Sanjoy Mondal
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
Sanjoy Mondal has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Abhishek Das
Department of Computer Science and Engineering, Aliah University, Kolkata, India
4 shared publications Abhishek Das
Department of Computer Science and Engineering, Aliah University, Kolkata, India
2 shared publicationsSaurav Ghosh
A. K. Choudhury School of Information Technology, University of Calcutta, Kolkata, India
2 shared publicationsAnirban Mukherjee
Department of Computer Science and Engineering, University of Calcutta, Kolkata, India
1 shared publication- Indrakshi Ghosh
Amity Institute of Biotechnology, Amity University, Kolkata, India
1 shared publication Ipshita Chatterjee
1 shared publication
Latest Publications
- Open Access
- 28 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 156091-156106
Tackling Heterogeneity in Intelligent Internet of Medical Things Applications Through Federated Transformer Regularization
In the conventional Internet of Medical Things (IoMT) system, patient data shared by the IoMT devices are susceptible and confidential and can be exposed to the antagonist. Hence, federated learning (FL) has become a promising solution for preserving the privacy of patient data. However, various complex variances in the IoMT context, such as device and data heterogeneity, model complexities, and others, may degrade the performance of the traditional FL model. This paper proposes a transformer-based federated learning framework for the IoMT network within a cloud-edge architecture. The proposed framework mitigates data and device heterogeneity in the IoMT framework by learning the IoMT devices through a multi-head self-attention (MHSA) mechanism. The transformer model is applied to each device’s local data to capture the complex pattern from each input data. Each device uses the transformer model as a part of its local model to minimize the local loss function. To reduce the risk of over-fitting in the transformer model, a regularization term is instigated to the local loss function of the learning process. Furthermore, it is shown that the proposed method augmented with the regularization factor converges to a stationary point θ* with a convergence rate of O(1/t) in some situations. In addition, the proposed method provides ϵ-privacy guarantees on a local data set of IoMT devices. The proposed framework is investigated on the Human Activity Recognition (HAR), Physical Activity Monitoring (PAMAP2), and Physikalisch-Technische Bundesanstalt (PTB)-XL datasets. It measures the performance of the proposed methods compared to the state-of-the-art on various parameters.
- 28 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 156091-156106
Open AccessTackling Heterogeneity in Intelligent Internet of Medical Things Applications Through Federated Transformer Regularization
In the conventional Internet of Medical Things (IoMT) system, patient data shared by the IoMT devices are susceptible and confidential and can be exposed to the antagonist. Hence, federated learning (FL) has become a promising solution for preserving the privacy of patient data. However, various complex variances in the IoMT context, such as device and data heterogeneity, model complexities, and others, may degrade the performance of the traditional FL model. This paper proposes a transformer-based federated learning framework for the IoMT network within a cloud-edge architecture. The proposed framework mitigates data and device heterogeneity in the IoMT framework by learning the IoMT devices through a multi-head self-attention (MHSA) mechanism. The transformer model is applied to each device’s local data to capture the complex pattern from each input data. Each device uses the transformer model as a part of its local model to minimize the local loss function. To reduce the risk of over-fitting in the transformer model, a regularization term is instigated to the local loss function of the learning process. Furthermore, it is shown that the proposed method augmented with the regularization factor converges to a stationary point θ* with a convergence rate of O(1/t) in some situations. In addition, the proposed method provides ϵ-privacy guarantees on a local data set of IoMT devices. The proposed framework is investigated on the Human Activity Recognition (HAR), Physical Activity Monitoring (PAMAP2), and Physikalisch-Technische Bundesanstalt (PTB)-XL datasets. It measures the performance of the proposed methods compared to the state-of-the-art on various parameters.
- Open Access
- 30 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (3) , 8317-8334
Energy-Aware Privacy-Preserving IoMT Framework for Consumer Electronics: A Federated Learning Approach to Remote Healthcare
The Internet of Medical Things (IoMT) relies on Internet of Things (IoT) devices to collect and share sensitive patient data, which raises significant privacy and security concerns. As IoMT systems become increasingly integrated into the Consumer Electronics (CE) and Consumer Technologies (CT) landscape, safeguarding patient privacy is critical. To address these challenges, this paper proposes a Two-Stage Federated Transfer Learning (FTL)-based IoMT framework tailored for CE/CT applications. The proposed framework enables IoT devices to train locally on sensitive data while sharing only encrypted model updates with a central server, ensuring secure aggregation and data confidentiality. Differential privacy (DP) is incorporated into the learning process to enhance privacy further, providing rigorous guarantees against data reconstruction attacks while maintaining model utility. To improve model convergence and mitigate accuracy degradation during FTL, this paper also introduces an Adaptive Learning Rate (ALR) mechanism that dynamically adjusts learning rates at different stages of training, optimizing performance across heterogeneous IoMT devices. Moreover, the framework employs a Cloud-Edge layer to address energy constraint issues to IoT devices to facilitate efficient model update exchanges, reducing communication overhead and energy consumption. The Edge node aggregates model updates securely before transmitting them to the central server using a Secure Aggregation (SA) protocol, ensuring privacy throughout the aggregation process. Experimental results demonstrate that the proposed framework achieves prediction accuracies of 94.65% and 98.25%, outperforming state-of-the-art approaches while maintaining strong privacy guarantees and reducing energy consumption.
- 30 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 71 (3) , 8317-8334
Open AccessEnergy-Aware Privacy-Preserving IoMT Framework for Consumer Electronics: A Federated Learning Approach to Remote Healthcare
The Internet of Medical Things (IoMT) relies on Internet of Things (IoT) devices to collect and share sensitive patient data, which raises significant privacy and security concerns. As IoMT systems become increasingly integrated into the Consumer Electronics (CE) and Consumer Technologies (CT) landscape, safeguarding patient privacy is critical. To address these challenges, this paper proposes a Two-Stage Federated Transfer Learning (FTL)-based IoMT framework tailored for CE/CT applications. The proposed framework enables IoT devices to train locally on sensitive data while sharing only encrypted model updates with a central server, ensuring secure aggregation and data confidentiality. Differential privacy (DP) is incorporated into the learning process to enhance privacy further, providing rigorous guarantees against data reconstruction attacks while maintaining model utility. To improve model convergence and mitigate accuracy degradation during FTL, this paper also introduces an Adaptive Learning Rate (ALR) mechanism that dynamically adjusts learning rates at different stages of training, optimizing performance across heterogeneous IoMT devices. Moreover, the framework employs a Cloud-Edge layer to address energy constraint issues to IoT devices to facilitate efficient model update exchanges, reducing communication overhead and energy consumption. The Edge node aggregates model updates securely before transmitting them to the central server using a Secure Aggregation (SA) protocol, ensuring privacy throughout the aggregation process. Experimental results demonstrate that the proposed framework achieves prediction accuracies of 94.65% and 98.25%, outperforming state-of-the-art approaches while maintaining strong privacy guarantees and reducing energy consumption.
- Open Access
- 27 January 2025
- Published by Springer Nature in Cureus Journal of Computer Science
- Vol. 17 (1)
Traffic Congestion Prediction Using Machine Learning Algorithm
Traffic congestion poses a significant challenge in urban environments, leading to delays, increased fuel consumption, and heightened environmental pollution. Addressing this issue, our study presents an innovative dynamic traffic signal control system designed to adapt to real-time traffic conditions. Traditional traffic management systems typically rely on fixed schedules, which are inefficient when dealing with fluctuating traffic volumes. In contrast, our proposed system leverages advanced technologies to optimize traffic flow dynamically. At the core of the system are convolutional neural networks, which process video footage from CCTV cameras to accurately detect and count vehicles. This real-time data enables the system to dynamically adjust traffic signal timings, prioritizing lanes with heavier congestion and minimizing overall delays. By effectively responding to changing traffic patterns, the system reduces wait times and alleviates congestion, as validated through extensive simulations and experimental studies. The proposed approach is both cost-effective and scalable, making it particularly suitable for densely populated regions, such as urban centers in India. Additionally, the system capitalizes on existing infrastructure, providing a practical and efficient solution to urban traffic challenges. Future developments aim to integrate features like emergency vehicle detection and weather condition monitoring, further enhancing the system's responsiveness and optimizing urban traffic management.
- 27 January 2025
- Published by Springer Nature in Cureus Journal of Computer Science
- Vol. 17 (1)
Open AccessTraffic Congestion Prediction Using Machine Learning Algorithm
Traffic congestion poses a significant challenge in urban environments, leading to delays, increased fuel consumption, and heightened environmental pollution. Addressing this issue, our study presents an innovative dynamic traffic signal control system designed to adapt to real-time traffic conditions. Traditional traffic management systems typically rely on fixed schedules, which are inefficient when dealing with fluctuating traffic volumes. In contrast, our proposed system leverages advanced technologies to optimize traffic flow dynamically. At the core of the system are convolutional neural networks, which process video footage from CCTV cameras to accurately detect and count vehicles. This real-time data enables the system to dynamically adjust traffic signal timings, prioritizing lanes with heavier congestion and minimizing overall delays. By effectively responding to changing traffic patterns, the system reduces wait times and alleviates congestion, as validated through extensive simulations and experimental studies. The proposed approach is both cost-effective and scalable, making it particularly suitable for densely populated regions, such as urban centers in India. Additionally, the system capitalizes on existing infrastructure, providing a practical and efficient solution to urban traffic challenges. Future developments aim to integrate features like emergency vehicle detection and weather condition monitoring, further enhancing the system's responsiveness and optimizing urban traffic management.
- Open Access
- 26 September 2023
- Published by Qeios Ltd
Review of: "Optimized Low-Powered Wide Area Network within Internet of Things"
Congratulations for your paper. The topic suggested is of great value. However few comments can increase the value of the manuscript. * Rewrite the abstract precisely. Write your contribution and novelty point wise (if possible in bullet point)...
- 26 September 2023
- Published by Qeios Ltd
Open AccessReview of: "Optimized Low-Powered Wide Area Network within Internet of Things"
Congratulations for your paper. The topic suggested is of great value. However few comments can increase the value of the manuscript. * Rewrite the abstract precisely. Write your contribution and novelty point wise (if possible in bullet point)...
- 15 July 2023
- Published by Springer Nature in Microsystem Technologies
- Vol. 30 (4) , 391
Correction to: Quality aware cost efficient reward mechanism in mobile crowdsensing system with uncertainty constraints
- 15 July 2023
- Published by Springer Nature in Microsystem Technologies
- Vol. 30 (4) , 391
Correction to: Quality aware cost efficient reward mechanism in mobile crowdsensing system with uncertainty constraints
- 1 July 2023
- Published by Springer Nature in Microsystem Technologies
- Vol. 30 (4) , 381-390
Quality aware cost efficient reward mechanism in mobile crowdsensing system with uncertainty constraints
- 1 July 2023
- Published by Springer Nature in Microsystem Technologies
- Vol. 30 (4) , 381-390
Quality aware cost efficient reward mechanism in mobile crowdsensing system with uncertainty constraints
- 21 November 2022
- Published by Springer Nature in Microsystem Technologies
- Vol. 29 (4) , 539-551
Energy efficient and secure healthcare data transmission in the internet of medical things network
- 21 November 2022
- Published by Springer Nature in Microsystem Technologies
- Vol. 29 (4) , 539-551
Energy efficient and secure healthcare data transmission in the internet of medical things network
- 17 March 2022
- Published by Springer Nature in Microsystem Technologies
- Vol. 28 (12) , 2641-2657
Participant selection algorithms for large-scale mobile crowd sensing environment
- 17 March 2022
- Published by Springer Nature in Microsystem Technologies
- Vol. 28 (12) , 2641-2657
Participant selection algorithms for large-scale mobile crowd sensing environment
- 10 February 2022
- Published by Springer Nature in Microsystem Technologies
- Vol. 28 (12) , 2593-2610
Energy efficient algorithms for enhancing lifetime in wireless sensor networks
- 10 February 2022
- Published by Springer Nature in Microsystem Technologies
- Vol. 28 (12) , 2593-2610
Energy efficient algorithms for enhancing lifetime in wireless sensor networks
- 3 February 2022
- Published by Springer Nature in Transactions of the Indian National Academy of Engineering
- Vol. 7 (1) , 157-174
The Role of Emerging Technologies to Fight Against COVID-19 Pandemic: An Exploratory Review
Since the end of the year 2019, the whole world is experiencing a global emergency due to the COVID-19 pandemic. The major sectors including industry, economics, education have been affected. Ongoing pandemics confined us to avoid mass gathering and rigorously maintain social distancing to mitigate the spreading of this infectious disease. In this situation emerging technologies including the internet of things (IoT), Artificial Intelligence (AI) is playing a very important role in various fields such as healthcare, economics, educational system, and others to monitoring or tackle the impact of COVID-19 pandemic. Several papers discussed the impact of IoT on the COVID-19 pandemic in various aspects. However, the challenges and designing issues towards the implementation of IoT-based monitoring systems are not deeply investigated. Alongside, the adaptation of IoT and other technologies in the post-covid situation is not addressed properly. Our review article provides an up to date extensive survey on how IoT-enabled technologies are helping to combat the pandemic and to manage industry, education, economic, and medical system. As result, the realization is that IoT and other associated technologies have a great impact on virus detection, tracking, and mitigate the spread. In the face of an expeditiously spreading pandemic, the associated designing issues of the IoT-based framework have been looked into as a part of this review. Alongside, this review highlights the major challenges like privacy, security scalability, etc. facing in using such technologies. Finally, we explore ’The New Normal’ and the use of technologies to help in the post-pandemic era.
- 3 February 2022
- Published by Springer Nature in Transactions of the Indian National Academy of Engineering
- Vol. 7 (1) , 157-174
The Role of Emerging Technologies to Fight Against COVID-19 Pandemic: An Exploratory Review
Since the end of the year 2019, the whole world is experiencing a global emergency due to the COVID-19 pandemic. The major sectors including industry, economics, education have been affected. Ongoing pandemics confined us to avoid mass gathering and rigorously maintain social distancing to mitigate the spreading of this infectious disease. In this situation emerging technologies including the internet of things (IoT), Artificial Intelligence (AI) is playing a very important role in various fields such as healthcare, economics, educational system, and others to monitoring or tackle the impact of COVID-19 pandemic. Several papers discussed the impact of IoT on the COVID-19 pandemic in various aspects. However, the challenges and designing issues towards the implementation of IoT-based monitoring systems are not deeply investigated. Alongside, the adaptation of IoT and other technologies in the post-covid situation is not addressed properly. Our review article provides an up to date extensive survey on how IoT-enabled technologies are helping to combat the pandemic and to manage industry, education, economic, and medical system. As result, the realization is that IoT and other associated technologies have a great impact on virus detection, tracking, and mitigate the spread. In the face of an expeditiously spreading pandemic, the associated designing issues of the IoT-based framework have been looked into as a part of this review. Alongside, this review highlights the major challenges like privacy, security scalability, etc. facing in using such technologies. Finally, we explore ’The New Normal’ and the use of technologies to help in the post-pandemic era.