T.B Sivakumar

@veltech.edu.in

Associate Professor and CSE Department
VEL TECH RANGARAJAN DR.SAGUNTHALA R&D INSTITUTE OF SCIENCE AND TECHNOLOGY, CHENNAI - 600 062,TAMILNADU

T.B Sivakumar


                  Download Compact PDF  
https://researchid.co/sivatb79

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Computer Science Applications
25

Scopus Publications

Scopus Publications

  • Quantum Key Distribution (QKD) Enabled Secure Model Update Exchange in Federated Learning
    Venkadeshan Ramalingam, Basant Kumar, Jagadeesan S, Vetriselvi T, Sivakumar T
    International Research Journal of Multidisciplinary Technovation, 2026
    Federated Learning (FL) allows the model to be trained cooperatively and retain the locality of data, but the exchange of model updates between dispersed clients and a central server can be compromised and manipulated. In this paper, a secure communication system of federated learning integrating quantum key distribution with the use of the BB84 protocol to enhance the establishment of secure keys is introduced. The suggested structure will achieve the use of QKD-generated symmetric keys along with classical cryptography tools to secure the privacy and integrity of model update messages. Federated learning communication and key generation, authentication, and encryption overheads are modeled at a system-level by developing a simulation environment. Parameters introduced to the simulation include the model update size, the number of clients, the communication latency and the cost of key refresh, which allows a more detailed examination of the system performance and feasibility. The findings show that the introduction of QKD is associated with limited and deterministic overhead on the communication latency and key management, and no convergence of the learning process is lost. This paper will concentrate on communication-layer security and will not consider the learning-layer threats e.g., adversarial model poisoning or client malicious behavior. These results show that quantum-secured key exchange can be integrated into federated learning systems and emphasize that it is a key enabling technology of secure communication in distributed learning systems in the future.
  • Hybrid CNN-LSTM Architecture for Personalized Disease Progression Prediction from Longitudinal EHR Data
    Sudha M, Aishwarya Shekhar, Anil, Nausherwan Raunaque, T.B Sivakumar, Manu Y M
    2026 2nd International Conference on Computing for Sustainability and Intelligent Future Comp Sif 2026, 2026
  • Predicting Lung Disease Progression Using Deep Learning on Pulmonary Function Test Data
    G. Revathy, C. Sudha, T. B. Sivakumar, E. Angel Anna Prathiba
    Applied Neural Networks in the AI Era from Theory to Real World Impact, 2025
    Indeed, asthma, chronic obstructive pulmonary disease (COPD), and pulmonary fibrosis are major health issues among people worldwide. Early diagnosis and accurate predictions of illness progression are essential for their management and treatment. Pulmonary Function Tests (PFTs) are valuable physiological tests reflecting lung function and disease severity changes over time. In this article, we show a deep learning approach to predict developments in lung diseases by PFT data. Our model is based on temporal patterns and characteristics from PFT readings that enable early diagnosis and prognosis for lung diseases. Unfortunately, due to a specific PFT dataset, collecting representative data for model training is always a challenge. Meanwhile, we address various sources of access to PFT datasets from public repositories through partnerships with healthcare institutions or data-sharing platforms. Once sufficient data is collected, we plan to perform preprocessing, develop deep learning models, and evaluate their effectiveness regarding lung disease development prediction.
  • Internet of Things and Cloud Computing-based Disease Diagnosis using Optimized Improved Generative Adversarial Network in Smart Healthcare System
    Thimmakkondu Babuji Sivakumar, Shahul Hameed Hasan Hussain, R. Balamanigandan
    Network Computation in Neural Systems, 2025
    The integration of IoT and cloud services enhances communication and quality of life, while predictive analytics powered by AI and deep learning enables proactive healthcare. Deep learning, a subset of machine learning, efficiently analyzes vast datasets, offering rapid disease prediction. Leveraging recurrent neural networks on electronic health records improves accuracy for timely intervention and preventative care. In this manuscript, Internet of Things and Cloud Computing-based Disease Diagnosis using Optimized Improved Generative Adversarial Network in Smart Healthcare System (IOT-CC-DD-OICAN-SHS) is proposed. Initially, an Internet of Things (IoT) device collects diabetes, chronic kidney disease, and heart disease data from patients via wearable devices and intelligent sensors and then saves the patient's large data in the cloud. These cloud data are pre-processed to turn them into a suitable format. The pre-processed dataset is sent into the Improved Generative Adversarial Network (IGAN), which reliably classifies the data as disease-free or diseased. Then, IGAN was optimized using the Flamingo Search optimization algorithm (FSOA). The proposed technique is implemented in Java using Cloud Sim and examined utilizing several performance metrics. The proposed method attains greater accuracy and specificity with lower execution time compared to existing methodologies, IoT-C-SHMS-HDP-DL, PPEDL-MDTC and CSO-CLSTM-DD-SHS respectively.
  • Optimizing the Quantum Circuit of Quantum SVM Using Hybrid Quantum Natural Gradient Descent(QNGD) and Quantum Butterfly Optimization Algorithm(QBOA)
    Raakesh Premkumar, T.B Sivakumar, L Maria Michael Visuwasam, G. Yuyaraj, Tharun Kumar C
    2025 International Conference on Information Implementation and Innovation in Technology I2itcon 2025, 2025
    This research endeavor is centered on the enhancement of the quantum circuit associated with the Quantum Support Vector Machine (QSVM), a fundamental algorithm within the realm of quantum machine learning, through the application of a hybrid optimization methodology that amalgamates Quantum Natural Gradient Descent (QNGD) with the Quantum Butterfly Optimization Algorithm (QBOA). The QSVM exploits quantum computational capabilities for proficient classification tasks within elevated-dimensional frameworks; however, its operational efficacy is frequently compromised by non-ideal quantum circuit parameters and the deleterious effects of noise present in near-term quantum computational devices. The suggested hybrid optimization technique augments the performance of QSVM by fusing the localized refinement capabilities of QNGD, which employs the Fisher Information Matrix for effective parameter adjustments, with the expansive exploration potential of QBOA, inspired by the foraging behaviors of butterflies. This collaborative approach yields accelerated convergence (38 iterations), enhanced classification accuracy (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 6. 8 \%}$</tex>), diminished circuit complexity (44 quantum gates), and increased resilience to noise (fidelity: <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{0. 9 8 5}$</tex>). In comparison to traditional optimization techniques such as Differential Evolution (DE), Grey Wolf Optimizer (GWO), and Firefly Algorithm (FA), the proposed framework exhibits markedly superior efficacy in the refinement of quantum kernel computations, entanglement strategies, and the overall depth of the circuit while concurrently alleviating the impacts of noise.
  • Remote Patient Monitoring System with Wearable IoT Devices and Biosensors for Vital Signs
    S. Naveen, T.B. Sivakumar, B. R. Supreeth, R. Niranjana, Vishwa Priya V, Saranya R
    3rd IEEE International Conference on Device Intelligence Computing and Communication Technologies Dicct 2025, 2025
    Due to infrequent patient monitoring and the reactive character of the traditional healthcare system, delayed diagnoses and inadequate management of chronic diseases are common outcomes. The study presents a solution to these drawbacks: a Remote Patient Monitoring (RPM) system that combines advanced biosensors with wearable IoT devices to track vital signs continuously. By ensuring proactive healthcare through real-time data collecting and analysis, the entire system overcomes the drawbacks of conventional techniques. Early anomaly detection and timely medical interventions are made possible by the method's utilization of scalable cloud infrastructure and advanced machine learning (ML) methods, such as CNNs (Convolutional Neural Networks) and Long Short-Term Memory (LSTMs). The proposed system achieves a 90% early detection rate, 95% sensitivity, 97% specificity in anomaly detection, and 92% patient satisfaction, which is a substantial improvement over existing techniques, according to the results. It also exhibits better vital sign measurement accuracy than existing systems, indicating its potential to completely transform patient care through better results and economical resource utilization.
  • Machine Learning Based Predicting for Consumer Purchasing Recommendations in Social Commerce Networks
    Samad Abdul, Mohammad Bdair, Anvesh Perada, Karamath Ateeq, Rajeswary Nair, T.B Sivakumar
    2025 International Conference on Computing Technologies and Data Communication Icctdc 2025, 2025
    Social commerce networks increased rapidly during recent years because internet purchasing merged with social media. These networks have transformed the complete process through which people find items and evaluate them alongside their purchase decisions. The process of forecasting consumer buying behavior across social networks proves difficult because it requires handling substantial amounts of information about social contacts and individual interests together with environmental factors. The investigation describes a thorough machine learning procedure to forecast social commerce network consumer purchasing behavior. The prediction of human behaviors and tastes relies on multiple machine learning strategies such as deep learning together with collaborative filtering along with content-based filtering. The accuracy of purchase predictions increases through evaluation of three key social influence elements across user content along with user relationships and peer reviews. A pair of distinctive features stand out as the main strengths and advantages of our innovative blend model implementation.
  • Privacy-Preserving IoT Analytics using Federated Learning and Decentralized AI at the Edge
    T.B Sivakumar, S. Lavanya, Y.M. Mahaboob John, Nageswaran M K, S. Kaliappan, et al.
    Icoicc 2025 3rd International Conference on Intelligent and Cloud Computing, 2025
    Advanced analytics solutions that address the privacy, latency, and efficiency issues present in traditional centralized systems are imperative due to the swift growth of IoT devices. Because their aggregate sensitive data and require longer data transfer times, existing approaches that rely on centralized data processing are set by serious privacy risks, high latency, and scalability issues. To get around these constraints, the article proposes a novel system that makes use of decentralized artificial intelligence at the edge and federated learning. Federated learning preserves privacy by sending only model updates, not raw data, whereas decentralized AI lowers latency by executing local real-time analytics. The proposed system showed significant improvements in data privacy as shown by a drop in data breaches from 15 to 4 and a drop-in data exposure rate to less than 10%. Latency reductions of up to 48% were achieved. The system's reliability in practical applications was further demonstrated by the improvement in computational efficiency that came with decreases in CPU, memory, and energy usage.
  • Optimized Fertilizer Dispensing for Sustainable Agriculture Through Secured IoT-Blockchain Framework IoT-Blockchain Framework for Sustainable Agriculture
    B. C. Preethi, G. Sugitha, T. B. Sivakumar
    International Journal of Advanced Computer Science and Applications, 2024
    — Precision farming is essential for optimizing resource use and improving crop yields to attain sustainable agriculture. However, challenges like data insecurity, fertilizer costs, and inadequate consideration of soil health pose a hindrance to achieving these goals. To overcome these issues, the proposed work presents a novel approach for optimizing fertilizer dispensing by developing a framework connecting IoT and blockchain with a community of greenhouses. The system consists of IoT sensors installed inside the greenhouses to measure soil pH and nutrient values. This collected sensor data is compressed and stored securely and in an off-chain manner by the IPFS (Inter-Planetary File System) hash using the Keccak-256. MetaMask transfers the data for blockchain registration and authentication. The data is then preprocessed using Z-score normalization, Label Encoding, and One-Hot Encoding to obtain a precise analysis. A Deep Learning-based Convolutional Neural Network (DL-CNN) is used to classify soil conditions and determine the appropriate fertilizer requirements. The results of the DL-CNN model are viewed in a dashboard through a Decentralized Application (D-App) that we developed to provide real-time information to consumers, field analysts, and agricultural organizations. Field analysts use the information to establish a control center for precisely applying fertilizers. The proposed method achieves a classification accuracy rate of 98.86%, thus increasing soil health and providing a solution for effectively managing fertilizers.
  • Data Glove-Based Hand Gesture Recognition for Improved Human-Computer Interaction
    Nanotechnology Perceptions, 2024
  • An optimization Method for Cloud Load Balancing using a Hybrid Oppositional Forgetting Learning (OFL) based Crow Search Algorithm and Fractional Dragonfly Algorithms (HOFL-CS-FDA)
    T.B Sivakumar, G. Yuvaraj, A. Shiny, A. Vinothini, K. Sachet, C. Tharun Kumar
    2024 Asian Conference on Intelligent Technologies Acoit 2024, 2024
  • Blockchain and Machine Learning for Security Attack Detection in Industrial IoT Networks
    Mahipal Singh Deora, Pramod Kumar, Kamatchi K, T.B Sivakumar, Sunetra Chatterjee, T. Maheshwaran
    Proceeding of 2024 International Conference on Communication Computing and Energy Efficient Technologies I3ceet 2024, 2024
  • Blockchain and Machine Learning Integration for Safe Data Sharing in Finance and HR
    T. B Sivakumar, E. Prathiba, Shweta Sharma, Rashmi Saket Prasad, M. S. Ramaratnam, V. Krishnamoorthy
    International Conference on Intelligent Algorithms for Computational Intelligence Systems Iacis 2024, 2024
  • Hybrid Spotted Hyena and Simulated Annealing Optimization Algorithm(HSHOSAA-1) for Efficient Task Scheduling in a Clustered Cloud Environment
    T. B Sivakumar, L. Maria Michael Visuvasam, V. Sangeetha, S. Bhuvana, K. Sathish Kumar, K. Sachet
    2024 3rd International Conference on Smart Technologies and Systems for Next Generation Computing Icstsn 2024, 2024
  • Machine Learning in Smart Cities: Survey of Wireless Sensor Network Applications
    Basavaraj G N, J. V. Rama Kumar, K. S. Jayareka, T.B Sivakumar, Raja Rajeswari Balaji, A. Backia Abinaya
    Proceeding of 2024 International Conference on Communication Computing and Energy Efficient Technologies I3ceet 2024, 2024
  • Turbocharged AI: Harnessing Federated Learning and Model Parallelism for Efficient Deep Learning on Distributed System
    Sheela Hundekari
    Communications on Applied Nonlinear Analysis, 2024
  • Enhanced Diabetes Prediction Using Deep Autoencoder Framework and Electronic Health Records
    T.B Sivakumar, Antara Malakar, Lekshmi S, G. Shailaja, E. Kalaivani, Dhananjaya Babu K
    2nd IEEE International Conference on Advances in Information Technology Icait 2024 Proceedings, 2024
  • Fuzzy Horizon: Unveiling the Fog of Uncertainty with Cognitive Cartography and Fuzzy Logic Fusion
    Kiran Sree Pokkuluri
    Communications on Applied Nonlinear Analysis, 2024
  • Harnessing Machine Learning for Metagenomics: Discovering the Invisible Microbial World
    S. Sabaria
    Communications on Applied Nonlinear Analysis, 2024
  • Advancing Precision Heart Disease Diagnosis for Proactive Healthcare Management using RF-IGE
    Zahraa M. Rashid, T.B Sivakumar, S K Rajesh Kanna, Minal Saxena, U Saritha, Malik Jawarneh
    Proceedings of the IEEE International Conference Image Information Processing, 2023
  • A novel approach to cryptography: Deep learning-based homomorphic secure searchable encryption for keyword searches in the blockchain healthcare system
    T. B. Sivakumar, Hasan Hussain
    Data Driven Blockchain Ecosystem Fundamentals Applications and Emerging Technologies, 2022
  • Cryptocurrency methodologies and techniques
    S. Hasan Hussain, T. B. Sivakumar, Alex Khang
    Data Driven Blockchain Ecosystem Fundamentals Applications and Emerging Technologies, 2022
  • QoS aware routing protocol using robust spatial gabriel graph based clustering scheme for ad hoc network
    George Sugitha, Thimmakkondu Babuji Sivakumar, Shahul Hameed Hasan Hussain
    Concurrency and Computation Practice and Experience, 2022
  • A secure mechanism for anonymous authentication in cloud computing
    International Journal of Applied Engineering Research, 2015
  • PHR in cloud environment using enhanced attribute based encryption and advanced encryption standard
    T.B. Sivakumar, S. Geetha
    Applied Mechanics and Materials, 2014