Sudipta Majumder
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sudipta Majumder has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
Rajesh Bose
7 shared publications- Haraprasad Mondal
Electronics and Communication Engineering, Dibrugarh University, Dibrugarh, India
3 shared publications Shrabani Sutradhar
3 shared publications- Abhijit Boruah
DUIET, Dibrugarh University
2 shared publications - Rabinder Kumar Prasad
Department of CSE, DUIET, Dibrugarh University, Dibrugarh, Assam, India
2 shared publications - Abdullah M. Albarrak
Department of Computer Science, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University, Riyadh 11432, Saudi Arabia
1 shared publication
Latest Publications
- 12 September 2026
- Published by Springer Nature in Network Modeling Analysis in Health Informatics and Bioinformatics
- Vol. 15 (1) , 198
A Statistically validated ensemble learning framework for diabetes prediction using clinical and metabolic features
- 12 September 2026
- Published by Springer Nature in Network Modeling Analysis in Health Informatics and Bioinformatics
- Vol. 15 (1) , 198
A Statistically validated ensemble learning framework for diabetes prediction using clinical and metabolic features
- Open Access
- 14 July 2026
- Published by Elsevier in Ain Shams Engineering Journal
- Vol. 17 (9)
Intelligent graph-blockchain healthcare storage with AI-Driven anomaly detection and distributed threshold security
- 14 July 2026
- Published by Elsevier in Ain Shams Engineering Journal
- Vol. 17 (9)
Open AccessIntelligent graph-blockchain healthcare storage with AI-Driven anomaly detection and distributed threshold security
- 16 February 2026
- Published by Springer Nature in OPSEARCH
- p. 1-30
An adaptive ACO-PPO framework for k-coverage optimization in sensor deployment for wireless sensor networks
- 16 February 2026
- Published by Springer Nature in OPSEARCH
- p. 1-30
An adaptive ACO-PPO framework for k-coverage optimization in sensor deployment for wireless sensor networks
- Open Access
- 29 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 1758-1779
M k -Means: Improving Partition-Based Clustering With Optimized Centroid Initialization
The k-means algorithm is a well-known technique in partition-based clustering, drawing plenty of attention by researchers over the years. It identifies distinct, non-overlapping patterns by assigning each data point to a specific cluster using a minimum squared distance approach. However, its’ effectiveness heavily depends on the selection of initial centroid values, which are chosen randomly. Despite numerous attempts by different researchers to address this limitation, there remains significant room for improvement in the effective initialization of centroids. Here, we introduce a modified k-means, that is,Mk-means method to precisely detect all clusters in a given dataset by utilizing as objective function referred to as the sum of squared errors. This method utilizes the partial sum of the squared errors of each cluster to improve cluster identification. The efficacy of the Mk-means method is evaluated using 15 synthetic benchmark datasets and 15 real-world benchmark datasets obtained from the UCI repository. Performance comparisons were conducted against several clustering algorithms, including the traditional k-means, FCM, k-means++, and more recent approaches such as IKMN, t-k-means, fast-t-k-means, fast-t-k-means++, and Global-k-means++. The results demonstrate that Mk-means outperforms these methods in terms of external validity indices- Adjusted Rand Index (ARI), Normalized Mutual Information (NMI), and Purity, as well as sum of squared error (SSE), an internal validity index. These findings highlight that Mk-means not only achieves more accurate clustering but also reduces within-cluster variance compared to its counterparts. The source code for the Mk-means algorithm is publicly available.
- 29 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 1758-1779
Open AccessM k -Means: Improving Partition-Based Clustering With Optimized Centroid Initialization
The k-means algorithm is a well-known technique in partition-based clustering, drawing plenty of attention by researchers over the years. It identifies distinct, non-overlapping patterns by assigning each data point to a specific cluster using a minimum squared distance approach. However, its’ effectiveness heavily depends on the selection of initial centroid values, which are chosen randomly. Despite numerous attempts by different researchers to address this limitation, there remains significant room for improvement in the effective initialization of centroids. Here, we introduce a modified k-means, that is,Mk-means method to precisely detect all clusters in a given dataset by utilizing as objective function referred to as the sum of squared errors. This method utilizes the partial sum of the squared errors of each cluster to improve cluster identification. The efficacy of the Mk-means method is evaluated using 15 synthetic benchmark datasets and 15 real-world benchmark datasets obtained from the UCI repository. Performance comparisons were conducted against several clustering algorithms, including the traditional k-means, FCM, k-means++, and more recent approaches such as IKMN, t-k-means, fast-t-k-means, fast-t-k-means++, and Global-k-means++. The results demonstrate that Mk-means outperforms these methods in terms of external validity indices- Adjusted Rand Index (ARI), Normalized Mutual Information (NMI), and Purity, as well as sum of squared error (SSE), an internal validity index. These findings highlight that Mk-means not only achieves more accurate clustering but also reduces within-cluster variance compared to its counterparts. The source code for the Mk-means algorithm is publicly available.
- Open Access
- 8 August 2025
- Published by MECS Publisher in International Journal of Information Engineering and Electronic Business
- Vol. 17 (4) , 26-40
A Scalable Blockchain Framework for Secure IoT Communication
The rapid proliferation of Internet of Things (IoT) devices has revealed weaknesses in its centralized communication architectures, rendering them vulnerable to security risks such as Distributed Denial of Service (DDoS) attacks. This scenario highlights the need for secure and efficient communication frameworks to safeguard IoT networks. In this paper, we present a blockchain-based framework designed to improve IoT communication networks' security, scalability, and performance. Our methodology utilizes decentralized architecture to mitigate risks linked to centralized sources of failure while enhancing performance metrics, including latency, throughput, energy consumption, and transaction success rates. We present an innovative approach that integrates a plateau effect in latency and consensus time, guaranteeing performance stability as the number of devices increases. The proposed model demonstrates decreases in latency by 26.57% and reductions in energy usage by 35.29% compared to existing Ethereum frameworks, based on extensive simulations conducted under diverse network conditions with one thousand devices, underscoring the framework's effectiveness in managing network congestion. This research offers a viable answer to the problems of IoT communication, facilitating future investigations into the optimization of blockchain integration for improving IoT security and efficiency.
- 8 August 2025
- Published by MECS Publisher in International Journal of Information Engineering and Electronic Business
- Vol. 17 (4) , 26-40
Open AccessA Scalable Blockchain Framework for Secure IoT Communication
The rapid proliferation of Internet of Things (IoT) devices has revealed weaknesses in its centralized communication architectures, rendering them vulnerable to security risks such as Distributed Denial of Service (DDoS) attacks. This scenario highlights the need for secure and efficient communication frameworks to safeguard IoT networks. In this paper, we present a blockchain-based framework designed to improve IoT communication networks' security, scalability, and performance. Our methodology utilizes decentralized architecture to mitigate risks linked to centralized sources of failure while enhancing performance metrics, including latency, throughput, energy consumption, and transaction success rates. We present an innovative approach that integrates a plateau effect in latency and consensus time, guaranteeing performance stability as the number of devices increases. The proposed model demonstrates decreases in latency by 26.57% and reductions in energy usage by 35.29% compared to existing Ethereum frameworks, based on extensive simulations conducted under diverse network conditions with one thousand devices, underscoring the framework's effectiveness in managing network congestion. This research offers a viable answer to the problems of IoT communication, facilitating future investigations into the optimization of blockchain integration for improving IoT security and efficiency.
- 23 December 2024
- Published by Springer Nature
- p. 25-38
Optimizing Task Offloading in Internet of Medical Things Systems: A Hybrid Fog-Cloud Approach with Actor-Critic Decision Making
- 23 December 2024
- Published by Springer Nature
- p. 25-38
Optimizing Task Offloading in Internet of Medical Things Systems: A Hybrid Fog-Cloud Approach with Actor-Critic Decision Making
- 17 December 2024
- Published by Springer Nature
- p. 89-105
Enhancing Healthcare Data Security with Homomorphic Encryption in Virtual Health Support
- 17 December 2024
- Published by Springer Nature
- p. 89-105
Enhancing Healthcare Data Security with Homomorphic Encryption in Virtual Health Support
- Open Access
- 15 May 2024
- Published by Frontiers Media SA in Frontiers in Water
- Vol. 6, 1401689
Modelling and prediction of aeration efficiency of the venturi aeration system using ANN-PSO and ANN-GA
The significance of this study involves the optimisation of the aeration efficiency (AE) of the venturi aerator using an artificial neural network (ANN) technique integrated with an optimisation algorithm, i.e., particle swarm optimisation (PSO) and genetic algorithm (GA). To optimise the effects of operational factors on aeration efficiency by utilising a venturi aeration system, aeration experiments were conducted in an experimental tank with dimensions of . The operating parameters of the venturi aerator include throat length (TL), effective outlet pipe (EOP), and flow rate (Q) to estimate the efficacy of the venturi aerator in terms of AE. A 3–6-1 ANN model was developed and integrated with the PSO and GA techniques to find out the best possible optimal operating variables of the venturi aerator. The coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) determined from the experimental and estimated data were used to assess and compare the performance of the ANN-PSO and ANN-GA modelling. It is shown that ANN-PSO provides a better result as compared to ANN-GA. The operational parameters, TL, EOP, and Q, were determined to have the most optimum values at 50 mm, 6 m, and 0.6 L/s, respectively. The optimised aeration efficiency of the venturi was found to be 0.105 kg O2/kWh at optimum operational circumstances. In fact, the neural network having an ideal design of (3-6-1) and a correlation coefficient value that is extremely close to unity has validated the results indicated above.- 15 May 2024
- Published by Frontiers Media SA in Frontiers in Water
- Vol. 6, 1401689
Open AccessModelling and prediction of aeration efficiency of the venturi aeration system using ANN-PSO and ANN-GA
The significance of this study involves the optimisation of the aeration efficiency (AE) of the venturi aerator using an artificial neural network (ANN) technique integrated with an optimisation algorithm, i.e., particle swarm optimisation (PSO) and genetic algorithm (GA). To optimise the effects of operational factors on aeration efficiency by utilising a venturi aeration system, aeration experiments were conducted in an experimental tank with dimensions of . The operating parameters of the venturi aerator include throat length (TL), effective outlet pipe (EOP), and flow rate (Q) to estimate the efficacy of the venturi aerator in terms of AE. A 3–6-1 ANN model was developed and integrated with the PSO and GA techniques to find out the best possible optimal operating variables of the venturi aerator. The coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) determined from the experimental and estimated data were used to assess and compare the performance of the ANN-PSO and ANN-GA modelling. It is shown that ANN-PSO provides a better result as compared to ANN-GA. The operational parameters, TL, EOP, and Q, were determined to have the most optimum values at 50 mm, 6 m, and 0.6 L/s, respectively. The optimised aeration efficiency of the venturi was found to be 0.105 kg O2/kWh at optimum operational circumstances. In fact, the neural network having an ideal design of (3-6-1) and a correlation coefficient value that is extremely close to unity has validated the results indicated above. - Open Access
- 12 February 2024
- Published by Elsevier in Decision Analytics Journal
- Vol. 10
A blockchain privacy-conserving framework for secure medical data transmission in the internet of medical things
- 12 February 2024
- Published by Elsevier in Decision Analytics Journal
- Vol. 10
Open AccessA blockchain privacy-conserving framework for secure medical data transmission in the internet of medical things