering, time-series analysis, and optimization methods. The chapter discusses privacy, security, ethical issues, and bias in ML-based IoT decision-making.
  • Agro E-Commerce Platform with AI-Based Disease Outbreak Prediction
    K. Vanitha, K.B. Jayanthi, Harish V, Kavyaa S
    Proceedings of 2nd International Conference on Visual Analytics and Data Visualization Icvadv 2026, 2026
    Modern agriculture faces persistent challenges such as soil nutrient degradation, crop disease outbreaks, and inefficient utilization of agricultural resources, which collectively reduce productivity and increase operational costs. To address these challenges, this paper presents an IoT-enabled agro e-commerce platform integrated with an AI-driven disease outbreak prediction framework. The system continuously monitors critical soil parameters, including moisture, pH, and nutrient levels, through distributed IoT sensors, while enabling real-time assessment of crop health. A machine learning-based multi-modal prediction model analyzes plant images, environmental sensor data, and weather information to forecast potential disease occurrences at an early stage, facilitating timely preventive interventions. The platform further incorporates an intelligent chatbot interface that delivers context-aware recommendations for fertilizer application, crop management, and disease mitigation. To enhance practical usability, an integrated e-commerce module allows farmers to directly procure recommended seeds, fertilizers, and agroinputs. Experimental results demonstrate a disease prediction accuracy of 92% and a statistically significant crop yield improvement of approximately 15 %, along with improved efficiency in soil resource utilization. The proposed platform provides a secure, scalable, and data-driven solution that supports sustainable and resilient agricultural practices.
  • Boosting Agricultural Productivity in India through Machine Learning-Based Yield Predictions
    Vanitha. K, K.B. Jayanthi
    Proceedings 3rd International Conference on Artificial Intelligence and Machine Learning Applications Healthcare and Internet of Things Aimla 2025, 2025
    Agricultural productivity stands as a cornerstone for India's sustenance and economic advancement, given the nation's vast array of climatic regions and agricultural practices. The accurate anticipation of crop yields emerges as a pivotal factor in optimizing agricultural outputs, guaranteeing food security, and effectively managing resource allocation. However, traditional predictive models often grapple with the intricate and nonlinear dynamics that influence crop yields. In response to this challenge, this study pioneers an innovative approach by leveraging a suite of machine learning models, encompassing Linear Regression, Random Forest Regression, CatBoost Regression, Gradient Boosting Regression, K-Nearest Neighbors Regression, and Bagging Regression, to refine the predictive accuracy of agricultural crop yields across diverse Indian states. Through the assembly of a comprehensive data set comprising climatic variables, fertilizer, pesticides, crop types, and historical yield data from various regions, this research aims to enhance the understanding of the intricate interplay between these factors. Our results illuminate a significant enhancement in predictive accuracy across all models examined, with the Random Forest Regression emerging as the most adept in forecasting crop yields accurately. This outcome not only augments precision in yield forecasts but also provides invaluable insights into the relative significance of distinct factors influencing crop productivity. This study underscores the pivotal role of advanced data preprocessing techniques, such as Power BI, in unleashing the full potential of machine learning for agricultural applications. By harnessing these methodologies, stakeholders can make more informed decisions, fostering improved agricultural productivity and sustain ability amidst the diverse agricultural landscape of India
  • IoT-Enhanced Disease Prediction: A Machine Learning Approach to Climate-Health Interactions
    K. Vanitha, Priyanka G, Vijayakumar N, Vikram K
    Proceedings of 5th International Conference on Trends in Material Science and Inventive Materials Ictmim 2025, 2025
    The intersection of climate change and human health has increased the need for new solutions to predict and mitigate infectious diseases. This study explores an Internet of Things-enabled, machine learning-based framework to model and analyze the interactions between climate change and health outcomes. IoT sensors gather real-time environmental data, which is integrated with weather patterns and disease history. Advanced machine-learning techniques are then applied to detect and evaluate potential disease outbreaks in specific regions. This approach demonstrates the potential, accuracy, and potential of early warning, providing a valuable tool for governments to deploy health services promptly. This research advances understanding of the health-security equation and provides ideas and technologies to improve global health in the face of climate change.
  • Enhancing Predictive Accuracy for Agricultural Crop Yields in Indian States Using Power Transformation in Machine Learning Models
    Vanitha K, Surya G, Rakshatha Priya P, Rashmi M
    10th International Conference on Advanced Computing and Communication Systems Icaccs 2024, 2024
    Agricultural productivity is critical for the sustenance and economic growth of India, a country with diverse climatic regions and crop practices. Accurate prediction of crop yields is essential for optimizing agricultural outputs, ensuring food security, and planning resource allocation. Traditional predictive models often struggle with the nonlinear and complex nature of factors influencing crop yields. This study introduces an innovative approach by integrating power transformations, specifically the Yeo-Johnson transformation, within machine learning models to enhance the predictive accuracy of agricultural crop yields in various Indian states. We collected a comprehensive dataset comprising climatic variables, soil properties, crop types, and historical yield data across different Indian states. The Yeo-Johnson power transformation was applied to normalize the distribution of these features, addressing issues of skewness and heteroscedasticity, thereby making the data more suitable for machine learning algorithms. We evaluated several machine learning models, including Linear Regression, Random Forest, and Gradient Boosting, to establish a benchmark for comparison. Our findings demonstrate a significant improvement in predictive accuracy with the application of the Yeo-Johnson transformation across all models tested are shown in table 1. The Gradient Boosting model, post-transformation, exhibited the highest accuracy, underscoring the potential of combining power transformations with ensemble learning techniques for crop yield prediction. This approach not only aids in achieving greater precision in forecasts but also provides insights into the relative importance of various factors affecting crop yields. The study emphasizes the role of advanced data preprocessing techniques, such as power transformations, in unlocking the full potential of machine learning for agricultural applications. By enhancing the predictive accuracy of crop yield models, stakeholders can make more informed decisions, leading to improved agricultural productivity and sustainability in the diverse and challenging landscape of Indian agriculture.
  • Real Time Weather Prediction System using Ensemble Machine Learning
    D. Dhilipkumar, P. S. Yaswanth Bala, T. Yogeswaran, K. Vanitha
    Proceedings of the 2023 2nd International Conference on Augmented Intelligence and Sustainable Systems Icaiss 2023, 2023
    Weather predictions have a big influence on society and everyday life, from improvement to disaster preparedness. Accurate weather forecasting is one of the biggest challenges faced by the meteorological department. These forecasts are significant because they have an impact on day-to-day living as well as the economy of a state or even on a whole country. Weather forecasts are essential because they serve as the first line of defence against natural disasters, which might mean the difference between life and death. Also, they aid in lowering the anticipated mitigation measures that must be implemented after a natural catastrophe. In recent years, there has been a growing interest in using machine learning techniques for weather prediction. In this study, we investigate the effectiveness of four popular classification algorithms, namely k nearest neighbour, Gaussian naive bayes, Gradient Boosting Classifier, and Support vector classifier, for predicting weather conditions. We also explore the use of ensemble learning to combine the predictions of multiple models to improve accuracy. The evaluation of the models is based on precision, recall, and specificity parameters, which are commonly used in classification tasks. We use a dataset containing historical weather data to train and test the models, and compare their performance using ensemble learning. Our results show that all four models can achieve high accuracy in weather prediction, with KNN and hybrid ensemble achieving the best results in terms of precision and recall. We also demonstrate the effectiveness of ensemble learning, which can further improve the accuracy of the predictions. Overall, our study demonstrates the potential of machine learning techniques for weather prediction, and provides insights into the relative strengths and weaknesses of different classification algorithms for this task. The results may be useful for developing more accurate and reliable weather forecasting systems.
  • High speed low energy CAM design using reordered overlapping
    P Sowmya, K Vanitha
    Icetech 2015 2015 IEEE International Conference on Engineering and Technology, 2015
    In this paper, a reordered search mechanism is introduced for high-speed low-power content-addressable memories (CAMs). Only by searching a few bits of a search word the mismatches can be occured. So to reduce the power consumption, search word circuit is partitioned into two sections that are searched sequentially. Searching will be faster if the last few bits is compared other than the rest of the bits. Each word circuit has a local control signal which controls the circuit. This allows the circuits to be operated in the required phase which greatly reduces the cycle time.
  • Nonspecific-user hand gesture recognition by using MEMS accelerometer
    D Jayaraman, K Vanitha
    2014 International Conference on Information Communication and Embedded Systems Icices 2014, 2015
    Hand gestures are a form of nonverbal communication, which allow a person to communicate a range of thoughts and feelings with or without speech. Here MEMS 3 axis accelerometer to detect the input gestures as X, Y, Z direction. The axis is to detect the four types of gesture, which includes up, down, left, right. The hand motion of data collected will directly send to the microcontroller to run on a PC with the help of wireless module. The data will compressed by different users, gesture to extract from sign sequence and template matching. A single gesture has contain an 8 numbers code. This code reduces the hundreds of data values in single gesture and also to compare with the stored templates. In this paper three models has introduced and discussed about its accuracy. The sequence of gesture contain 85 experiments, finally the results achieves an overall accuracy of 96% based on the sign sequence generation and template matching, this each recognition contains the ranging from 94% to 100%.

RECENT SCHOLAR PUBLICATIONS

  • Deep learning for early detection of cerebral small vessel disease using self-supervised graph embeddings and retinal image analysis
    S Nandhini, K Vanitha
    Scientific Reports , 2026
    2026
  • Analyzing Bitcoin's Intraday Variance Using LSTM, GARCH and Hybrid Model
    K Vanitha, S Adarsh, M Ayyanar, B Abinash
    2025 International Conference on Electrical, Communication, and Computing … , 2025
    2025
  • XGBoost-Powered Predictive Modeling for Myalgic Encephalomyelitis/Chronic Fatigue Syndrome
    KVK Vanitha, U Preethi, R Suvetha, S Sruthi
    2025 6th International Conference on IoT Based Control Networks and … , 2025
    2025
  • Multi-task Convolution Neural Network towards Detection and Classification of Cardiovascular Disease on Leveraging Color Fundus Retina Images
    S Nandhini, K Vanitha
    2025 First International Conference of Advances in Engineering and Computing … , 2025
    2025
  • Robust IoT Botnet Detection via Residual Graph Attention Networks and Gradient Boosting: A Topology-Aware Hybrid Framework
    G Priyanka, K Vanitha
    2025 First International Conference of Advances in Engineering and Computing … , 2025
    2025
  • An Intelligent System for Mining-Related Air Quality and Hazard Identification Based on Machine Learning Techniques
    V Madhubashini, S Kaviya, K Deenu, S Sudhakshinadevi, S Sruthi, ...
    2025 10th International Conference on Communication and Electronics Systems … , 2025
    2025
  • IoT-Based Livestock Animal Tracking and Health Monitoring System
    S Mahendrakumar, S Sanjeeth, K Sarvesh, GR Shalini, SR Thiyaneshwar, ...
    2025 Second International Conference on Intelligent Technologies for … , 2025
    2025
  • Detection and Prevention of Distributed Denial of Service Attack to IoT servers using Recurrent Neural Network with Long Short Term Memory
    K Vanitha, M Abirami
    2025 5th International Conference on Soft Computing for Security … , 2025
    2025
  • An Intelligent Crime Risk Prediction Framework using Behavioral Analysis and Advanced Machine Learning
    K Vanitha
    2025 5th International Conference on Soft Computing for Security … , 2025
    2025
  • Optimized LSTM-based Machine Learning Framework for Real-Time Crime Hotspot Prediction
    K Vanitha
    2025 5th International Conference on Soft Computing for Security … , 2025
    2025
  • Clinical Evaluation of Detox Water as an Adjunctive Treatment in Hyperlipidemia
    K Vanitha, MC Baba, V Nivethika, S Prashanth
    International Journal of Research in AYUSH 1 (3-4), 116-120 , 2025
    2025
  • Role of Yoga and Naturopathic Intervention and Diet in the Management of Grade II Obesity–A Case Report
    K Vanitha, V Nivethika, S Prashanth
    DY Patil Journal of Health Sciences 13 (3), 206-210 , 2025
    2025
  • Graph Attention Network Towards Detection and Mitigation of Distributed Denial of Service Attack to IoT Servers
    M Abirami, K Vanitha
    2025 International Conference on Inventive Computation Technologies (ICICT … , 2025
    2025
  • IoT-Enhanced Disease Prediction: A Machine Learning Approach to Climate-Health Interactions
    K Vanitha, G Priyanka, N Vijayakumar, K Vikram
    2025 5th International Conference on Trends in Material Science and … , 2025
    2025
  • Enhanced tuberculosis detection using Vision Transformers and explainable AI with a Grad-CAM approach on chest X-rays
    K Vanitha, TR Mahesh, VV Kumar, S Guluwadi
    BMC Medical Imaging 25 (1), 96 , 2025
    2025
    Citations: 33
  • Dual Space DTR-Net Learning Based Heart Disease Prediction
    T Maragatham, K Vanitha, R Sivarajan
    2025 3rd International Conference on Intelligent Data Communication … , 2025
    2025
  • Cloud technology-enabled IoT milk quality assessment and billing system for dairy cooperatives
    S Mahendrakumar, G Karthikeyan, M Muthuvinayagam, G Vijayakumari, ...
    2025 International Conference on Multi-Agent Systems for Collaborative … , 2025
    2025
    Citations: 1
  • Survey for Agriculture Crop Yield Prediction and Recommendation Based on Deep Ensemble Learning Models
    TK Anjana, K Vanitha, RS Ravi
    2024 International Conference on Emerging Research in Computational Science … , 2024
    2024
  • An extensible CNN Model for lung cancer diagnosis using CT images
    K Vanitha, A Balajee, TR Mahesh, V Vivek, Y Kumar, DR Kasai
    2024 International Conference on Emerging Research in Computational Science … , 2024
    2024
    Citations: 1
  • Enhancing MRI-Based Brain Tumor Classification Accuracy through EfficientNetB3 and Advanced Image Data Augmentation Techniques
    K Vanitha, TR Mahesh, AA Thahaseen, B Manivannan, K Anitha, ...
    2024 International Conference on Emerging Research in Computational Science … , 2024
    2024
    Citations: 1

MOST CITED SCHOLAR PUBLICATIONS

  • Deep learning ensemble approach with explainable AI for lung and colon cancer classification using advanced hyperparameter tuning
    K Vanitha, MT R, SS Sree, S Guluwadi
    BMC Medical Informatics and Decision Making 24 (1), 222 , 2024
    2024
    Citations: 56
  • Attention-based feature fusion with external attention transformers for breast cancer histopathology analysis
    K Vanitha, A Manimaran, K Chokkanathan, K Anitha, TR Mahesh, ...
    IEEE Access 12, 126296-126312 , 2024
    2024
    Citations: 39
  • Enhanced tuberculosis detection using Vision Transformers and explainable AI with a Grad-CAM approach on chest X-rays
    K Vanitha, TR Mahesh, VV Kumar, S Guluwadi
    BMC Medical Imaging 25 (1), 96 , 2025
    2025
    Citations: 33
  • Guava leaf disease classification using support vector machine
    P Perumal, K Sellamuthu, K Vanitha, VK Manavalasundaram
    Turkish Journal of Computer and Mathematics Education 12 (7), 1177-1183 , 2021
    2021
    Citations: 33
  • Enhancing image-based diagnosis of gastrointestinal tract diseases through deep learning with EfficientNet and advanced data augmentation techniques
    AMJMD Zubair Rahman, R Mythili, K Chokkanathan, TR Mahesh, ...
    BMC Medical Imaging 24 (1), 306 , 2024
    2024
    Citations: 27
  • An efficient approach to identify selfish node in MANET
    MM Musthafa, K Vanitha, AMJMDZ RAHMAN, K Anitha
    2020 International Conference on Computer Communication and Informatics … , 2020
    2020
    Citations: 24
  • Ai-driven zero trust architecture: Enhancing cyber-security resilience
    K Chokkanathan, SM Karpagavalli, G Priyanka, K Vanitha, K Anitha, ...
    2024 8th International Conference on Computational System and Information … , 2024
    2024
    Citations: 21
  • Preventing malicious packet dropping nodes in MANET using IFHM based SAODV routing protocol
    K Vanitha, AMJ Zubair Rahaman
    Cluster Computing 22 (Suppl 6), 13453-13461 , 2019
    2019
    Citations: 18
  • Efficient semantic interrogation scheme over cryptographic data in cloud
    K Vanitha, CN Vanitha, MM Musthafa, S Malathy
    2020 International Conference on Inventive Computation Technologies (ICICT … , 2020
    2020
    Citations: 10
  • Number Plate Recognition Using OpenCV
    RR Chandrika, K Vanitha, A Thahaseen, V Neerugatti, M TR
    2024 International Conference on Emerging Smart Computing and Informatics … , 2024
    2024
    Citations: 8
  • Skin cancer prediction using machine learning
    R Suchithra, K Vanitha
    2022 International Interdisciplinary Humanitarian Conference for … , 2022
    2022
    Citations: 8
  • An Analysis of Issues in Security and Routing Protocol in MANET
    K Vanitha, AMJMZ Rahman, K Anitha
    International Journal of Engineering Research & Technology (IJERT) 3 (1 … , 2014
    2014
    Citations: 8
  • Intelligent systems for medical diagnostics with the detection of diabetic retinopathy at reduced entropy
    TR Mahesh, T Rajan, K Vanitha, HK Shashikala
    2023 International Conference on Network, Multimedia and Information … , 2023
    2023
    Citations: 7
  • Smart shopping trolley based on IoT with mobile application
    G Pradeepkumar, V Ramesh, A Karthika, A Karthikeyan, R Sacithraa, ...
    2023 International Conference on Sustainable Computing and Data … , 2023
    2023
    Citations: 7
  • Analysis of Cryptographic Techniques in Network Security
    K Vanitha, K Anitha, AMJMZ Rahaman, MM Musthafa
    Journal of Applied Science and Computations 5 (8), Page No:155-163 , 2018
    2018
    Citations: 7
  • Detecting spammers on social networks
    AJ Banu, NN Ahamed, B Manivannan, K Vanitha, MM Musthafa
    International Journal of Engineering and Computer Science 6 (2), 20240-20247 , 2017
    2017
    Citations: 7
  • Efficient Routing for Broadcasting in Mobile Ad Hoc Networks
    KV V.Sivakumar, A.M.J.Md.Zubair Rahman
    International Journal of Applied Engineering Research 9 (27), 9546-9552 , 2014
    2014
    Citations: 6
  • Ensemble techniques for the prediction of heart disease with reduced entropy
    TR Mahesh, MM Musthafa, AMJMZ Rahman, J Viswanath, K Vanitha
    2024 IEEE International Conference on Interdisciplinary Approaches in … , 2024
    2024
    Citations: 5
  • Impact of Selected Plant Growth Regulators on Rooting Response of Stem Cuttings of Psidium guajava L.
    M Kumar, V Sivakumar
    International Journal of Plant & Soil Science 35 (24), 320-325 , 2023
    2023
    Citations: 5
  • Optimizing deep learning based approach for brain tumor segmentation in magnetic resonance imaging (MRI) scans
    MDALM Hassan, MFH Fahim, R Jha, K Vanitha, NM Abrar, M TR
    2024 IEEE AITU: Digital Generation, 38-44 , 2024
    2024
    Citations: 4