Computer Engineering, Computer Vision and Pattern Recognition, Artificial Intelligence, Software
47
Scopus Publications
707
Scholar Citations
16
Scholar h-index
19
Scholar i10-index
Scopus Publications
Aural Eyes: A Transformer-Driven Multimodal Visual-to-Auditory Perception Framework Integrating YOLO26 and ViT-LSTM for Assistive Scene Understanding Nivethini S, Nivetha P P, D Deepa Proceedings of the 2026 International Conference on AI Driven Smart Systems and Ubiquitous Computing Icauc 2026, 2026 The physically challenged, that is, the blind people wrestle with the interpretation and communication with the environment considerably, thus real-time assistive technology is required. This paper proposes Aural Eyes which is a hybrid object detection and classification system that is used to transform visual information into auditory information. The model combines high-performance object localization through the use of the YOLO26 OpenCV-based pre-processing, object localization, and a Vision Transformer (ViT) with LSTM to classify the image at the fine phase. OpenCV allows increasing the quality of the image with noise removal, contrast enhancement and geometric deformation, whereas YOLO26 supports bounding boxes of high speed and accuracy in the absence of post-processing NMS. ViT-LSTM module is a module that captures global spatial features as well as the temporal dependency and finest object recognition especially in cluttered or dynamic environments. Experimental analysis shows that it has been determined that there are better-detected results, fewer false addicts and more adaptive to qualified datasets than standalone YOLO26. The modular arrangement provides real-time functionality and thus the system can be implemented in assistive devices that avail smart auditory feedback to a visually impaired user.
Intelligent Ridge Path Planning for Agriculture Robot Using Modified Q-Learning Algorithm A. Sivasangari, V. J. K. Kishor Sonti, J. Cruz Antony, E. Murali, D. Deepa, A. Happonen Computers Materials and Continua, 2026 In the past two decades, Precision Agriculture has received research attention since the development of robotics. Agricultural robotic equipment and drones, which can be operated by farmers, are appearing more frequently and being used to make the process of farming easier and more productive. This paper attempts to develop a modified Q-learning algorithm. A reinforcement learning algorithm called Q-learning has Q-values that are updated in order to find the best routes for the robotic devices to follow while avoiding any obstacles. Different types of terrain and other factors that influence the development of good routes for the robotic devices are included in the experiments performed. Through an extensive set of experiments done with different types of terrain the researchers found that the modified Q-learning algorithm converges to the optimal path significantly quicker than the current benchmark Deep Q-Network (DQN) algorithms and that the average distance that the modified Q-learning algorithm travels to get to its destination over different terrane types was 28.7% shorter than the average distance traveled using the standard DQNs. The researchers also found that the modified Q-learning algorithm has been able to successfully avoid obstacles on 99.5% of all occasions tested. The shortest route to the destination is expected to take less time, and it demonstrates the benefit of using a robotic device that has the ability to detect and avoid obstacles in order to be effective on more difficult types of terrain.
Data Transformation and Predictive Analytics of Cardiovascular Disease Using Machine and Ensemble Learning Techniques , J. Cruz Antony, E. Murali, D. Deepa, R. Vignesh, S. Hemalatha, Umme Fahad International Journal of Intelligent Systems and Applications, 2025 About one person dies every minute from cardiovascular disease; consequently, it has almost surpassed war as the largest cause of death in the twenty-first century. In cardiology, early and accurate diagnosis of heart illness is a cornerstone of effective healthcare. Predictive analytics, which involves machine-learning algorithms, can be a great option for contributing towards the early detection of cardiovascular disease. This study evaluates the data preprocessing techniques involved in building machine learning models to predict cardiovascular disease and identify the features contributing to the cardio attack. A novel data transformation technique named the superlative boundary binning method was proposed to enhance machine learning and ensemble learning classification models for predicting cardiac illness based on independent physiological feature parameters. The results revealed that the ensemble learning classifier AdaBoost using the superlative boundary binning method has performed well with a classification accuracy of 93% when compared with the other data transformation and machine learning classifier models.
Generative AI-Enhanced Deep Learning for Glaucoma: A Framework for Early Detection and Progression Forecasting Deepa D, R Pugalenthi Proceedings of 5th International Conference on Evolutionary Computing and Mobile Sustainable Networks Icecmsn 2025, 2025 Glaucoma is still a leading cause of permanent blindness, and artificial intelligence (AI) has the potential to be used to detect the disease at an early stage. Nevertheless, the current constraints of ophthalmic datasets in the development of deep learning (DL) models are devastating because they are small, unheterogeneous, and cross-sectional in nature. To address these data-centric bottlenecks, this paper suggests a new framework to be implemented with the help of generative AI. We present a procedure by which large-scale, high-fidelity syn- thetic data of color fundus photographs and optical coherence tomography (OCT) scans might be produced using Generative Adversarial Networks (GANs). This is not only a way of overcoming data scarcity and bias in representation, but also allows the synthesis of longitudinal data to model the progression of a disease. Such enhanced datasets will be trained on the models of advanced DLs: a Vision Transformer (ViT) to detect the early signs and a spatiotemporal Convolutional Long Short-Term Memory (ConvLSTM) network to predict the progression. Such models should perform much better than models trained using real data alone especially with respect to their extrapolation to a wide range of real-world clinical environments. This framework will generate credible, precise, and fair AI tools by incorporating explainable AI (XAI) methods, which will lead to customized and predictive glaucoma care.
Event Causality Insights Through AI Kantu Jahnavi, Venkat Saladi, D. Deepa Proceedings of 3rd International Conference on Augmented Intelligence and Sustainable Systems Icaiss 2025, 2025
Image Super-Resolution Using Auto Encoders K. Sandhya Rani, Pancheti Bhavya, R. Vignesh, E. Murali, D. Deepa, J. Cruz Antony Proceedings of 8th International Conference on Trends in Electronics and Informatics Icoei 2025, 2025
Authentication of Digital Document using Blockchain D Deepa, G.M. Karpura Dheepan, R Yogitha, K Veena, M Selvi, K Rahul Srithar, A S Abdul Rahman 2023 2nd International Conference on Advances in Computational Intelligence and Communication Icacic 2023, 2023
Gene Expression Analysis on Cancer Dataset R. Vignesh, D. Deepa, Suja Cherukullapurath Mana, B.Keerthi Samhitha, Anandhi. T Proceedings of the 5th International Conference on Trends in Electronics and Informatics Icoei 2021, 2021
IoT and Machine Learning Based Smart Grid System A. Sivasangari, D. Deepa, Lakshmanan L, Jesudoss A, Vignesh R 2021 5th International Conference on Computer Communication and Signal Processing Icccsp 2021, 2021
Eyeball based Cursor Movement Control A Sivasangari., D Deepa., T Anandhi., Anitha Ponraj, M.S Roobini. Proceedings of the 2020 IEEE International Conference on Communication and Signal Processing Iccsp 2020, 2020
Dynamic enforcement of causal consistency for a geo-replicated cloud storage system International Journal of Electrical Engineering and Technology, 2020
Visualizing road damage by monitoring system in cloud Deepa D., R. Vignesh, Sivasangari A, Suja Cherukullapurath Mana, B. Keerthi Samhitha, Jithina Jose International Journal of Electrical Engineering and Technology, 2020
Gridlock surveillance and management system M. V. Ishwarya, D. Deepa, S. Hemalatha, A. Venkata Sai Nynesh, A. Prudhvi Tej Journal of Computational and Theoretical Nanoscience, 2019
RECENT SCHOLAR PUBLICATIONS
Advanced Microplastic Identification in Marine Environments via Hybrid Deep Learning D Deepa, SS Nivedha, AR Nivetha 2026 International Conference on Electronics and Renewable Systems (ICEARS … , 2026 2026
Predictive Analytics for Enhancing Student Learning Outcomes in Blended Learning Environments: A Systematic Review M Mehfooza, IH Basha, SB Elghali, T Padmavathy, D Deepa SN Computer Science 7 (1), 98 , 2026 2026
Intelligent Ridge Path Planning for Agriculture Robot Using Modified Q-Learning Algorithm A Sivasangari, VJKK Sonti, JC Antony, E Murali, D Deepa, A Happonen CMC-COMPUTERS MATERIALS & CONTINUA 87 (3) , 2026 2026
Future Directions for Surgical Robots in Smart Hospitals A Sivasangari, VJKK Sonti, JC Antony, E Murali, D Deepa Surgical Robots in Smart Hospitals, 599-625 , 2025 2025
Road accident spot prediction with multiple deep learning P Siddhartha, VB Pasasla, D Deepa AIP Conference Proceedings 3257 (1), 020132 , 2025 2025
Innovative certificate and signature verification system for authentication and fraud detection A Sivasangari, S Helen, D Deepa, R Vignesh, P Indrareddy, JC Hasini AIP Conference Proceedings 3257 (1), 020044 , 2025 2025
Python-powered cloud security hub: Collaborative threat intel sharing D Deepa, A Sivasangari, B Shivakumar, RES Nath, R Vignesh, E Murali AIP Conference Proceedings 3257 (1), 020104 , 2025 2025 Citations: 2
Blockchain hashing prototype of blockchain mining and hashing with the help of secured hashing algorithm of SHA256 bits C Geetha, S Bhuvaneshwaran, S Don Inigo, D Deepa AIP Conference Proceedings 3257 (1), 020092 , 2025 2025
Personal identity security system using blockchain R Lalitha, T Sai Nath, VH Sai, D Deepa AIP Conference Proceedings 3257 (1), 020093 , 2025 2025
Cardio sentinel prognosticator using ML AA Prakash, S Hemalatha, D Deepa, Ravee, Rahul AIP Conference Proceedings 3257 (1), 020024 , 2025 2025
Event Causality Insights Through AI K Jahnavi, V Saladi, D Deepa 2025 Third International Conference on Augmented Intelligence and … , 2025 2025
Image Super-Resolution Using Auto Encoders KS Rani, P Bhavya, R Vignesh, E Murali, D Deepa, JC Antony 2025 8th International Conference on Trends in Electronics and Informatics … , 2025 2025
Data Transformation and Predictive Analytics of Cardiovascular Disease Using Machine and Ensemble Learning Techniques JC Antony, E Murali, D Deepa, R Vignesh, S Hemalatha, U Fahad INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS AND APPLICATIONS 17 (1), 88-97 , 2025 2025
A novel trust assessment system for online social networking environment using learning assisted classification model S Nithya, D Deepa, VD Babu, H Fawareh, RD Kayalvizhy 2024 International Conference on Innovative Computing, Intelligent … , 2024 2024 Citations: 22
Deep Learning Based Automatic Detection of Bike Riders with No Helmet A Sivasangari, T Sasikala, D Deepa, S Gowri, N Rani 2024 15th International Conference on Computing Communication and Networking … , 2024 2024 Citations: 1
PRS-UBR: Product Recommender System Using Utility-Based Recommendation J Cruz Antony, I Thanzia Raksheen, PS Raj, D Deepa, R Vignesh International Conference on Innovations and Advances in Cognitive Systems, 52-62 , 2024 2024
Personal identification using human ear recognition system R Vignesh, S Sivasangari, D Deepa, E Murali, S Hemalatha, N Priyanka AIP Conference Proceedings 2850 (1), 030012 , 2024 2024
Mobile veggie detector: real-time detection of vegetables through mobile application and deep learning TV Shreenithi, V Shreemathi 2024 10th International Conference on Advanced Computing and Communication … , 2024 2024 Citations: 5
Ballot Casting System using Blockchain Technology KM Reddy, KK Sai, D Deepa 2024 3rd International Conference on Sentiment Analysis and Deep Learning … , 2024 2024
ESSR-GAN: Enhanced super and semi supervised remora resolution based generative adversarial learning framework model for smartphone based road damage detection D Deepa, A Sivasangari multimedia Tools and Applications 83 (2), 5099-5129 , 2024 2024 Citations: 24
MOST CITED SCHOLAR PUBLICATIONS
An effective detection and classification of road damages using hybrid deep learning framework D Deepa, A Sivasangari Multimedia Tools and Applications 82 (12), 18151-18184 , 2023 2023 Citations: 83
Integrated security framework for healthcare using blockchain and fog computing A Sivasangari, VJKK Sonti, P Ajitha, D Deepa, R Vignesh 2022 2nd international conference on power electronics & IoT applications in … , 2022 2022 Citations: 52
Big data analytics for 5G-enabled IoT healthcare A Sivasangari, L Lakshmanan, P Ajitha, D Deepa, J Jabez Blockchain for 5G-Enabled IoT: The New Wave for Industrial Automation, 261-275 , 2021 2021 Citations: 49
EEG-based computer-aided diagnosis of autism spectrum disorder A Sivasangari, K Sonti, GP Kanmani, D Deepa Cognitive Systems and Signal Processing in Image Processing, 277-292 , 2022 2022 Citations: 47
Blockchain for 5G-Enabled IoT A Sivasangari, L Lakshmanan, P Ajitha, D Deepa, J Jabez, S Tanwar Springer, Cham. , 2021 2021 Citations: 36
Pothole detection using roboflow convolutional neural networks D Deepa, A Sivasangari, R Roonwal, R Nayan 2023 7th International Conference on Intelligent Computing and Control … , 2023 2023 Citations: 35
Security and privacy in wireless body sensor networks using lightweight cryptography scheme A Sivasangari, A Ananthi, D Deepa, G Rajesh, XM Raajini Security and privacy issues in IoT devices and sensor networks, 43-59 , 2021 2021 Citations: 35
Eyeball based cursor movement control A Sivasangari, D Deepa, T Anandhi, A Ponraj, MS Roobini 2020 International Conference on Communication and Signal Processing (ICCSP … , 2020 2020 Citations: 30
Cloud-computed solar tracking system G Govinda Rajulu, M Jamuna Rani, D Deepa, U Mamodiya, ... Computer Communication, Networking and IoT: Proceedings of 5th ICICC 2021 … , 2022 2022 Citations: 28
Operating parameters prediction of liquefied petroleum gas refrigerator using simulated annealing algorithm B Sampath, M Pandian, D Deepa, R Subbiah AIP Conference Proceedings 2460 (1), 070003 , 2022 2022 Citations: 28
Prediction probability of getting an admission into a university using machine learning A Sivasangari, V Shivani, Y Bindhu, D Deepa, R Vignesh 2021 5th international conference on computing methodologies and … , 2021 2021 Citations: 27
ESSR-GAN: Enhanced super and semi supervised remora resolution based generative adversarial learning framework model for smartphone based road damage detection D Deepa, A Sivasangari multimedia Tools and Applications 83 (2), 5099-5129 , 2024 2024 Citations: 24
A novel trust assessment system for online social networking environment using learning assisted classification model S Nithya, D Deepa, VD Babu, H Fawareh, RD Kayalvizhy 2024 International Conference on Innovative Computing, Intelligent … , 2024 2024 Citations: 22
Dynamic enforcement of causal consistency for a geo-replicated cloud storage system R Vignesh, D Deepa, P Anitha, S Divya, S Roobini International Journal of Electrical Engineering and Technology 11 (3) , 2020 2020 Citations: 22
Visualizing road damage by monitoring system in cloud D Deepa, R Vignesh, A Sivasangari, SC Mana, BK Samhitha, J Jose International Journal of Electrical Engineering and Technology 11 (4), 191-203 , 2020 2020 Citations: 22
Prediction of lung cancer using convolutional neural network (CNN) BK Samhitha, SC Mana, J Jose, R Vignesh, D Deepa International Journal 9 (3) , 2020 2020 Citations: 21
Gridlock surveillance and management system MV Ishwarya, D Deepa, S Hemalatha, A Venkata Sai Nynesh, ... Journal of Computational and Theoretical Nanoscience 16 (8), 3281-3284 , 2019 2019 Citations: 15
Segmentation of shopping mall customers using clustering D Deepa, A Sivasangari, R Vignesh, N Priyanka, J Cruz Antony, ... Data Intelligence and Cognitive Informatics: Proceedings of ICDICI 2022, 619-629 , 2022 2022 Citations: 13
Car accident detection and notification system using smartphone MS Roobini, S Mulakalapally, N Mungamuri, M Lakshmi, A Ponraj, ... Journal of Computational and Theoretical Nanoscience 17 (8), 3389-3393 , 2020 2020 Citations: 12
A Design Framework for Smart Ration Shop Using Blockchain and IoT Technologies. D Malathi, V Ponnusamy, S Saravanan, D Deepa, TA Ahanger Intelligent Automation & Soft Computing 32 (1) , 2022 2022 Citations: 9