A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference Sadhana Selvakumar, B. Senthilkumar Scientific Reports, 2025 Medical image analysis using deep learning algorithms has become a basis of modern healthcare, enabling early detection, diagnosis, treatment planning, and disease monitoring. However, sharing sensitive raw medical data with third parties for analysis raises significant privacy concerns. This paper presents a privacy-preserving machine learning (PPML) framework using a Fully Connected Neural Network (FCNN) for secure medical image analysis using the MedMNIST dataset. The proposed PPML framework leverages a torus-based fully homomorphic encryption (TFHE) to ensure data privacy during inference, maintain patient confidentiality, and ensure compliance with privacy regulations. The FCNN model is trained in a plaintext environment for FHE compatibility using Quantization-Aware Training to optimize weights and activations. The quantized FCNN model is then validated under FHE constraints through simulation and compiled into an FHE-compatible circuit for encrypted inference on sensitive data. The proposed framework is evaluated on the MedMNIST datasets to assess its accuracy and inference time in both plaintext and encrypted environments. Experimental results reveal that the PPML framework achieves a prediction accuracy of 88.2% in the plaintext setting and 87.5% during encrypted inference, with an average inference time of 150 milliseconds per image. This shows that FCNN models paired with TFHE-based encryption achieve high prediction accuracy on MedMNIST datasets with minimal performance degradation compared to unencrypted inference.
An Effective Production, Distribution and Performance Analysis of Jeevamirtham towards the Smart Agronomy for Plants and Crops B. Senthilkumar, K. Sampathkumar, R. Gowrishankar Indian Journal of Agricultural Research, 2025 Background: Agriculture not only provides food for the living beings, it also maintains the environmental balance in the globe. Water management and manure supply management to the plants and crops is the important factors to be considered for healthy and heavy yielding. Manures plays major role in the effective agriculture process. Both non organic and organic manures are effectively utilized by the farmers now a day. By considering the soil, air, water and the entire environmental safety, feeding non organic manure has been slowed down by the formers and governments. Hence, the only chance remains are the traditional organic manure feeding for the effective growth and yielding. Many organic manure has been proposed and tested by many researchers for its effectiveness on all plants and crops. Among all the organic manures tested, one organic manure “Jeevamirtham” have provided best results in almost allplants and crops. Preparation and feeding of Jeevamirtham is a tedious and time consumingprocess and it needs high man power and water source. Hence, to handle this Jeevamirtham, the traditional method of manure feeding needs help from technology. Methods: To satisfy the needs of agriculture activities, a smart method of organic manure preparation and feeding has been proposed and tested in this work. This new method consists of automatic mixer, jeevamirtham producing tank, slurry pump and distribution setup. It is a semi-automated method which provides manure to individual plant and crop in equal volume. Result: This proposed method is capable of producing 3000 litres of Jeevamirtham in 72 hours of time and supplies almost equally to all plants and crops in the field. Further, this new method has achieved notable improvements in plant growth, yielding, disease resistance, draught resistance, 95% of fertility with longer life time in various soil environments. The PM also has an improvement of 2-4% in the yielding with comparatively small quantity of water, time and manpower requirement than all other existing methods.
Leveraging a hybrid whale-grey wolf optimisation algorithm to enhance fifth generation deployment efficiency in multi-access edge computing B. Senthilkumar, U. Barakkath Nisha, V. Kalpana, Priscilla Joy, S. Gokila International Journal of Grid and Utility Computing, 2025 In contemporary advanced manufacturing environments, deploying numerous intelligent mobile devices is crucial to meet the rising need for adaptable production capabilities. This research article focuses on addressing critical challenges in modern connected environments where intelligent mobile devices play a crucial role. These devices are equipped with a variety of sensors and constantly synchronise massive data sets. Furthermore, with the increasing importance of energy efficiency, current studies highlight energy use as a substantial expense. Nevertheless, previous research has mostly focused on analysing energy consumption in cloud servers, neglecting to include the energy usage associated with edge computing and underestimating the influence of various mobile devices. This becomes further crucial as interconnected settings increase. The research article presents an integer programming paradigm that addresses the difficulty of efficiently deploying MEC servers and fifth generation (5G) small cells. Given the NP-hard nature of edge server deployment, the research article proposes a novel Hybrid Whale-Grey Wolf Optimisation (HWGWO) algorithm. This metaheuristic algorithm combines the global exploration capabilities of WOA with the local search efficiency of GWO, thereby achieving a balanced and efficient search process.
An exploration of edge-based energy harvesting and routing strategies to enhance communication efficiency in IoT networks B. Senthilkumar, Prashant Bachanna, S. Chandragandhi, U. Barakkath Nisha, M. Sravani, S. Swathi, P. Penchala Prasanth, R. Yasir Abdullah International Journal of Grid and Utility Computing, 2025 This article explores the domain of Internet of Things (IoT) sensor networks, with a specific emphasis on improving sustainability and communication efficiency. Given the widespread use of interconnected devices, it is crucial to prioritise sustainable functioning and effective communication. Energy harvesting is becoming a promising approach for overcoming power limitations, allowing sensors to gather energy from their environment. Furthermore, routing algorithms have a crucial function in optimising communication efficiency inside these networks. The aim of this paper is to investigate various methods of harnessing energy and routing algorithms to discover novel approaches that promote sustainability and improve communication performance in IoT sensor networks. This study aims to offer significant insights and recommendations for creating resilient and environmentally friendly IoT solutions through a thorough analysis. The study assesses a range of energy acquisition techniques, encompassing solar, kinetic, thermal and radio frequency acquisition. Every solution has distinct benefits and difficulties, requiring a detailed evaluation of their appropriateness for implementing IoT sensors in different situations. In addition, the examination includes the study of routing algorithms, which are crucial for ensuring efficient data transfer and network stability. The goal is to determine the most effective methods for improving communication performance while minimising energy use. This study aims to enhance the development of sustainable and resilient IoT sensor networks by combining knowledge from the areas of energy harvesting and routing.
Reinforcing blockchain security with advanced anomaly detection in edge computing using EDGESENTRY B. Senthilkumar, Prashant Bachanna, U. Barakkath Nisha, M. Sravani, S. Swathi, K. Srihari, Thrivikram Bathini, R. Yasir Abdullah International Journal of Grid and Utility Computing, 2025 Within the realm of distributed systems, the fusion of blockchain technology and edge computing has generated considerable attention, offering the potential for improved security and efficiency in decentralised applications. This article presents EDGESENTRY, an abbreviation for 'Enhanced Detection for Genuine Edge Security', a novel anomaly detection technique designed exclusively for blockchain-integrated edge computing settings. A comparison between EDGESENTRY and currently available anomaly detection algorithms developed for edge computing were conducted. This comparison focuses on highlighting the distinctive characteristics and performance benefits of EDGESENTRY. By conducting thorough experimentation and assessment, which includes comparing against the most advanced methodologies, the efficiency of EDGESENTRY in identifying and reducing irregularities in blockchain transactions that occur at the outer edges of the network was calculated. This research article emphasises the importance of EDGESENTRY in strengthening the security of blockchain in edge computing environments. Furthermore, the article examines the consequences for future investigation and advancement, including possible improvements to the algorithm and study of new uses in emerging fields. EDGESENTRY tackles the difficulties of identifying abnormal behaviour in decentralised systems, hence enabling the development of more secure and robust edge computing infrastructures at the time of blockchain advancements.
Hybrid energy harvesting by reverse di-electric on a piezo-electric generator with thermo-couple and monitoring in WSN J.R. Nishanth, B. Senthilkumar Automatika, 2024 Smart renewable energy harvesting has been implemented from hybrid sources such as solar and wind.The wireless sensor node is created for monitoring surface water.In the intelligent building, electrical energy is harvested from the hybrid source of solar and wind energy.The source energy was selected for the harvesting process by using a fuzzy controller.In this proposed method, piezo-electric reverse electro-wetting on di-electric energy harvesting is proposed where constant DC voltage is generated by a rectifier.A DC-DC converter is designed to power up the remote read-out sensor.The produced charge is transformed by a charge amplifier with the proportion of output voltage that is delivered to the wireless receiver.The harvested DC voltage varies with the temperature and external environmental effect.In our work, we obtained 6 10 -3 W/m 2 of voltage and this harvested energy is monitored using the Internet of Things (IoT) by the proposed EHOR (Energy Harvested Optimized Routing) algorithm.
Smart Electric Meter Using Lora R. Gowrishankar, B. Senthilkumar, N. Prakash, Visal prewin KS, Harshini S, Dhanalakshmi P Proceedings of the 2024 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2024, 2024 In the modern world of abundant mechanism, power(Electricity) is the most crucial term to deal with any digital system to function. Therefore, it is equally LoRa allows long-range communication with low power, making it ideal for remote energy monitoring. The smart meter tracks energy consumption and sends data via LoRa-WAN, enabling real-time access from anywhere. This helps users manage their energy use, avoid excess consumption, and reduce costs. The low-power nature of LoRa ensures the system works efficiently in areas without strong Wi-Fi or cellular signals. In the IoT applications, the communication range is the most crucial component, since most Wi-Fi based systems in the IoT require multiple By installing the required software on your gadget, you may access all of the collected data from any location using a PC, smartphone, or other device by installing the Gateway and sending it to the cloud server.
Automatic Vehicle Speed Control System R. Gowrishankar, B. Senthilkumar, N. Prakash, D. Balasubramaniyan, M. Dinesh Pandiyan, S.D. Sasidharan Proceedings of the 2024 International Conference on Innovative Computing Intelligent Communication and Smart Electrical Systems Icses 2024, 2024 The automatic vehicle speed control system (AVSCS) is a cutting-edge automotive innovation designed to enhance road safety and driving comfort. Integrating advanced sensor technology, AVSCS enables real-time monitoring of vehicle speed and distance from surrounding vehicles, automatically adjusting the throttle and brake to maintain a safe following distance. By leveraging intelligent algorithms and control mechanisms, [1] AVSCS optimizes driving efficiency and minimizes the risk of collisions, contributing significantly to accident prevention and overall road safety. This project aims to explore the potential of AVSCS in revolutionizing modern transportation, providing a foundation for the development of future intelligent driving systems.
An Effective Production, Distribution and Performance Analysis of Jeevamirtham towards the Smart Agronomy for Plants and Crops. B Senthilkumar, K Sampathkumar, R Gowrishankar Indian Journal of Agricultural Research 59 (9) , 2025 2025
A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference: S. Selvakumar, S. B S Selvakumar, B Senthilkumar Scientific Reports 15 (1), 27880 , 2025 2025 Citations: 9
Fast and ultra-low energy subthreshold level shifter using split-gate buffer for low-power digital VLSI systems SA Sivakumar, B Senthilkumar, S Rajendran Analog Integrated Circuits and Signal Processing 123 (2), 31 , 2025 2025
Reinforcing blockchain security with advanced anomaly detection in edge computing using EDGESENTRY B Senthilkumar, P Bachanna, UB Nisha, M Sravani, S Swathi, K Srihari, ... International Journal of Grid and Utility Computing 16 (5-6), 527-539 , 2025 2025
Leveraging a hybrid whale-grey wolf optimisation algorithm to enhance fifth generation deployment efficiency in multi-access edge computing B Senthilkumar, UB Nisha, V Kalpana, P Joy, S Gokila International Journal of Grid and Utility Computing 16 (5-6), 451-460 , 2025 2025
An exploration of edge-based energy harvesting and routing strategies to enhance communication efficiency in IoT networks B Senthilkumar, P Bachanna, S Chandragandhi, UB Nisha, M Sravani, ... International Journal of Grid and Utility Computing 16 (5-6), 505-526 , 2025 2025
Automatic Vehicle Speed Control System R Gowrishankar, B Senthilkumar, N Prakash, D Balasubramaniyan, ... 2024 International Conference on Innovative Computing, Intelligent … , 2024 2024
Smart Electric Meter Using Lora R Gowrishankar, B Senthilkumar, N Prakash 2024 International Conference on Innovative Computing, Intelligent … , 2024 2024
Hybrid energy harvesting by reverse di-electric on a piezo-electric generator with thermo-couple and monitoring in WSN JR Nishanth, B Senthilkumar Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2024 2024 Citations: 5
SWARM INTELLIGENCE APPROACH FOR LOAD BALANCING IN DISTRIBUTED COMPUTING SYSTEMS USING FIREFLY ALGORITHM R Gowrishankar, B Senthilkumar, E Jananandhini, D Ramasamy ICTACT Journal on Soft Compufing 14 (4) , 2024 2024 Citations: 1
LEVERAGING A HYBRID WHALE-GREY WOLF OPTIMISATION ALGORITHM TO ENHANCE FIFTH GENERATION DEPLOYMENT EFFICIENCY IN MULTI-ACCESS EDGE COMPUTING V KALPANA, P JOY, B SENTHILKUMAR, NU BARAKKATH, S GOKILA INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING 1 (1) , 2024 2024
REINFORCING BLOCKCHAIN SECURITY WITH ADVANCED ANOMALY DETECTION IN EDGE COMPUTING USING EDGESENTRY P BACHANNA, B SENTHILKUMAR, NU BARAKKATH, M SRAVANI, ... INTERNATIONAL JOURNAL OF GRID AND UTILITY COMPUTING 1 (1) , 2024 2024
Analysis and Design of Low Area and Highly Energy Efficient Hybrid Adder for Signal Processing Applications R Gowrishankar, B Senthilkumar 2022 Smart Technologies, Communication and Robotics (STCR), 1-4 , 2022 2022
Fast and Ultra-Low Energy Subthreshold Level Shifter using Split-gate Buffer for Low-power Digital VLSI Systems S SA, B Senthilkumar, S Rajendran 2022 Citations: 1
Design of Efficient Serial Divider Using HAN CARLSON Adder RG Dr.B.Senthilkumar International Journal of Innovative Science and Research Technology 3 (11 … , 2018 2018
Application of 6:2 Compressor in the Design of Multiplier DSKN Arthi R, Dr Senthilkumar B, Gowrishankar R, Tamilselvan S International Journal of Scientific Engineering and Research (IJSER) 6 (11 … , 2018 2018
Combination of noise removal and contrast enhancement methods for the preprocessing of mammogram images-towards the detection of breast cancer B Senthilkumar, R Gowrishankar, M Vaishnavi, S Gokila Bioscience Journal 33 (6), 1653-1658 , 2017 2017 Citations: 3
Fast Digital Curvelet Transform Based Denoising in Combination with a New Segmentation for Breast Cancer Detection B Senthilkumar, R Gowrishankar, M Vaishnavi, S Gokila BIOMEDICINE 36 (4), 57-60 , 2016 2016
VLSI IMPLEMENTATION OF NOVEL ROUND KEYS GENERATION SCHEME FOR CRYPTOGRAPHY APPLICATIONS BY ERROR CONTROL ALGORITHM B Senthilkumar, V Rajamani Journal of Engineering Science and Technology 10 (5), 667-679 , 2015 2015
A NOVEL VLSI BASED CRYPTOCODING TECHNIQUE USING ERROR CONTROL ALGORITHM. B SENTHILKUMAR, V RAJAMANI Journal of Theoretical & Applied Information Technology 74 (1) , 2015 2015
MOST CITED SCHOLAR PUBLICATIONS
A novel region growing segmentation algorithm for the detection of breast cancer B Senthilkumar, G Umamaheswari, J Karthik 2010 IEEE International Conference on Computational Intelligence and … , 2010 2010.0 Citations: 56
Combination of novel enhancement technique and fuzzy c-means clustering technique in breast cancer detection B Senthilkumar, G Umamaheswari Biomedical Research 24 (2), 252-256 , 2013 2013.0 Citations: 15
A novel edge detection algorithm for the detection of breast cancer B Senthilkumar, G Umamaheswari European Journal of Scientific Research 53 (1), 51-55 , 2011 2011.0 Citations: 13
Breast cancer detection using combined curvelet based enhancement and a novel segmentation methods B Senthilkumar, G Umamaheswari Biomed Pap Med Fac Univ Palacky Olomouc Czech Repub 159 (1), 83-86 , 2015 2015.0 Citations: 11
A privacy preserving machine learning framework for medical image analysis using quantized fully connected neural networks with TFHE based inference: S. Selvakumar, S. B S Selvakumar, B Senthilkumar Scientific Reports 15 (1), 27880 , 2025 2025.0 Citations: 9
A review on computer aided detection and diagnosis-towards the treatment of breast cancer B Senthilkumar, G Umamaheshwari Eur. J. Sci. Res 52 (4), 437-452 , 2011 2011.0 Citations: 7
Hybrid energy harvesting by reverse di-electric on a piezo-electric generator with thermo-couple and monitoring in WSN JR Nishanth, B Senthilkumar Automatika: časopis za automatiku, mjerenje, elektroniku, računarstvo i … , 2024 2024.0 Citations: 5
A Fuzzy Approach for Representative Node Selection in Cross Layer TCP A Chandrasekar, S Arumugam, S Meenatchi, C Navaneethan, ... Journal of Theoretical and Applied Information Technology 64 (1), 1-15 , 2014 2014.0 Citations: 4
Combination of noise removal and contrast enhancement methods for the preprocessing of mammogram images-towards the detection of breast cancer B Senthilkumar, R Gowrishankar, M Vaishnavi, S Gokila Bioscience Journal 33 (6), 1653-1658 , 2017 2017.0 Citations: 3
VLSI IMPLEMENTATION OF KEY DEPENDENT SUBSTITUTION BOX USING ERROR CONTROL ALGORITHM FOR SUBSTITUTION-PERMUTATION SUPPORTED CRYPTOGRAPHY. B Senthilkumar, V Rajamani Journal of Theoretical & Applied Information Technology 64 (1) , 2014 2014.0 Citations: 3
NOVEL PREPROCESSING TECHNIQUE IN THE COMPUTER AIDED DETECTION OF BREAST CANCER S Balasubramaniam, U Govindaswamy 2015.0 Citations: 2
Improved noise removal algorithm implementation in FPGA for the breast cancer detection B Senthilkumar, G Umamaheswari 2012 IEEE International Conference on Computational Intelligence and … , 2012 2012.0 Citations: 2
SWARM INTELLIGENCE APPROACH FOR LOAD BALANCING IN DISTRIBUTED COMPUTING SYSTEMS USING FIREFLY ALGORITHM R Gowrishankar, B Senthilkumar, E Jananandhini, D Ramasamy ICTACT Journal on Soft Compufing 14 (4) , 2024 2024.0 Citations: 1
Fast and Ultra-Low Energy Subthreshold Level Shifter using Split-gate Buffer for Low-power Digital VLSI Systems S SA, B Senthilkumar, S Rajendran 2022.0 Citations: 1
IMPLEMENTATION OF MODIFIED SELECTIVE MEDIAN FILTER IN FPGA–TOWARDS THE DETECTION OF BREAST CANCER B Senthilkumar, G Umamaheswari Citations: 1
An Effective Production, Distribution and Performance Analysis of Jeevamirtham towards the Smart Agronomy for Plants and Crops. B Senthilkumar, K Sampathkumar, R Gowrishankar Indian Journal of Agricultural Research 59 (9) , 2025 2025.0
Fast and ultra-low energy subthreshold level shifter using split-gate buffer for low-power digital VLSI systems SA Sivakumar, B Senthilkumar, S Rajendran Analog Integrated Circuits and Signal Processing 123 (2), 31 , 2025 2025.0
Reinforcing blockchain security with advanced anomaly detection in edge computing using EDGESENTRY B Senthilkumar, P Bachanna, UB Nisha, M Sravani, S Swathi, K Srihari, ... International Journal of Grid and Utility Computing 16 (5-6), 527-539 , 2025 2025.0
Leveraging a hybrid whale-grey wolf optimisation algorithm to enhance fifth generation deployment efficiency in multi-access edge computing B Senthilkumar, UB Nisha, V Kalpana, P Joy, S Gokila International Journal of Grid and Utility Computing 16 (5-6), 451-460 , 2025 2025.0
An exploration of edge-based energy harvesting and routing strategies to enhance communication efficiency in IoT networks B Senthilkumar, P Bachanna, S Chandragandhi, UB Nisha, M Sravani, ... International Journal of Grid and Utility Computing 16 (5-6), 505-526 , 2025 2025.0