Electrical and Electronic Engineering, Engineering, Engineering
7
Scopus Publications
10
Scholar Citations
2
Scholar h-index
Scopus Publications
Deep Learning-Based Predictive Vehicle Fault Detection Using Simulated Multi-Sensor Timeseries Data A.A. Anumol, P. Vijayalakshmi, A. Kingsly Jabakumar, T. Arun, S. Prabhavathy, V. Nithya Proceedings of 2nd International Conference on Visual Analytics and Data Visualization Icvadv 2026, 2026 Conventional vehicle health monitoring still depends on hardware-heavy threshold rules that react only after a fault appears. This work presents a software-only predictive maintenance pipeline that combines convolutional neural networks, bidirectional LSTMs and an attention layer to detect and classify vehicle faults from simulated multi-sensor time-series data. The system runs entirely in Google Colab and reaches <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 4 - 9 6 \%}$</tex> classification accuracy, while its remaining useful life head attains a mean absolute error of about <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\pm \mathbf{4. 5}$</tex> cycles. Six deep learning models are trained and compared: three baselines (Bi-LSTM, GRU, 1D-CNN) and three hybrid variants (CNN-LSTM, CNN-BiLSTM, CNN-BiLSTM-Attention). The hybrid CNN-BiLSTM-Attention model improves accuracy over the best baseline by roughly <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$5-6 \%$</tex> and also exposes interpretable attention maps. All models operate on synthetic temperature, vibration and current signals generated for four operating states: Normal, Overheating, Mechanical Fault and Electrical Fault. The best model offers real-time inference of around 50 ms per sample with a footprint of about 1.5 MB, which makes it practical for Industry 4.0 deployments and easy to use in teaching and research without extra hardware.
Comprehensive Review of AI-Powered Waste Sorting System for Sanitation Workers Shiva Reshma R, Pradeep R, Prabhavathy S, Nithya V 2025 IEEE 1st International Conference on Innovations in Engineering and Next Generation Technologies for Sustainability Icinvents 2025, 2025 The rising worldwide garbage epidemic, fueled by urbanization and industrialization, presents substantial environmental challenges, affecting air, water, and soil quality. This pressing situation necessitates quick, inventive answers. Recycling has developed as an important approach, especially when combined with automated sorting systems. Numerous studies have focused on designing automated systems to address environmental concerns, in accordance with circular economy concepts. Recent advances in artificial intelligence (AI) have resulted in the development of a variety of solutions targeted at increasing accuracy and efficiency. Researchers have investigated artificial intelligence approaches such as machine learning, deep learning, and ensemble methods to improve trash classification systems. This paper investigates AI-based garbage classification systems and demonstrates their applicability in real-world scenarios. Robotic arms powered by artificial intelligence and linked with microcontrollers such as Raspberry Pi, ESP32, and Arduino automate the recognition and sorting of elements such as plastic, metal, paper, and biodegradable materials, revolutionizing waste segregation. These systems increase recycling efficiency and reduce contamination rates by attaining high accuracy in real-time object detection using deep learning algorithms like YOLOv6 and YOLOv8.
Comparative Study of Breast Cancer Detection Using Histopathology Images Shiva Reshma R, Pradeep R, Prabhavathy S, Tharanisrisakthi B T 10th International Conference on Advanced Computing and Communication Systems Icaccs 2024, 2024 Breast cancer continues to be a major health issue, necessitating efficient and accurate diagnostic methods for early detection. Deep learning approaches have recently showed significant potential in improving the accuracy and efficiency of breast cancer detection, notably in histopathology image processing. This review provides a thorough analysis of existing research on deep and machine-learning applications in breast cancer detection, highlighting the diverse diagnostic setups utilized in various studies. Deep learning is particularly promising in the detection of breast cancer because of its ability to provide accurate, automated, and early detection of potential malignancies, ultimately contributing to better patient outcomes and more effective healthcare practices as a result. The paper explores the range of techniques employed, with a specific focus on different classifiers that works on supervised learning.
Diabetic Retinopathy Classification using Hybrid Optimized U-Net and Improved ResNet-18 with MISH Activation S. Nithyapriya, S. Yuvalatha, S. Prabhavathy, T. Arun, S.K Muthusundar, Antonidoss A 2024 International Conference on Smart Technologies for Sustainable Development Goals Icstsdg 2024, 2024 Diabetic Retinopathy (DR) refers to damage to the retina caused by diabetes, which can cause visual impairments or potentially lead to blindness. The process of manually identifying diabetic retinopathy is slow and can easily be affected by human mistakes because of the eye's complex anatomy. This paper aims to determine the optimal model for accurately staging diabetic retinopathy (DR) across five DR categories. The proposed system involves image pre-processing, segmentation and classification. A well-structured preprocessing framework was implemented, integrating Median Filtering technique to decrease noise and Gamma Correction for improved image quality. Data augmentation is performed through methods like flipping, cropping rotating, and translation of fundus images. In this study, a hybrid optimization strategy is proposed by combining the Adam optimizer with Simulated Annealing (SA) and Cosine Annealing for training a U-Net model for diabetic retinopathy (DR) lesion segmentation. Canny Edge Detection is employed to discover edges correctly within the image. For DR categorisation in this work, enhanced Resnet 18 combined with MISH activation function is used. The suggested model makes use of residual blocks in conjunction with identity and convolutional blocks. Experiments on the APTOS dataset show that the proposed model outperforms state-of-the-art techniques. Accuracy, precision, recall, and F1 score are all improved by the suggested Resnet18 model, which receives scores of 99.45%, 98.64%, 98.63%, and 98.63%, respectively.
A Hybrid Model to Predict the Breast Cancer using Stacking and Bagging Model S. Yuvalatha, S. Nithyapriya, S. Prabhavathy, R. Priyadharshini, S. Savitha, S. Kayathri 3rd IEEE International Conference on Mobile Networks and Wireless Communications Icmnwc 2023, 2023 Breast cancer is a malignant tumor that develops in the cells of the breast tissue. Breast cancer is one of the major causes of death for women globally. In the examination of medical data, breast cancer prediction is a difficult task. To make decisions and accurately distinguish between benign and malignant tumors, physicians and pathologists need certain automated technologies. In this paper, hybrid ensemble technique (Bagging and Stacking) is used to predict the breast tumors as benign and malignant tumors. In the proposed work, the subset of data is created from the initial Wisconsin (Diagnostic) Data Set by bootstrapping technique. Each bootstrap dataset is used to train the weak learner. The weak learners are K-Nearest Neighbors (KNN) Random Forest (RF), Decision Tree (DT) and Support Vector Machine (SVM). The Logistic Regression (LR) is used as the Meta Learner. The Meta Learner uses the predictions of weak learners as its training data. The proposed hybrid ensemble model obtains an accuracy 98.7%, Precision 98.83%, Recall 98.54%, F1 Score 98.68% and 0.012% error
IoT Based Smart Monitoring and Controlling System for Gas Leakage in Industries Muralidharan V, Prabhavathy S, Pavithra L, Nithya V Ssrg International Journal of Electrical and Electronics Engineering, 2022 The main objective of the work is to design a microcontroller-based toxic gas detecting and alerting system. The ultrasonic sensor is used to determine if gas is present in the ambient or not by analyzing the acoustic waves. The MQ-135 gas sensor is used to identify the leakage of gas. The IoT part of the system deals with the connectivity of the entire system to the Blynk platform via the Wi-Fi module of the NodeMCU microcontroller.<br /> The emergency actions are automated, and detection is predicted using two preset threshold values of gas pressure in case of gas leakage. The system enables monitoring and alerting gas leakages in industries before the accident could occur, leading to a faster response time in the event of a leakage condition. The availability of the Blynk cloud platform makes it easier to collect regular data and generate useful insights from it. The results from the accumulated data of the ultrasonic sensor let us automate security actions before the conditions go out of control.<br /> An IoT - based smart control and monitoring system for industrial gas leakage problems is proposed with the ability to monitor the pipelines, store the pressure levels and generate insights based on recorded data. The key idea of the system is to generate notifications and alarms based on the preset threshold value to show an increase in safety. The IoT part of the system deals with the connectivity of the entire system to the Blynk platform via the Wi-Fi module of the NodeMCU microcontroller. The online platform provides a range of tasks that can be done. From data visualization to automation, Blynk provides multiple facilities to carry out our essential operations in the project. As a part of our system, the online platform helps us to read, record, and analyze the data received from the microcontroller unit. The e-mail notification is also initiated through this online mobile application.
Automated Plant Leaf Classification using Ensemble Transfer Learning in CNN model S. Yuvalatha, J. Keerthika, S. Prabhavathy, M. Banupriya, R. Priyadharshini 2022 IEEE North Karnataka Subsection Flagship International Conference Nkcon 2022, 2022 In the agriculture production, one of the biggest challenges is detecting the plant leaf disease in their early stages which significantly affects the farmer's earnings. In this paper various transfer learning CNN model of mobile NetV2, ResNet, InceptionV3, VGG16, Densenet are used to categories the potato leaf disease into healthy, Early blight, Late blight. Data fragmentation strategies are applied to expand the number of images for the collected dataset to train the model. The mobileNetV2 achieve the accuracy of 86.8%. In this work the ensemble transfer learning for CNN model is proposed to identify the leaf disease. For the classification, majority voting ensemble techniques are used and obtained the accuracy of 94.8%.
RECENT SCHOLAR PUBLICATIONS
Deep Learning-Based Predictive Vehicle Fault Detection Using Simulated Multi-Sensor Timeseries Data AA Anumol, P Vijayalakshmi, AK Jabakumar, T Arun, S Prabhavathy, ... 2026 International Conference on Visual Analytics and Data Visualization … , 2026 2026.0
Comprehensive Review of AI-Powered Waste Sorting System for Sanitation Workers R Pradeep, S Prabhavathy, V Nithya 2025 IEEE First International Conference on Innovations in Engineering and … , 2025 2025.0
Diabetic Retinopathy Classification Using Hybrid Optimized U-Net and Improved ResNet-18 with MISH Activation S Nithyapriya, S Yuvalatha, S Prabhavathy, T Arun, SK Muthusundar 2024 International Conference on Smart Technologies for Sustainable … , 2024 2024.0
Comparative Study of Breast Cancer Detection Using Histopathology Images R Pradeep, S Prabhavathy, BT Tharanisrisakthi 2024 10th International Conference on Advanced Computing and Communication … , 2024 2024.0 Citations: 1
A hybrid model to predict the breast cancer using stacking and bagging model S Yuvalatha, S Nithyapriya, S Prabhavathy, R Priyadharshini, S Savitha, ... 2023 3rd International Conference on Mobile Networks and Wireless … , 2023 2023.0 Citations: 1
INVESTIGATIONS ON DNA-BASED NANOROBOTS IN CANCER TREATMENT VN S.Prabhavathy L.Pavithra, V.Muralidharan GIS SCIENCE JOURNAL 9 (ISSUE 12, 2022), 787-792 , 2022 2022.0
Automated Plant Leaf Classification using Ensemble Transfer Learning in CNN model S Yuvalatha, J Keerthika, S Prabhavathy, M Banupriya, R Priyadharshini 2022 IEEE North Karnataka Subsection Flagship International Conference … , 2022 2022.0 Citations: 5
IoT Based Smart Monitoring and Controlling System for Gas Leakage in Industries PL Nithya V Muralidharan V , Prabhavathy S SSRG International Journal of Electrical and Electronics Engineering 9 (9 … , 2022 2022.0 Citations: 3
THREE DIMENSIONAL PARITY FORTCAM BASED FPGA FOR ERROR DETECTION AND CORRECTION MVV Mrs.V.Nithya Ms.L.Pavithra, Mrs.S.Prabhavathy Journal of Emerging Technologies and Innovative Research 8 (8), 299-303 , 2021 2021.0
MSIC Vector Used in BIST for Power Reduction by Selective Trigger scan Architecture SPR Hemalatha International journal of Hardware and software research in Engineering 2 (3 … , 2014 2014.0
Machine learning Approach for brain tumour Detection MLP 6Mrs. S. Prabhavathy 1Dr. J. Vimala Ithayan, 2Mrs. R. Sujitha, 3Dr. S ... Journal of Survey in Fisheries Sciences 10 (4), 793-802 , 0
MOST CITED SCHOLAR PUBLICATIONS
Automated Plant Leaf Classification using Ensemble Transfer Learning in CNN model S Yuvalatha, J Keerthika, S Prabhavathy, M Banupriya, R Priyadharshini 2022 IEEE North Karnataka Subsection Flagship International Conference … , 2022 2022.0 Citations: 5
IoT Based Smart Monitoring and Controlling System for Gas Leakage in Industries PL Nithya V Muralidharan V , Prabhavathy S SSRG International Journal of Electrical and Electronics Engineering 9 (9 … , 2022 2022.0 Citations: 3
Comparative Study of Breast Cancer Detection Using Histopathology Images R Pradeep, S Prabhavathy, BT Tharanisrisakthi 2024 10th International Conference on Advanced Computing and Communication … , 2024 2024.0 Citations: 1
A hybrid model to predict the breast cancer using stacking and bagging model S Yuvalatha, S Nithyapriya, S Prabhavathy, R Priyadharshini, S Savitha, ... 2023 3rd International Conference on Mobile Networks and Wireless … , 2023 2023.0 Citations: 1
Deep Learning-Based Predictive Vehicle Fault Detection Using Simulated Multi-Sensor Timeseries Data AA Anumol, P Vijayalakshmi, AK Jabakumar, T Arun, S Prabhavathy, ... 2026 International Conference on Visual Analytics and Data Visualization … , 2026 2026.0
Comprehensive Review of AI-Powered Waste Sorting System for Sanitation Workers R Pradeep, S Prabhavathy, V Nithya 2025 IEEE First International Conference on Innovations in Engineering and … , 2025 2025.0
Diabetic Retinopathy Classification Using Hybrid Optimized U-Net and Improved ResNet-18 with MISH Activation S Nithyapriya, S Yuvalatha, S Prabhavathy, T Arun, SK Muthusundar 2024 International Conference on Smart Technologies for Sustainable … , 2024 2024.0
INVESTIGATIONS ON DNA-BASED NANOROBOTS IN CANCER TREATMENT VN S.Prabhavathy L.Pavithra, V.Muralidharan GIS SCIENCE JOURNAL 9 (ISSUE 12, 2022), 787-792 , 2022 2022.0
THREE DIMENSIONAL PARITY FORTCAM BASED FPGA FOR ERROR DETECTION AND CORRECTION MVV Mrs.V.Nithya Ms.L.Pavithra, Mrs.S.Prabhavathy Journal of Emerging Technologies and Innovative Research 8 (8), 299-303 , 2021 2021.0
MSIC Vector Used in BIST for Power Reduction by Selective Trigger scan Architecture SPR Hemalatha International journal of Hardware and software research in Engineering 2 (3 … , 2014 2014.0
Machine learning Approach for brain tumour Detection MLP 6Mrs. S. Prabhavathy 1Dr. J. Vimala Ithayan, 2Mrs. R. Sujitha, 3Dr. S ... Journal of Survey in Fisheries Sciences 10 (4), 793-802 , 0
RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)
1. Name:” SMART FRIDGE WITH ARTIFICIAL INTELLIGENCE DRIVEN BREAKFAST, LUNCH AND DINNER PREFERENCES” 10.05.2024
Date of filing of Application: 30/04/2024
Application A
Publication Date: 10/05/2024
2. Name: ARTIFICIAL INTELLIGENCE BASED AUTOMATED BUS FARE COLLECTION SYSTEM
Date of filing of Application: 30/04/2024
Application No. 202441088462 A
Publication Date: 22/11/2024
3. Name: MACHINE LEARNING BASED FORECASTING OF CROP YIELD USING CLIMATE AND REMOTE SENSING DATA
Date of filing of Application: 30/05/2025
Application No. 202521043062 A
Publication Date: 04/07/2025
4. Name : FPGA-BASED FUZZY PID CONTROLLER FOR INTELLIGENT VEHICLE CRUISING AND COLLISION AVOIDANCE IN INTERNET OF VEHICLES (IOV)
Date of filing of Application: 08/05/2026
Application No. 202641058520 A
Publication Date: 22/05/2026
