Hema Priya Natarajan
Verified @gmail.com
Scopus Publications
- Advancing Healthcare Diagnostics: A Precision-Driven Approach to Disease Prediction and Personalized Treatment Recommendation
Hema Priya Natarajan, M. Chandru, A. Pushparaj
SN Computer Science, 2026 - A Review on Federated Learning with Dual Knowledge Transfer
Hemapriya N, Gukan T K
2026 2nd International Conference on Intelligent Systems for Communication Iot and Security Iciscois 2026, 2026
With smartphones and edge devices being commonplace, expansive personal photo data has become incredibly common. As we embark on applications that utilize personal photo data to train effective classification models, including smart photo organization, the risks of privacy and the complexities of deploying centralized training weigh heavily on us. With the capabilities of Federated Learning (FL), users can collaboratively train models with other users without the sharing of raw personal data. However, FL is challenged by non-IID (non-independently and identically distributed) data, as dataset uniqueness stemmed from clients' unique photo collections is problematic because it yields non-IID client datasets that are often unbalanced too. FL methods, such as FedAvg, traditionally develop an adaptable global model while providing poorly personalized local models to users; newer approaches, like FedRep, improve personalization, but can instead worsen the performance of the global model. This paper presents an innovative dual knowledge transfer framework that mitigates the impact on i) local model personalization, and ii) global model generalization. The framework combines synthetic feature generation and bidirectional knowledge distillation to ensure users receive a personalized model while the users collaboratively improve the performance of the global model, all without compromising an individual's privacy. - Privacy Preserving Federated Reinforcement Imitation Learning Framework With Robust Aggregation for Cloud-Based Domestic Robots
Hema Priya Natarajan
Concurrency and Computation Practice and Experience, 2025
The evolution of cloud‐based web services for the control and tracking of robotic devices has significantly transformed the field of robotics. Domestic robotic devices performing household activities are becoming increasingly popular, as they collect large volumes of data, transmit it to the cloud, and leverage web services for collaborative learning. These devices interconnect and learn from their peers over the cloud. However, this distributed and interconnected learning environment introduces a serious vulnerability to model poisoning attacks, where malicious participants can deliberately corrupt the learning process. These attacks are a direct result of Byzantine behavior, where certain participants act arbitrarily or adversarially, undermining the integrity of the global model. These attacks pose a critical threat to the reliability, safety, and privacy of robotic systems operating in real‐world environments. To accelerate learning, peers connected through cloud‐based services contribute data and updates, but this collaboration inevitably leads to the exposure of sensitive information, further escalating privacy concerns. To tackle these pressing issues, we propose a novel framework called Federated Reinforcement Imitation Learning (FRIL). The framework involves the design of the FRIL architecture, an in‐depth analysis of threats in a distributed setting, and the development of a robust algorithm specifically designed to defend against model poisoning attacks. Experimental results demonstrate a high learning accuracy of 88 percent using the Edge IIoT dataset. The collaborative, decentralized, and privacy‐preserving nature of the proposed framework, combined with imitation learning, makes it highly resilient against adversarial interference, ensuring the stability and integrity of the Federated Learning process in domestic robotic environments. This work directly targets the growing threat of model poisoning attacks and provides a concrete solution to secure collaborative learning in intelligent robotic systems. - FEDTWIN–trustworthy digital twin as a service for visually impaired
Hema Priya Natarajan, Pushparaj Annadurai
Automatika, 2025
The Industrial Internet of Things (IIoT) revolutionize industries such as manufacturing, logistics, energy, and healthcare by merging smart sensors and devices with sophisticated network connectivity and advanced data analysis. Digital Twin As a Service (DTaaS) for Internet of Healthcare Things (IoHT) in the healthcare industry opens exciting opportunities to create virtual replicas of real healthcare systems and assets. Digital twins relying on cloud platforms, such as Amazon Web Services, Microsoft Azure, and Google Cloud, provide several vital capabilities, including data informed decision making, personalized patient simulation, up to 30% decrease in equipment downtime with predictive maintenance, and operational efficiency of more than 25% through real-time remote monitoring. This paper proposes an all encompassing methodology towards the development and deployment of compositional digital twins utilizing services applied towards assisting the visually challenged with a smart stick. Federated learning has been proposed as one potential approach that could help in preserving the privacy of clients, particularly concerning the protection of patient's confidential information. One of the possible healthcare scenario that demonstrates how digital twin technology guiding visually impaired individuals, with a possible enhancement in the success rate of mobility by 40%. - Hashed Nebula: Self-attention with Feature Engineering for Dynamic Malware Detection
Shymala Gowri S, Hema Priya N, Gopika Rani N
International Conference on Communication Computing Networking and Control in Cyber Physical Systems Ccncps 2025, 2025
Identification of malware is vital for safeguarding safety critical systems from cyber threats. Currently learning based approaches aid the malware detection pipeline. Current techniques to detect malware on Windows systems tend to overlook various types of behaviors, primarily concentrating on Application Programming Interface (API) calls without considering heterogeneous information, and also it requires large amounts of annotated data. To solve these problems, in this work, Hashed Nebula is proposed, a self-attention transformer-based neural network is considered along with a hashing method to encode API call names, categories, and arguments separately to improve features selection. Proposed Hashed-Nebula is evaluated on benchmark malware datasets such as Speakeasy and Malicious Code Dataset (MCD). Hashed-Nebula performs better than the existing Nebula model, with 4% increase in detection accuracy and 2% improvement in F1 score on Speakeasy dataset. In addition, it shows an 18% increase in detection accuracy and a 4% improvement in F1 score in the MCD dataset. Hashed-Nebula could serve as a reliable and efficient solution for malware detection. - Predicting Crop Yield Based on Bagging Ensemble Model in Machine Learning
K Umamaheswari, M.P. Ramkumar, N.Hema Priya
2025 4th International Conference on Smart Technologies and Systems for Next Generation Computing Icstsn 2025, 2025
This paper is concerned with various machine Learning (ML) techniques to estimate the crop yield based on various factors, followed by an averaging technique. Multiple models are utilised by this ensemble machine learning technique called Bagging, taking weak learners as the base model to make the prediction. The pertinent ML algorithms that support crop yield prediction are Support Vector machines (SVM), Random trees (RT), Linear Regression (LR), K Nearest Neighbour (KNN), Random Forest (RF), Multiple Regression (MR), Support Vector Regression (SVR), Artificial Neural Networks (ANN) and Deep Neural Networks (DNN). Of these, in this paper, Classification and Regression Tree (CART), Ridge Regression (RR), eXtreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN) were implemented along with Bagging as the ensemble technique. The output of the entity models was thus averaged to give a final prediction. - Trustworthy Glucose Prediction Using Federated Learning: Privacy Preserving as a Service
Agasthia Packianathan Maria, Hema Priya N, Shymala Gowri S
2025 International Conference on Computational Innovations and Engineering Sustainability Iccies 2025, 2025
Diabetes is one of the most difficult chronic diseases to manage, especially among working individuals and elderly people with limited mobility. Without adequate time to monitor the blood sugar levels, many individuals find it particularly difficult to keep tabs on their glucose. This paper proposes a solution to this issue leveraging Deep Learning (DL) methods, particularly Long Short-Term Memory (LSTM) networks, which are a type of Recurrent Neural Networks (RNN) ideally designed for time series forecasting. To automate the process of diabetes management, the LSTM model is designed to predict glucose levels by being trained on active data collected from the users in real time. For the model to learn without the sensitive data being exposed, data privacy and protection mechanisms are established using Federated Learning (FL). This method allows sensitive information to remain securely stored within devices while ensuring the advantages of joint model training and reduced vulnerability risks from storing shared data. The healthcare centers provide the combination of LSTM and FL and host it in a cloud environment as a service or as web services enabling patients to receive blood glucose level predictions in real time without visiting the clinic. The proposed system shows an accuracy of LSTM with FL which results to 95% and only LSTM as such receives 98% with loss being minutely less of 1% compared to each other. The total error reduced using RMSE and MAE are 0.17 and 0.02 for plain LSTM and 0.29 and 0.09 for LSTM with FL. - DeepFM model based Trustworthy Web Service Recommendation System
Hema Priya N, Gopikarani N, Shymalagowri S, Ruthravarshini R
2025 International Conference on Next Generation Computing Systems Intelligent System for Sustainable Development Icngcs 2025 Conference Proceedings, 2025
In today's changing web environment, users find it difficult to choose reliable services because of the variety and unpredictability of online platforms. This paper presents a Trustworthy Web Service Recommendation System that uses a DeepFM model along with a self-attention mechanism to offer accurate, privacy-friendly, and personalized service recommendations. By examining user behaviour, service features, and previous interactions, the system generates high-quality recommendations. Furthermore, a privacy-preserving module protects data, and a trust score mechanism increases confidence in the chosen services. - Multi-Classification Based Microservices Security Using Federated Learning
Hema Priya N, Valan Antony Raj G, Athithiya A, Gukan T K, Nithishkrishna R S, Sailesh K
2025 International Conference on Intelligent Innovations in Engineering and Technology Iciiet 2025, 2025
Modern e-commerce platforms increasingly rely on microservices architecture for its superior scalability and flexibility. However, this distributed approach introduces significant security vulnerabilities, particularly concerning sensitive data protection. Our research presents an innovative security enhancement method that combines federated learning with LSTM models, validated using the Sock Shop dataset. The federated learning paradigm facilitates decentralized model training while maintaining data privacy across distributed microservices. Our Dual Model Federated Learning (DMFL) framework employs Multi-task Federated Learning to develop multi classification anomaly detection models for individual microservices. The External Attention Mechanism with Multi-channel Residual Structure effectively identifies complex anomaly patterns and the Local-Global Parallel Knowledge Transfer framework enables efficient knowledge exchange between local and global features. Experimental evaluation demonstrates that our approach significantly improves security measures without compromising data privacy, outperforming traditional centralized methods. The DMFL method achieves impressive performance metrics of 96.2% accuracy, 93.5% precision, and 91.7% recall. - Attention-Enhanced Deep Learning Models for EEG-Based Driver Drowsiness Detection
Shymala Gowri S, Hema Priya N, A. S. Harini, Dharshini V, Kannishree K, Poorvajavani S. K, Prathika A. K
2025 International Conference on Intelligent Innovations in Engineering and Technology Iciiet 2025, 2025
Driver fatigue and drowsiness have become increasingly significant factors in traffic accidents. Road traffic accidents are responsible for hundreds of thousands of deaths in the world every year. Many of today's detection methods for drowsiness use environmental condition or observable differences in driver behavior, which can often yield unreliable information. To be effective, a solution must ensure minimal environmental restrictions. In this work, EEG signals provide indicators to fatigue and attention. The SEED VIG dataset was utilized to preprocess and synchronize EEG signals for possible classification of drivers into alert and drowsy depictions. To classify the EEG signals, deep learning models: (a) Entropy Optimization Network (EON), (b) HealNet EEG, (c) Self-Attention based architectures, and (d) Multi-Scale CNNs, were configured to be fully functional. Each of these models produced results that demonstrated the inability of traditional algorithms to yield more reliable estimates when detecting drowsiness and fatigue. This research offers real time solutions utilizing AI EEG analysis for intelligent transportation systems, justified and reliable alternatives to reduce accidents and loss of life on roadways. - LV-YOLO: logistic vehicle speed detection and counting using deep learning based YOLO network
N. Gopika Rani, N. Hema Priya, A. Ahilan, N. Muthukumaran
Signal Image and Video Processing, 2024 - Federated Learning Based Privacy Preserving for Brain Tumor Detection
Hema Priya Natarajan, Shymalagowri S, Dharaneesh Ckv, Pushparaj A, Krithik Ram B
2024 IEEE Silchar Subsection Conference Silcon 2024, 2024 - Federated Learning-based Healthcare Services for COVID-19 Pandemic
Shymala Gowri S, Hema Priya N, Wael Suliman, VinayaKumar Ravi, Agasthia Packianathan Maria
2024 6th International Symposium on Advanced Electrical and Communication Technologies Isaect 2024, 2024 - A Comparative Analysis of Physiological Signal Processing and Classification: Advances in EEG, EMG, and EOG Modalities
Shymala Gowri S, Niranjana RS, Wael Suliman, Hema Priya N, VinayaKumar Ravi
2024 6th International Symposium on Advanced Electrical and Communication Technologies Isaect 2024, 2024 - Privacy Preservation Using Federated Learning for Credit Card Transactions
Hema Priya N, P D Rathika, Pushparaj A
Proceedings of the 2023 International Conference on Intelligent Systems for Communication Iot and Security Iciscois 2023, 2023 - Preface
Shri Gopalakrishnan, K. Prakasan, Geetha Govindarajulu, Gopinath Damodaran, G Varadaraj, et al.
Proceedings of the 2023 International Conference on Intelligent Systems for Communication Iot and Security Iciscois 2023, 2023 - Analysis of Trust aware Web Services using Federated Learning
N.Hema Priya, N.Gopika Rani, S. Shymalagowri, R. Sivasaran
Proceedings of the 2023 International Conference on Intelligent Systems for Communication Iot and Security Iciscois 2023, 2023 - Secured machine learning using Approximate homomorphic scheme for healthcare
S Shymala Gowri, Sudha Sadasivam, N Hema Priya, Deva Priyan T A
Proceedings of the 2023 International Conference on Intelligent Systems for Communication Iot and Security Iciscois 2023, 2023 - Covid-19: Comparison of Time Series Forecasting Models and Hybrid ARIMA-ANN
N. Hema Priya, S. M. Adithya Harish, N. Ravi Subramanian, B. Surendiran
Lecture Notes in Networks and Systems, 2022 - Improving Security with Federated Learning
Hema Priya.N, Adithya Harish S M, Shymala Gowri S, PD Rathika
2021 International Conference on Computational Performance Evaluation Compe 2021, 2021 - Image Classification in the Era of Deep Learning
A. Ashin, P.D. Rathika, Y. Mahavidhya, N. Hemapriya, S.Shymala Gowri
2021 International Conference on Advancements in Electrical Electronics Communication Computing and Automation Icaeca 2021, 2021 - Deep belief network based detection and categorization of malicious URLs
ShymalaGowri Selvaganapathy, Mathappan Nivaashini, HemaPriya Natarajan
Information Security Journal, 2018 - QOS based web service composition for selection using improved gravitational search algorithm
Asian Journal of Information Technology, 2016 - Optimal web service selection using hybrid IWD evolutionary algorithm
International Journal of Applied Engineering Research, 2015 - QoS based selection and composition of web services-a fuzzy approach
Priya
Journal of Computer Science, 2014
RECENT SCHOLAR PUBLICATIONS
- Advancing Healthcare Diagnostics: A Precision-Driven Approach to Disease Prediction and Personalized Treatment Recommendation
HP Natarajan, M Chandru, A Pushparaj
SN Computer Science 7 (3), 220 , 2026
2026 - Multi-Classification Based Microservices Security Using Federated Learning
N Hema, Priya, R Valan, Antony, A Athithiya, TK Gukan, ...
2025 International Conference on Intelligent Innovations in Engineering and … , 2025
2025 - FEDTWIN–trustworthy digital twin as a service for visually impaired
HP Natarajan, P Annadurai
Automatika 66 (4), 923-938 , 2025
2025 - DeepFM model based Trustworthy Web Service Recommendation System
N Hema Priya, N Gopikarani, S Shymalagowri, R Ruthravarshini
2025 International Conference on Next Generation Computing Systems (ICNGCS), 1-7 , 2025
2025
Citations: 1 - Privacy Preserving Federated Reinforcement Imitation Learning Framework With Robust Aggregation for Cloud‐Based Domestic Robots
H Priya Natarajan
Concurrency and Computation: Practice and Experience 37 (15-17), e70153 , 2025
2025
Citations: 1 - Trustworthy Glucose Prediction Using Federated Learning: Privacy Preserving as a Service
A. P. Maria, H. P. N and S. G. S
2025 International Conference on Computational Innovations and Engineering … , 2025
2025 - RONI and TRIM based defense methods for federated learning driven backdoor attacks
HP Natarajan, AR Yogharaj, CKV Dharaneesh
Data Science & Exploration in Artificial Intelligence, 383-392 , 2025
2025
Citations: 1 - Federated Learning-based Healthcare Services for COVID-19 Pandemic
S Gowri S, H Priya N, W Suliman, VK Ravi, AP Maria
2024 6th International Symposium on Advanced Electrical and Communication … , 2024
2024
Citations: 1 - A Comparative Analysis of Physiological Signal Processing and Classification: Advances in EEG, EMG, and EOG Modalities
S Gowri S, N RS, W Suliman, H Priya N, VK Ravi
2024 6th International Symposium on Advanced Electrical and Communication … , 2024
2024
Citations: 1 - Federated Learning Based Privacy Preserving for Brain Tumor Detection
HP Natarajan, S Shymalagowri, D Ckv, A Pushparaj, K Ram
2024 IEEE Silchar Subsection Conference (SILCON 2024), 1-6 , 2024
2024
Citations: 4 - LV-YOLO: logistic vehicle speed detection and counting using deep learning based YOLO network
NG Rani, NH Priya, A Ahilan, N Muthukumaran
Signal, Image and Video Processing 18 (10), 7419-7429 , 2024
2024
Citations: 54 - Machine learning based robotic-assisted upper limb rehabilitation therapies: a review
SG Selvaganapathy, N Hema Priya, PD Rathika, M Mohana Lakshmi
Computer Vision and Robotics: Proceedings of CVR 2022, 59-73 , 2023
2023
Citations: 1 - Secured machine learning using approximate homomorphic scheme for healthcare
SS Gowri, S Sadasivam, NH Priya, DP TA
2023 International Conference on Intelligent Systems for Communication, IoT … , 2023
2023
Citations: 7 - Analysis of Trust aware Web Services using Federated Learning
NH Priya, NG Rani, S Shymalagowri, R Sivasaran
2023 International Conference on Intelligent Systems for Communication, IoT … , 2023
2023
Citations: 4 - Privacy Preservation Using Federated Learning for Credit Card Transactions
HN Priya, PD Rathika, P A
2023 International Conference on Intelligent Systems for Communication, IoT … , 2023
2023
Citations: 15 - A Novel Collaborative Caching Technique To Improve Performance on Data Storage In Hadoop
NG rani, NH Priya
YMER , 2022
2022 - Covid-19: Comparison of time series forecasting models and hybrid ARIMA-ANN
N Hema Priya, SM Adithya Harish, N Ravi Subramanian, B Surendiran
Rising Threats in Expert Applications and Solutions: Proceedings of FICR … , 2022
2022
Citations: 6 - OBJECT DETECTION USING SEMI SUPERVISED LEARNING METHODS.
SG Selvaganapathy, N Hema Priya, PD Rathika, K Venkatachalam
ICTACT Journal on Soft Computing 12 (4) , 2022
2022 - THE SMART ROBOTIC PROCESS AUTOMATION MODEL FOR STREAMLINING INDUSTRIAL PROCESSES
PD Rathika, NH Priya, SS Gowri
ICTACT JOURNAL ON DATA SCIENCE AND MACHINE LEARNING 3 (03), 322-326 , 2022
2022 - Stock market Prediction using Reinforcement Learning Technique
SG S, H Priya N, R Pd
YMER 21 (7), 1022-1036 , 2022
2022
MOST CITED SCHOLAR PUBLICATIONS
- Deep belief network based detection and categorization of malicious URLs
ShymalaGowri, Nivaashini, HemaPriya
Information Security Journal: A Global Perspective 27 (3), 145-161 , 2018
2018
Citations: 96 - LV-YOLO: logistic vehicle speed detection and counting using deep learning based YOLO network
NG Rani, NH Priya, A Ahilan, N Muthukumaran
Signal, Image and Video Processing 18 (10), 7419-7429 , 2024
2024
Citations: 54 - QoS based optimal selection of web services using fuzzy logic
NH Priya, S Chandramathi
Journal of Emerging Technologies in Web Intelligence 6 (3), 331-339 , 2014
2014
Citations: 16 - Privacy Preservation Using Federated Learning for Credit Card Transactions
HN Priya, PD Rathika, P A
2023 International Conference on Intelligent Systems for Communication, IoT … , 2023
2023
Citations: 15 - Improving Security with Federated Learning
H Priya.N, AH S M, S Gowri, PD Rathika
2021 International Conference on Computational Performance Evaluation (ComPE … , 2021
2021
Citations: 12 - QOS BASED SELECTION AND COMPOSITION OF WEB SERVICES-A FUZZY APPROACH
NH Priya, C S
Journal of Computer Science 10 (5), 861-868 , 2014
2014
Citations: 9 - Secured machine learning using approximate homomorphic scheme for healthcare
SS Gowri, S Sadasivam, NH Priya, DP TA
2023 International Conference on Intelligent Systems for Communication, IoT … , 2023
2023
Citations: 7 - Covid-19: Comparison of time series forecasting models and hybrid ARIMA-ANN
N Hema Priya, SM Adithya Harish, N Ravi Subramanian, B Surendiran
Rising Threats in Expert Applications and Solutions: Proceedings of FICR … , 2022
2022
Citations: 6 - Analysis of heart disease prediction using machine learning techniques
NH Priya, N Gopikarani, SS Gowri
Handbook of Artificial Intelligence in Biomedical Engineering, 173-194 , 2021
2021
Citations: 6 - Federated Learning Based Privacy Preserving for Brain Tumor Detection
HP Natarajan, S Shymalagowri, D Ckv, A Pushparaj, K Ram
2024 IEEE Silchar Subsection Conference (SILCON 2024), 1-6 , 2024
2024
Citations: 4 - Analysis of Trust aware Web Services using Federated Learning
NH Priya, NG Rani, S Shymalagowri, R Sivasaran
2023 International Conference on Intelligent Systems for Communication, IoT … , 2023
2023
Citations: 4 - Optimal Selection and Composition of Web Services – A Survey
NH Priya, S Chandramathi
International Journal of Computer Applications 49 (2), 0975-8887 , 2012
2012
Citations: 4 - Summarization of Customer Reviews in Web Services using Natural Language Processing
N Hema, Priya, GS Shymala, SN Ravi, HSM Adithya
Proceedings of the First International Conference on Combinatorial and … , 2021
2021
Citations: 3 - Image Classification in the Era of Deep Learning
A Ashin, PD Rathika, Y Mahavidhya, N Hemapriya, SS Gowri
2021 International Conference on Advancements in Electrical, Electronics … , 2021
2021
Citations: 3 - Summarization of Customer Reviews in Web Services using Natural Language Processing
NH Priya, SG S, R Subramaniam N, AH S M
Proceedings of the First International Conference on Combinatorial and … , 2021
2021
Citations: 2 - Forensic Analysis and Security Assessment in Android m-Banking Applications: A Survey
K Khavya, NH Priya
Indian Journal of Computer Science 4 (5) , 2019
2019
Citations: 2 - DeepFM model based Trustworthy Web Service Recommendation System
N Hema Priya, N Gopikarani, S Shymalagowri, R Ruthravarshini
2025 International Conference on Next Generation Computing Systems (ICNGCS), 1-7 , 2025
2025
Citations: 1 - Privacy Preserving Federated Reinforcement Imitation Learning Framework With Robust Aggregation for Cloud‐Based Domestic Robots
H Priya Natarajan
Concurrency and Computation: Practice and Experience 37 (15-17), e70153 , 2025
2025
Citations: 1 - RONI and TRIM based defense methods for federated learning driven backdoor attacks
HP Natarajan, AR Yogharaj, CKV Dharaneesh
Data Science & Exploration in Artificial Intelligence, 383-392 , 2025
2025
Citations: 1 - Federated Learning-based Healthcare Services for COVID-19 Pandemic
S Gowri S, H Priya N, W Suliman, VK Ravi, AP Maria
2024 6th International Symposium on Advanced Electrical and Communication … , 2024
2024
Citations: 1
