Dr. Balika J chelliah

Scopus Publications

Hybrid Fed-QNet: a federated deep learning framework with quantum GANs for privacy-aware plant disease detection
V. Brindha Devi, Balika J. Chelliah, Y. Arockia Jesuraj, S. Dhanasekaran
Evolving Systems, 2026
Automated email processing via a transformer based framework for open-set email categorization, abstractive summarization and sentiment analysis
Soundarya Suresh, M. Amrutha Sridhanya, Balika J. Chelliah, B. Aarthi
Neural Computing and Applications, 2026
A comprehensive cross-attention and fuzzy segmentation approach for rice plant disease detection
R. Prabavathi, Balika J. Chelliah, R. Sampath, S. Vinodh Kumar
International Journal of Machine Learning and Cybernetics, 2025
A comprehensive approach to fetal health prediction using preprocessing and classification
Valliammai Ramanathan, Balika J. Chelliah
Progressive Computational Intelligence Information Technology and Networking, 2025
The main focus of this paper is to enhance the interpretation of cardiotocography (CTG) data, which is used to identify fetal discomfort during pregnancy by tracking the heart rate of fetus and contraction of uterine. To ensure the validity of classification models used to evaluate fetal well-being, effective pre-processing is essential. The research uses methods that minimize noise while maintaining significant signal characteristics, such as the Savitzky-Golay and median filters for smoothing and linear interpolation for addressing missing data. This work uses cost-sensitive learning to solve the issue of minority classes that are underrepresented in CTG data. In order to emphasize accurate identification of critical categories such as “suspected” and “pathological,” the model assigns larger misclassification costs to these. This ensures improved classification performance in these critical circumstances.
Detecting Re-Entrancy Attacks in Ethereum via Dynamic Tracing
Preethy Jemima P, Balika J Chelliah
2025 IEEE 7th International Conference on Computing Communication and Automation Iccca 2025, 2025
One of the most promising technology of blockchain still suffers from multiple attacks. Attack detection is handled by various technologies to enhance the security. Hackers moto is to steal the digital currency here the discussion is of the digital currency Ethereum which also has suffered from the famous attack Re-entrancy attack. Though the usage of smart contact is highly believed by users, making the function to be called again and again leads to this kind of attack. Re-entrancy attacks pose a persistent threat to Ethereum smart contracts, enabling malicious users to repeatedly call vulnerable functions before the state variables are correctly updated. While traditional approaches rely heavily on symbolic execution and SMT solvers for vulnerability detection, these methods suffer from scalability and precision limitations. A novel hybrid framework that integrates dynamic execution tracing with AI-driven classification models, such as Quantum Neural Networks (QNN), for the robust detection of re-entrancy attacks. The system leverages taint analysis and runtime monitoring to generate behavioral features, which are then used to train and evaluate machine learning models. Experiments conducted on benchmark datasets demonstrate superior accuracy and reduced false positives when compared to conventional static analysis techniques, showcasing the effectiveness of combining dynamic and AI-based strategies for smart contract security.
Multilingual language classification model for offensive comments categorisation in social media using HAMMC tree search with enhanced optimisation technique
B. Aarthi, Balika J. Chelliah
International Journal of Computational Science and Engineering, 2025
The exponential rise of social media platforms has led to a surge in offensive content, highlighting the necessity for effectively detecting and managing such comments. This necessitates precise and advanced online social networks (OSN) categorisation and optimisation methods. This study introduces and assesses a novel technique for automatically categorising texts, supporting over 60 languages, without relying on a pre-annotated dataset. The technique employs multilingual methods based on the randomised explicit semantic analysis (ESA) strategy. To combat the inherently multilingual nature of social media content, the paper introduces an innovative classification and optimisation strategy named 'hybrid adaptive Markov chain Monte Carlo tree search (HAMCMTS) with enhanced eagle Aquila optimiser (EEAO)'. The study uses three publicly available datasets to identify negative or offensive comments in various languages, offering a comprehensive analysis in this field. The proposed approach holds potential for diverse applications, particularly in multilingual categorisation tasks like monitoring disaster-related communications on social media to improve visibility and trust. Moreover, it incorporates a sophisticated mechanism to bolster the dependability of its recommendations.
An approach Towards Ocular Disease Impact Analysis Using One Shot Detector
Meivezhi G D, Balika J Chelliah
2025 2nd Asia Pacific Conference on Innovation in Technology Apcit 2025, 2025
Diabetes is a prevalent chronic condition that significantly impacts patients' daily lives and can lead to damage to vital organs over time. While it cannot be cured, proper care is essential to mitigate its adverse effects. Regular visits to healthcare professionals are crucial to ensuring diabetics receive appropriate care. The existing challenges in Diabetic retinopathy detection and evaluation is towards the lack of appropriate dataset and quality of dataset. However, there is a need for innovative approaches to empower individuals with diabetes to manage their blood sugar levels proactively without constant doctor visits. The proposed method aims to address this challenge by employing predictive techniques to enable self-monitoring of blood sugar levels. The primary objective of the suggested approach is to alleviate the burden of frequent physician visits and diagnostic centre appointments. It utilizes deep predictive neural networks and advanced algorithms to analyse data related to retinopathy, a common complication of diabetes. The proposed algorithm is employed to identify retinal abnormalities, while the histogram and GLCM Gray co-matrix is utilized to extract relevant features from the data. Subsequently, a Deep Predictive Neural Network (DPNN-OSD) based One-shot detector (OSD) is developed which is employed for classification tasks. The effectiveness of the model is evaluated using metrics such as accuracy, precision, recall, and confusion matrix analysis. To validate the model and anticipate potential issues, various experimental inputs are provided to the system. By integrating predictive analytics and machine learning techniques, the proposed approach aims to empower individuals with diabetes to monitor their condition effectively and intervene early, when necessary, thereby improving their overall health outcomes.
Real-Time Smart Meeting Assistant Using Edge AI for Audio Capture, Speech-to-Text Conversion, and Meeting Scheduling
A Senthilselvi, Mohammad Saquib Daiyan, Mosaab Ahmad, Rajul Mishra, Pakshal Tata, Balika J Chelliah
2025 2nd International Conference on Computing and Data Science Iccds 2025, 2025
This research presents a novel approach to enhancing meeting productivity through the integration of edge AI, cloud-based transcription, and real-time scheduling. Using a Seeed Studio XIAO ESP32S3 Sense device for continuous audio recording, the system sends two-minute audio chunks to a FastAPI backend for transcription using speech-to-text models. Following transcription, the text is processed by a Tiny LLaMA model to extract meaningful insights, such as action items, summaries, and key decisions. Additionally, speaker diarization is applied to differentiate speakers, improving the clarity of transcripts. The system integrates with Google APIs for automatic event scheduling and meeting reminders. This research explores the design, implementation, and evaluation of this intelligent meeting assistant, with an emphasis on accuracy, scalability, and real-time performance. Experimental results demonstrate that the system achieves a Word Error Rate (WER) of 7.3% for transcription in quiet environments, 89.5% accuracy in speaker diarization for meetings with up to 6 participants, and extracts relevant action items with 85.7% precision. The end-to-end system latency averages 3.2 seconds for processing a 2-minute audio segment, making it suitable for real-time applications. User satisfaction surveys indicate a significant 37% improvement in meeting productivity and a 42% reduction in post-meeting administrative tasks.
Enhancing Cervical Cancer Detection: Explainable AI and Attention Mechanisms for Pap Smear Classification
Balika J Chelliah, Sarghi Kaur Gahra, M. Shrinidhi, S. Yamini Devi, A. SenthilSelvi, P. Meenalohchini
2025 8th International Conference on Circuit Power and Computing Technologies Iccpct 2025, 2025
Cervical cancer is the second most prevalent female cancer in India, responsible for almost $\mathbf{1 8. 3 \%}$ of all cancers in women, with more than 120,000 new cases every year. Though preventable and curable at early ages, poor availability of skilled cytopathologists and late diagnosis remain the causative factors of high mortality. Conventional approaches to diagnosis heavily depend on Pap smear slide manual screening, which is time consuming, subjective, and prone to errors, particularly in resourcescarce areas. To address these challenges, this study proposes an attention-based and explainable deep learning architecture for cervical cell classification. The architecture is constructed over the EfficientNet-B0 backbone for strong feature extraction, supplemented with a Convolutional Block Attention Module (CBAM) to highlight clinically important features by using improved channel-wise attention. The system has an extensive preprocessing pipeline including image resizing, denoising, Otsu’s thresholding, morphological operations, and color normalization to provide quality input data. The model is trained on a curated dataset comprising both cancerous and normal cervical cytology images. Post-hoc explanation methods such as Grad-CAM++, SHAP, and LIME are used for explaining and justifying the predictions made by the model. The proposed method attains an accuracy of 82%, a sensitivity of 80.6%, specificity of 83.1%, and an AUC score of $\mathbf{0. 8 7}$. This work emphasizes the potential of explainable deep learning systems to aid early and accurate cervical cancer diagnosis, particularly in underserved healthcare environments.
A Decentralized Cloud-Based Approach to Enhancing EHR Security with Blockchain and Dual Encryption
A Senthilselvi, M Eyadu Nandhan, R Kishore, M Charan, Balika J Chelliah, S. SenthilPandi
Proceedings of 3rd IEEE International Conference on Knowledge Engineering and Communication Systems Ickecs 2025, 2025
With the widespread support of Electronic Health Records (EHRs) in the medical field also comes a realistic worry of the need to secure this information from unauthorized access. In traditional electronic health record management systems, centralized system approach puts up at risk of data invasions, mainly patient records which are very delicate and confidential. This paper describes an efficient cloud-based file sharing system for the storage and management of EHRs that takes advantage of cloud computing and blockchain technologies. The presented method implements dual-layer encryption which includes Elliptic Curve Digital Signature Algorithm (ECDSA) and Secured Hashing Algorithm-256 (SHA-256) hashing to assure the authenticity, integrity and confidentiality of the EHRs. The use of a blockchain approach within the system bounds allows for elimination of even servers thereby enhancing how the information integrity is preserved. The electronic health records management system proposed in this paper eliminates the major concerns of data integrity associated with client-server-based systems and overcomes hematogenic challenges through maintaining patients’ associate’s privacy even as threats evolve in the CS world.
Cloud-Integrated Smart Detection of Solar Panel Damage and Degradation
A. Senthilselvi, Chengalapattu Vivek Sai, Aditya Raghavendran, S B Jayakumar, Balika J Chelliah, N. Alangudi Balaji
2025 8th International Conference on Circuit Power and Computing Technologies Iccpct 2025, 2025
Correction to: HATDO: hybrid Archimedes Tasmanian devil optimization CNN for classifying offensive comments and non-offensive comments (Neural Computing and Applications, (2023), 35, 25, (18395-18415), 10.1007/s00521-023-08657-z)
B. Aarthi, Balika J. Chelliah
Neural Computing and Applications, 2024
BO-LCNN: butterfly optimization based lightweight convolutional neural network for remote data integrity auditing and data sanitizing model
B. Judy Flavia, Balika J. Chelliah
Telecommunication Systems, 2024
Early Prediction of Pancreatic Malignancy by using Deep Learning Techniques
Abirami S, Balika J Chelliah
2024 3rd International Conference on Electrical Electronics Information and Communication Technologies Iceeict 2024, 2024
Hierarchical blockchain-based secure data storage in cloud using Merkle tree approach
Judy Flavia Bruno, Balika J. Chelliah
International Journal of Cloud Computing, 2024
An Investigation into the Application of Chaotic Map Encryption for Image Transfer in an IoT Framework
Reenie Tanya, Balika J Chelliah
2024 IEEE 2nd International Conference on Emerging Trends in Engineering and Medical Sciences Icetems 2024, 2024
Enhancing PCOS Prediction Using Machine Learning and Explainable AI
Balika J Chelliah, Sarghi Kaur Gahra, A. Senthilselvi
2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology IC Sit 2024, 2024
DeepHealth : Deep Learning-Powered Smart App for Personalized Health Tracking
Balika J Chelliah, Raghavendra. G, Senthilselvi A
Iccds 2024 International Conference on Computing and Data Science, 2024
Analysis of demand forecasting of agriculture using machine learning algorithm
Balika J. Chelliah, T. P. Latchoumi, A. Senthilselvi
Environment Development and Sustainability, 2024
Smart Ports: Utilizing AI-Driven Predictive Analytics and Simulation for Operational Excellence
Balika J Chelliah, Sarghi Kaur Gahra, A. Senthilselvi, S.Senthil Pandi
2024 International Conference on Smart Technologies for Sustainable Development Goals Icstsdg 2024, 2024
Enhancing Dyslexia Awareness: A ML Model for Early Identification and Support
A. Senthilselvi, Aniket Kumar, S Aakash, G. Sreedhar, Balika J Chelliah
2024 International Conference on Communication Computing and Internet of Things Ic3iot 2024 Proceedings, 2024
Harnessing T5 Large Language Model for Enhanced PDF Text Comprehension and Q&A Generation
Balika J Chelliah, MB Hariharan, Abijith Prakash, Bharathwaj Manoharan, A. Senthilselvi
Iccds 2024 International Conference on Computing and Data Science, 2024
A Novel Approach to Handle Disaster with Twitter Reports by Deep Learning
Balika J Chelliah, A Santhoshika, B Kavya, S Bala Arbind, A Senthilselvi
2nd IEEE International Conference on Data Science and Information System Icdsis 2024, 2024
Emergency Activity Tracking: An Intelligent System for Monitoring Human Activity
Balika J Chelliah, V Ashwin Ram, Krishnan N, Navnit Krishna P, Senthilselvi Ayothi
Proceedings of the 2nd IEEE International Conference on Networking and Communications 2024 Icnwc 2024, 2024
Load-balancing in Cloud Computing Environment using Hybrid Particle Swarm Optimization and Ant Colony Optimization Algorithm
A. Senthilselvi, V S Varshini, E Reena Sharan, T Shruthi Shree, Balika J Chelliah, S Senthil Pandi
2024 2nd International Conference on Advances in Computation Communication and Information Technology Icaiccit 2024, 2024
Mobile-Friendly Plant Disease Detection and Classification using Metadata and Asymmetric Knowledge Distillation
Balika J Chelliah, S.Jasper Sofi, K S S SreeKrishna, Sai Vishaal, A Senthilselvi, S Senthil Pandi
2024 2nd International Conference on Advances in Computation Communication and Information Technology Icaiccit 2024, 2024
Prognosticating Pneumonia: A Comparative Analysis of Prediction Models Enhanced by and Devoid of Attention Mechanism
Balika J Chelliah, V Surya, Rohan Thomas Jepagnanam, P Taroon, A Senthilselvi, S Senthil Pandi
2024 2nd International Conference on Advances in Computation Communication and Information Technology Icaiccit 2024, 2024
A Novel Approach to Protect Environment by CO2 Emission Detection
Senthilselvi, Varun S, Akash Prabhu P, Vijeesh P.K, Balika J Chelliah, Senthil Pandi S
Iccds 2024 International Conference on Computing and Data Science, 2024
A Novel Approach to Interpret Multiclass Skin Disease Using Explainable AI
Balika J Chelliah, A Senthilselvi, R P Pranav, S Tilak, G Arunprasad, S.Senthil Pandi
2024 2nd International Conference on Advances in Computation Communication and Information Technology Icaiccit 2024, 2024
Artificial lizard search optimized fuzzy logic approach to addressing authentication and data security challenges in P2P cloud environments
Judy Flavia B, Balika J. Chelliah
Computers and Security, 2023
Hybrid Whale Archimedes Optimization–based MLPNN model for soil nutrient classification and pH prediction
Prabavathi Raman, Balika Joseph Chelliah
Environmental Science and Pollution Research, 2023
HATDO: hybrid Archimedes Tasmanian devil optimization CNN for classifying offensive comments and non-offensive comments
B. Aarthi, Balika J. Chelliah
Neural Computing and Applications, 2023
An intelligent approach using boosted support vector machine based arithmetic optimization algorithm for accurate detection of plant leaf disease
M. Prabu, Balika J. Chelliah
Pattern Analysis and Applications, 2023
Enhanced reptile search optimization with convolutional autoencoder for soil nutrient classification model
Prabavathi Raman, Balika J. Chelliah
Peerj, 2023
Develop Hybrid Wolf Optimization with Faster RCNN to Enhance Plant Disease Detection Performance Analysis
M. Prabu, Balika J. Chelliah
Lecture Notes on Data Engineering and Communications Technologies, 2023
An Optimized Hybrid Soil Texture Classification Model using Stacked Sparse Autoencoder
R Prabavathi, Balika J Chelliah
1st International Conference on Emerging Research in Computational Science Icercs 2023 Proceedings, 2023
Latent Dirichlet Allocation Model for plurilingual Language Opinion Classification in Social media
Aarthi B, Balika J Chelliah
2023 IEEE International Conference on Research Methodologies in Knowledge Management Artificial Intelligence and Telecommunication Engineering Rmkmate 2023, 2023
Fake News Classification from Online Social Network Comments using BILSTM Deep learning Model
Aarthi B, Balika J Chelliah
Proceedings of the 2023 2nd International Conference on Augmented Intelligence and Sustainable Systems Icaiss 2023, 2023
Adaptive and effective spatio-temporal modelling for offensive video classification using deep neural network
Balika J. Chelliah, K. Harshitha, Saharsh Pandey
International Journal of Intelligent Engineering Informatics, 2023
Similarity-based optimised and adaptive adversarial attack on image classification using neural network
Balika J. Chelliah, Mohammad Mustafa Malik, Ashwin Kumar, Nitin Singh, R. Regin
International Journal of Intelligent Engineering Informatics, 2023
A Comprehensive Review on Machine Learning Approaches for Yield Prediction Using Essential Soil Nutrients
R. Prabavathi, Balika J Chelliah
Universal Journal of Agricultural Research, 2022
Deep recurrent neural network-based Aquila optimization-based online shaming emotion analysis
B. Aarthi, Balika J. Chelliah
Concurrency and Computation Practice and Experience, 2022
Mango leaf disease identification and classification using a CNN architecture optimized by crossover-based levy flight distribution algorithm
M. Prabu, Balika J. Chelliah
Neural Computing and Applications, 2022
An Efficient Storage Solution for Healthcare Management Systems Using Cloud
Judy Flavia B, Balika J Chelliah
Proceedings of the 3rd International Conference on Smart Technologies in Computing Electrical and Electronics Icstcee 2022, 2022
An Optimized Gaussian Extreme Learning Machine (GELM) for Predicting the Crop Yield using Soil Factors
R. Prabavathi, Balika J Chelliah
Proceedings of the 2022 International Conference on Electronic Systems and Intelligent Computing Icesic 2022, 2022
A Comprehensive Study on Cybersecurity Challenges and Solutions in an IoT Framework
Reenie Tanya, Balika J. Chelliah
Towards A Wireless Connected World Achievements and New Technologies, 2022
A Collaborative and Early Detection of Email Spam using Multitask Learning
Balika J Chelliah, Anand Sasidharan, Dharmesh Kumar Singh, Nilesh Dangi
Ecs Transactions, 2022
Collaborative and early detection of email spam using multitask learning
Chelliah Balika J., Sasidharan Anand, Singh Dharmesh Kumar, Dangi Nilesh
International Journal of Performability Engineering, 2021
VESDNet: Deep Vessel Segmentation (U) Network for the Early Diagnosis of Diabetic Retinopathy
G. Kumaran, Balika J. Chelliah, S. Arun Kumar
Lecture Notes in Electrical Engineering, 2021
A Robust Statistical CNNCTC-Based AI Model for Tracking and Monitoring COVID-19
Balika J. Chelliah, S. Arunkumar, R. Prabavathi, B. Aarthi
Lecture Notes in Electrical Engineering, 2021
An Intelligent Stabilized Smart Sewage Treatment Plant (STP)
R. Prabavathi, J. Shiny Duela, Balika J Chelliah, S. Mohana Saranya, A. Sheela
Proceedings of the 2021 4th International Conference on Computing and Communications Technologies Iccct 2021, 2021
Node clone detection using a stable overlay network
Balika J. Chelliah, M. S. Antony Vigil, M. S. Bennet Praba
International Journal of Electrical and Computer Engineering, 2020
Service selection in service oriented architecture using probabilistic approach and asynchronous queues with interceptor validation
Balika J. Chelliah, K. Sathish, S. Arun Kumar
International Journal of Electrical and Computer Engineering, 2020
A unified framework for analysis of android vulnerability based on consent model
Dr. Balika J. Chelliah, Vishal K.S, Naresh Rengaswamy, Deepak O
Journal of Advanced Research in Dynamical and Control Systems, 2020
Text and data formatting for machine learning
Balika J Chelliah, Arth jain, Utkarsh Singh, Garima Mehta
International Journal of Innovative Technology and Exploring Engineering, 2019
Advancement of driverless cars and heavy vehicles using artificial intelligence (Object detection)
Balika J Chelliah, , Vishal Chauhan, Shivendra Mishra, Vivek Sharma, , , and
International Journal of Engineering and Advanced Technology, 2019
Experimental comparison of quantum and classical support vector machines
International Journal of Innovative Technology and Exploring Engineering, 2019
Computer vision framework for visual sharp object detection using deep learning model
International Journal of Engineering and Advanced Technology, 2019
Security implications in cyber physical systems
International Journal of Innovative Technology and Exploring Engineering, 2019
3D character generation using PCGML
International Journal of Innovative Technology and Exploring Engineering, 2019
Location-aware collaborative filtering for web service recommendations based on user and service history
Balika J Chelliah, , K. Vivekanandan, and
Journal of Engineering Science and Technology Review, 2017
Skyline based quality service selection through aggregated response matrix formulator
International Journal of Control Theory and Applications, 2016
Custom security in web services
Balika J. Chelliah, K. Vivekanandan, P. Jeni
Indian Journal of Science and Technology, 2016
Multi criteria decision making for n-dimensional vertical partitions
Prathipa Baskaran, Balika J. Chelliah
International Review on Computers and Software, 2015

Dr. Balika J chelliah

EDUCATION

RESEARCH INTERESTS

Scopus Publications