Dr.G.Premalatha

@srmist.edu.in

Assistant Professor, Engineering & Technology
SRM Institute of Science and Technology

Dr.G.Premalatha


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

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Vision and Pattern Recognition, Computer Science, Computer Science Applications
23

Scopus Publications

85

Scholar Citations

5

Scholar h-index

2

Scholar i10-index

Scopus Publications

  • A Sophisticated Onscreen Smart Framework for Predicting Diabetes in Remote Healthcare
    Koteeswaran Seerangan, Premalatha Gunasekaran, Nithya Rekha Sivakumar, Resmi Ravi Nair, Malarvizhi Nandagopal, Neeba Eralil Abi, Nalini Manogaran
    Diagnostics, 2026
    Background/Objectives: Diabetes is one of the most familiar and common diseases among people currently, and is a type of metabolic disease that is caused due to high levels of sugar in the blood for longer periods of time. If the disease is predicted at an earlier stage, the severity and risks associated with diabetes are significantly reduced, which helps to save the lifespan of people. In earlier investigations, various kinds of automated models based on artificial intelligence (AI) were developed for this purpose. However, key issues still revolve around the lack of robustness, dependability, and precise prediction. The motivation behind the proposed study is to design and develop an automated tool for the diagnosis of chronic disease with the use of novel AI methodology. Methods: For this purpose, a new detection framework is introduced, known as the Brass Optimized Learning-Based Diabetes Prediction (BOLD) model for remote healthcare applications. By using this kind of optimization-integrated deep learning technique, the overall performance and efficiency of the diabetes detection system are maximized. This framework preprocesses the input diabetes dataset before performing the data splitting, normalization, and cleaning activities. Next, the best attributes for improving the prognostic performance of the classifier are chosen using the Brassy Pelican Optimization (BPO) procedure. The Hunting Optimized Recurrent Neural Network—Long Short-Term Memory (RNN-LSTM) method is used to categorize the people into those who are diabetic and those who are not based on the chosen attributes. The approach employs a Deer Hunting Optimization (DHO) method to choose the hyperparameters needed to make an informed choice. A variety of parameters have been employed to confirm the results, which are evaluated for performance verification using the PIDD, Indonesia diabetic database, and kidney disease dataset. Results: The BOLD framework is successful to the extent that it has been able to achieve several metrics of comparably good results, such as an RMSE value of 0.015, a Cohen’s Kappa measure of 0.99, a precision of 0.991, a recall of 0.99, an accuracy equal to 0.996, and an AUC equal to 0.99. Conclusions: It is also remarkable that a very short time of 0.8 s was enough for it to deliver this kind of performance, making it a neat combination of both time and power efficiency.
  • DeepSight: AI Driven Navigation Assistance for the Visually Impaired
    Dominic Thomas, Anubhav Rawat, Ayushman Das, Swastika Kangabam, G. Premalatha
    Proceedings of the 12th International Conference on Biosignals Images and Instrumentation Icbsii 2026, 2026
    Independent mobility remains challenging for visually impaired individuals, especially in dynamic environments where conventional aids lack semantic understanding. Deep Sight is a lightweight, monocular-vision-based navigation system that combines YOLOv8 object detection with Lite-Mono depth estimation to provide real-time obstacle awareness from a single RGB camera. The fused outputs enable metric distance estimation using calibrated intrinsics and ground-plane geometry. A wearable Raspberry Pi Zero 2 W streams frames to a remote GPU-based server, achieving up to 20 FPS. These spatial audio cues of distance and direction provide intuitive feedback for non-visual navigation. Extensive experiments in both indoor and outdoor environments ensure low latency, reliable detection, and practical usability, toward an accessible, low-cost assistive solution.
  • Defect Detection and Classification on Robot-Painted Pattern Surfaces Using Machine Learning Techniques
    Nakul Limbani, Shiv Rastogi, Premalatha G, S. Prabhu, G. Vadivu
    IFIP Advances in Information and Communication Technology, 2026
  • The Role of AI in Consumer Decision-Making: Transforming Purchase Behavior and Personalization
    N. Muthurasu, Venkata Ramana Kaneti, S. Vengatesh Kumar, G. Premalatha, P. Aparna, K. Raju, Beslin Pajila
    Modern Consumer Behavior at the Intersection of AI and Social Media, 2026
    This chapter explores the impact of artificial intelligence (AI) on consumer decision-making, focusing on its role in transforming purchasing behavior and personalization. AI technologies such as machine learning, predictive analytics, and recommendation systems have revolutionized how businesses engage with consumers, providing personalized experiences across the decision-making process. From problem recognition to post-purchase evaluations, AI enhances efficiency and relevance. However, it also raises ethical concerns, including data privacy, algorithmic bias, and transparency. The chapter examines these challenges and offers insights for marketers and retailers on leveraging AI for consumer behavior analysis. It also highlights areas for future research, particularly in AI ethics, data privacy, and the long-term effects on consumer autonomy.
  • Interpretable AI in Finance: Enhancing Transparency and Trust
    M.K. Vidhyalakshmi, C. Geetha, B. Yamini, G. Premalatha
    Interpretable and Trustworthy AI Techniques and Frameworks, 2025
    The development of interpretable artificial intelligence (AI) finance has great prospects, and some of its obvious trends are likely to affect its evolution. While dealing with advanced models, the researchers are finding new ways of enabling their comprehension without compromising precision. Achieving the successful application of interpretable AI strategies in the financial sector is largely dependent on the collaboration of machine-learning experts within the finance field, as well as the regulators within that economy. The use of interpretable AI combined with novel solutions such as blockchain technology may enhance the market’s transparency and trust in its offerings. In that case, their legal culture in the promotion of ethics in AI will shift from prohibiting the abuse of AI to giving clearer boundaries and parameters for the proper use of AI systems. As the structures that govern AI development and usage move forward, it is expected that the explainability of systems of AI would be of importance from a regulatory and fairness perspective. Interpretable AI is becoming increasingly pivotal in the financial sector, where transparency and accountability are critical. As machine-learning models become more complex, their decisions often turn into “black box” outputs that are challenging to understand. This chapter examines the role of interpretable AI in financial decision-making, exploring methodologies and tools that enhance the transparency of machine-learning systems. By bridging the gap between human experts and automated systems, interpretable AI fosters trust and ensures that financial institutions can comply with regulatory requirements while maintaining ethical standards.
  • Navigating the Landscape of Interpretable and Trustworthy AI: Key Challenges and Solutions
    B. Yamini, G. Premalatha, D. Vetriselvi, M.K. Vidhyalakshmi
    Interpretable and Trustworthy AI Techniques and Frameworks, 2025
    This chapter discusses the nature of interpretable and trustworthy artificial intelligence (AI) and some of the most important challenges and issues that remain in this area. Legibility and trustworthiness in AI that is now increasingly permeating decision-making in varied applications must be considered a major challenge. This chapter discusses the challenges encountered by developers of AI systems in arriving at transparency, fairness, accountability, and functionality. It is difficult for users, regulators, and developers to understand the workings behind the decisions made by a deep learning model because of its black-box nature, leading to the drugging fears of bias, security vulnerabilities, and ethical concerns. Much horror is caused by adversarial attacks and data-based biases, creating an additional layer of complication in deploying AI in sensitive areas such as healthcare, finance, and criminal justice. The issues with AI have led to a number of explainable AI (XAI) techniques being put forth by researchers, including local interpretable model-agnostic explanations (LIME) and Shapley Additive Explanations (SHAP), which explain decisions made by a model. Other techniques such as attention, feature importance analysis, and models that blend accuracy and interpretability are being pursued. Meanwhile, adversarial defense and ethical AI governance frameworks are being worked on, to enhance robustness and regulatory compliance of AI systems. Becoming a trustworthy AI involves ensuring fairness through bias remediation in the training data. These might include adversarial bias, fairness constraints, and model auditing, aimed at checking discriminatory outcomes. Implementing human-centric AI design is another must-have that gets AI systems to conform with user anticipations to foster trust and usability. Human-in-the-loop (HITL) frameworks enhancing AI decision-making within human oversight complement these with something robust.
  • Retraction to: Improved gait recognition through gait energy image partitioning (Computational Intelligence, (2020), 36, 3, (1261-1274), 10.1111/coin.12340)
    Computational Intelligence, 2025
    RETRACTION : G. Premalatha , P. V. Chandramani , “,” Computational Intelligence 36 no. ( 2020 ): 1261 – 1274 , https://doi.org/10.1111/coin.12340 . The above article, published online on 22 June 2020 in Wiley Online Library ( wileyonlinelibrary.com ) has been retracted by agreement between the journal Editor‐in‐Chief, Diana Inkpen; and Wiley Periodicals LLC. The article was published as part of a guest‐edited issue. Following an investigation by the publisher, all parties have concluded that this article was accepted solely on the basis of a compromised peer review process. The editors have therefore decided to retract the article. The authors have been informed of the retraction.
  • Smart healthcare infrastructure and remote monitoring: Trends, technologies, and challenges
    P. Vinayagam, S. Saranya, G. Premalatha, N. Pavithra, Kalai Priya V., Nivas Kumar V., P. J. Beslin Pajila
    Leveraging Urban Computing for Sustainable Urban Development, 2025
    Technological advancements and innovative healthcare structures such as smart health and telemonitoring allow real-time data capture and diagnosis of patients besides individualized treatment. With mobile devices, IoT, AI, and enhanced internet speed, there is ongoing health tracking in patient health management solutions, chronic disease management, elderly care, and post-surgery care. A convergence of smart technology, healthcare, and cloud and edge computing make it possible to drive data insights and predictive analytics for enhanced patient care at lower costs or even accessing easy healthcare solutions which are otherwise unavailable for the less privileged. But there are still major obstacles today, such as concerns with information protection, privacy, compatibility, and legislation. Potential directions for the future are suggested with a focus on increasing of the interaction between blockchain applications, preserving data privacy, and establishing an ethical approach to this innovative technology.
  • Smart Insole Gait Analysis
    Palak Seth, Varun Gadi, Premalatha G
    4th IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics Icdcece 2025, 2025
    Wearable technology has transformed sports performance and health monitoring with real-time biomechanical testing. It is feasible to wear smart insoles with accelerometers and pressure sensors that allow gait analysis through the measurement of critical parameters like joint angles, stride length, ground reaction forces, and foot patterns. An intelligent insole system that tracks gait data, identifies gait deviations from ideal kinematics, and offers movement correction feedback. Thus introducing a novel approach for continuous gait monitoring and real-time correction. The system is coupled with machine learning algorithms to evaluate biomechanical parameters and optimize motion effectiveness. Experimental results show that the system can detect 93% gait anomalies at 150ms latency and offer real-time feedback, showing the system to prevent injury and optimize performance. The proposed approach is advantageous to sports individuals, rehabilitation patients, and fitness consumers by way of cost-effective and
  • Prosthetic Hand Grasp Recognition Using Residual-Unet Combined with Cross Over Attention
    Premalatha G, Srivatsal Narayan, Sekar Anup Chander, Srikanth Vasamsetti
    Proceedings of the 11th International Conference on Bio Signals Images and Instrumentation Icbsii 2025, 2025
    Grasp pattern recognition plays a pivotal role in empowering prosthetic hands to accurate and effective grip categorization is the foundation of prosthetic hand functionality, therefore facilitating better user experiences and usability. This work presents a custom-built U-Net architecture improved with residual blocks and cross-over attention methods, especially designed for grip categorization tasks. While cross-over attention improves spatial and contextual learning across network layers, the proposed model uses the natural capabilities of U-Net for feature extraction reinforced by residual connections to reduce vanishing gradient problems and increase convergence. Two separate classification scenarios—Whole Category Classification (WCC) and Binary Outcome Classification (BOC)—were followed in experimental assessments. Under WCC, the model attained an accuracy of $83 \\%$ and under BOC, $79 \\%$ to show its dependability and flexibility throughout several categorization needs. This study highlights how sophisticated neural network designs might help prosthetic technology to progress and open the path for more responsive and easy artificial limb control systems
  • Advanced IoT-Enabled Wearable Technology for Maritime Personnel Safety: Real-Time Man Overboard Detection and Emergency Response System
    K.Bharath Kumar Reddy, G.N.S.S. Aditya, B. Yamini, G. Premalatha
    2025 Global Conference on Information Technology and Communication Networks Gitcon 2025, 2025
  • CRAFT: Chronic Renal disease prediction using Artificialneural network with Feature selection Technique
    Panimalar Kathiroli, V. Vijayalakshmi, G. Premalatha
    Aip Conference Proceedings, 2024
  • DeepLG SecNet: utilizing deep LSTM and GRU with secure network for enhanced intrusion detection in IoT environments
    Manikandan Nanjappan, K. Pradeep, Gobalakrishnan Natesan, A. Samydurai, G. Premalatha
    Cluster Computing, 2024
  • RETRACTION:GAITBOOST: Boosting gait recognition performance with BAT-extreme learning machines algorithm
    G. Premalatha, Premanand V. Chandramani, K. Panimalar
    Journal of Intelligent and Fuzzy Systems, 2024
  • Green computing-based digital waste management and resource allocation for distributed fog data centers
    N. Manikandan, D. Vinod, R. Anto Arockia Rosaline, P. Nancy, G. Premalatha
    Computational Intelligence for Green Cloud Computing and Digital Waste Management, 2024
  • Machine Learning Based Sleep Apnea Detection Using EEG Signals
    Rishabh Shah, Divyansh Gaur, G. Premalatha
    2024 IEEE International Conference on Smart Power Control and Renewable Energy Icspcre 2024, 2024
  • Maximizing Mango Yields: Disease Prediction, Grade Classification, and Production Management through Efficient Net Models and PHP-MySQL Integration
    Yamini B, G. Premalatha, Konijeti Sai Kalyan, Rakesh Maddu, Rohith Nukala, Paulraj Jino
    2024 International Conference on Smart Technologies for Sustainable Development Goals Icstsdg 2024, 2024
  • Feature selection for predicting bankruptcy: Comparative analysis
    G. Premalatha, R. Priyanka, Konanki Chaitya
    2023 5th International Conference on Electrical Computer and Communication Technologies Icecct 2023, 2023
  • An Efficient Cloud Storage Model for GOP-Level Video Deduplication using Adaptive GOP Structure
    G. Sujatha, A. Devipriya, D. Brindha, G. Premalatha
    Cybernetics and Systems, 2023
  • A Machine Learning Strategy for Reducing Childhood Obesity Using Millet
    M. Birundadevi, G. Premalatha, M. Nalini, Chelladurai Iyyanar, Vettrivel Arul
    IEEE 9th International Conference on Smart Structures and Systems Icsss 2023, 2023
  • Effective Evaluation of Medical Images Using Artificial Intelligence Techniques
    S. Kannan, G. Premalatha, M. Jamuna Rani, D. Jayakumar, P. Senthil, S. Palanivelrajan, S. Devi, Kibebe Sahile
    Computational Intelligence and Neuroscience, 2022
  • Improved gait recognition through gait energy image partitioning
    G. Premalatha, Premanand V Chandramani
    Computational Intelligence, 2020
  • Depletion of vampire attacks in medium access control level using interior gateway routing protocol
    R. Abirami, G. Premalatha
    2014 International Conference on Information Communication and Embedded Systems Icices 2014, 2015

RECENT SCHOLAR PUBLICATIONS

  • DeepSight: AI Driven Navigation Assistance for the Visually Impaired
    D Thomas, A Rawat, A Das, S Kangabam, G Premalatha
    2026 Twelfth International Conference on Bio Signals, Images, and … , 2026
    2026
  • Interpretable AI inFinance: Enhancing Transparency and Trust
    MK Vidhyalakshmi, C Geetha, B Yamini, G Premalatha
    Interpretable and Trustworthy AI, 316-343 , 2025
    2025
  • 16 Interpretable Al in
    G Premalatha
    Interpretable and Trustworthy AI: Techniques and Frameworks, 316 , 2025
    2025
  • Navigating the Landscape of Interpretable and Trustworthy AI: Key Challenges and Solutions
    B Yamini, G Premalatha, D Vetriselvi, MK Vidhyalakshmi
    Interpretable and Trustworthy AI, 38-68 , 2025
    2025
  • Advanced IoT-Enabled Wearable Technology for Maritime Personnel Safety: Real-Time Man Overboard Detection and Emergency Response System
    KBK Reddy, G Aditya, B Yamini, G Premalatha
    2025 Global Conference on Information Technology and Communication Networks … , 2025
    2025
  • Smart Insole Gait Analysis
    P Seth, V Gadi, P G
    2025 4th International Conference on Distributed Computing and Electrical … , 2025
    2025
  • Prosthetic Hand Grasp Recognition Using Residual-Unet Combined with Cross Over Attention
    G Premalatha, S Narayan, SA Chander, S Vasamsetti
    2025 Eleventh International Conference on Bio Signals, Images, and … , 2025
    2025
  • Maximizing Mango Yields: Disease Prediction, Grade Classification, and Production Management Through Efficient Net Models and PHP-MySQL Integration
    B Yamini, G Premalatha, KS Kalyan, R Maddu, R Nukala, P Jino
    2024 International Conference on Smart Technologies for Sustainable … , 2024
    2024
  • CRAFT: Chronic Renal Disease prediction using artificial neural network with feature selection technique
    P Kathiroli, V Vijayalakshmi, G Premalatha
    AIP Conference Proceedings 3075 (1), 020260 , 2024
    2024
    Citations: 1
  • Machine learning based sleep apnea detection using EEG signals
    R Shah, D Gaur, G Premalatha
    2024 IEEE International Conference on Smart Power Control and Renewable … , 2024
    2024
    Citations: 4
  • DeepLG SecNet: utilizing deep LSTM and GRU with secure network for enhanced intrusion detection in IoT environments
    M Nanjappan, K Pradeep, G Natesan, A Samydurai, G Premalatha
    Cluster Computing 27 (4), 5459-5471 , 2024
    2024
    Citations: 44
  • A Machine Learning Strategy for Reducing Childhood Obesity Using Millet
    M Birundadevi, G Premalatha, M Nalini, C Iyyanar, V Arul
    2023 9th International Conference on Smart Structures and Systems (ICSSS), 1-6 , 2023
    2023
    Citations: 5
  • An efficient Cloud Storage Model for GOP-Level Video deduplication using adaptive GOP structure
    G Sujatha, A Devipriya, D Brindha, G Premalatha
    Cybernetics and Systems, 1-26 , 2023
    2023
    Citations: 5
  • Feature selection for predicting bankruptcy: Comparative analysis
    G Premalatha, R Priyanka, K Chaitya
    2023 Fifth International Conference on Electrical, Computer and … , 2023
    2023
    Citations: 2
  • Effective Evaluation of Medical Images Using Artificial Intelligence Techniques
    KS S Kannan, G Premalatha, M Jamuna Rani, D. Jayakumar, P. Senthil, S ...
    Computational Intelligence and Neuroscience, 9 pages , 2022
    2022
    Citations: 5
  • RETRACTED: Improved gait recognition through gait energy image partitioning
    G Premalatha, P V Chandramani
    Computational Intelligence 36 (3), 1261-1274 , 2020
    2020
    Citations: 15
  • Color Space Conversion Based Texture Feature Model for Thermal Sequence Analysis
    RM G.Premalatha,M.Anithaarokiamary, S.Priyadharshini
    IOSR Journal of Engineering (IOSR JEN), PP 57-60 , 2019
    2019
  • View-invariant gait recognition using gait energy image (GEI)
    G Premalatha, AT Williams, SK Abraham
    Biometrics and Bioinformatics 8 (6), 161-167 , 2016
    2016
  • Depletion of vampire attacks in medium access control level using interior gateway routing protocol
    GP S.Abirami
    International Conference on Information Communication and Embedded Systems … , 2015
    2015
    Citations: 4
  • Framework For Simultaneous Recognized the Levels of Facial Activity
    GP Nisha Rani
    International Conference on Science and Innovative Engineering , 2014
    2014

MOST CITED SCHOLAR PUBLICATIONS

  • DeepLG SecNet: utilizing deep LSTM and GRU with secure network for enhanced intrusion detection in IoT environments
    M Nanjappan, K Pradeep, G Natesan, A Samydurai, G Premalatha
    Cluster Computing 27 (4), 5459-5471 , 2024
    2024
    Citations: 44
  • RETRACTED: Improved gait recognition through gait energy image partitioning
    G Premalatha, P V Chandramani
    Computational Intelligence 36 (3), 1261-1274 , 2020
    2020
    Citations: 15
  • A Machine Learning Strategy for Reducing Childhood Obesity Using Millet
    M Birundadevi, G Premalatha, M Nalini, C Iyyanar, V Arul
    2023 9th International Conference on Smart Structures and Systems (ICSSS), 1-6 , 2023
    2023
    Citations: 5
  • An efficient Cloud Storage Model for GOP-Level Video deduplication using adaptive GOP structure
    G Sujatha, A Devipriya, D Brindha, G Premalatha
    Cybernetics and Systems, 1-26 , 2023
    2023
    Citations: 5
  • Effective Evaluation of Medical Images Using Artificial Intelligence Techniques
    KS S Kannan, G Premalatha, M Jamuna Rani, D. Jayakumar, P. Senthil, S ...
    Computational Intelligence and Neuroscience, 9 pages , 2022
    2022
    Citations: 5
  • Machine learning based sleep apnea detection using EEG signals
    R Shah, D Gaur, G Premalatha
    2024 IEEE International Conference on Smart Power Control and Renewable … , 2024
    2024
    Citations: 4
  • Depletion of vampire attacks in medium access control level using interior gateway routing protocol
    GP S.Abirami
    International Conference on Information Communication and Embedded Systems … , 2015
    2015
    Citations: 4
  • Feature selection for predicting bankruptcy: Comparative analysis
    G Premalatha, R Priyanka, K Chaitya
    2023 Fifth International Conference on Electrical, Computer and … , 2023
    2023
    Citations: 2
  • CRAFT: Chronic Renal Disease prediction using artificial neural network with feature selection technique
    P Kathiroli, V Vijayalakshmi, G Premalatha
    AIP Conference Proceedings 3075 (1), 020260 , 2024
    2024
    Citations: 1
  • DeepSight: AI Driven Navigation Assistance for the Visually Impaired
    D Thomas, A Rawat, A Das, S Kangabam, G Premalatha
    2026 Twelfth International Conference on Bio Signals, Images, and … , 2026
    2026
  • Interpretable AI inFinance: Enhancing Transparency and Trust
    MK Vidhyalakshmi, C Geetha, B Yamini, G Premalatha
    Interpretable and Trustworthy AI, 316-343 , 2025
    2025
  • 16 Interpretable Al in
    G Premalatha
    Interpretable and Trustworthy AI: Techniques and Frameworks, 316 , 2025
    2025
  • Navigating the Landscape of Interpretable and Trustworthy AI: Key Challenges and Solutions
    B Yamini, G Premalatha, D Vetriselvi, MK Vidhyalakshmi
    Interpretable and Trustworthy AI, 38-68 , 2025
    2025
  • Advanced IoT-Enabled Wearable Technology for Maritime Personnel Safety: Real-Time Man Overboard Detection and Emergency Response System
    KBK Reddy, G Aditya, B Yamini, G Premalatha
    2025 Global Conference on Information Technology and Communication Networks … , 2025
    2025
  • Smart Insole Gait Analysis
    P Seth, V Gadi, P G
    2025 4th International Conference on Distributed Computing and Electrical … , 2025
    2025
  • Prosthetic Hand Grasp Recognition Using Residual-Unet Combined with Cross Over Attention
    G Premalatha, S Narayan, SA Chander, S Vasamsetti
    2025 Eleventh International Conference on Bio Signals, Images, and … , 2025
    2025
  • Maximizing Mango Yields: Disease Prediction, Grade Classification, and Production Management Through Efficient Net Models and PHP-MySQL Integration
    B Yamini, G Premalatha, KS Kalyan, R Maddu, R Nukala, P Jino
    2024 International Conference on Smart Technologies for Sustainable … , 2024
    2024
  • Color Space Conversion Based Texture Feature Model for Thermal Sequence Analysis
    RM G.Premalatha,M.Anithaarokiamary, S.Priyadharshini
    IOSR Journal of Engineering (IOSR JEN), PP 57-60 , 2019
    2019
  • View-invariant gait recognition using gait energy image (GEI)
    G Premalatha, AT Williams, SK Abraham
    Biometrics and Bioinformatics 8 (6), 161-167 , 2016
    2016
  • Framework For Simultaneous Recognized the Levels of Facial Activity
    GP Nisha Rani
    International Conference on Science and Innovative Engineering , 2014
    2014