Kamruddin Nur
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Kamruddin Nur has a total of 128 co-authors. Here are the top co-authors by number of shared publications:
- Muhammad Firoz Mridha
Department of Computer Science and Engineering, American International University-Bangladesh, Dhaka, Bangladesh
5 shared publications - Rafael Pous
Department of Information and Communication Technologies Engineering, Pompeu Fabra University, 08018 Barcelona, Spain
5 shared publications - Rifat Al Mamun Rudro
Department of Computer Science, American International University-Bangladesh, Dhaka, Bangladesh
4 shared publications Anna Carreras
Universtiat Pompeu Fabra, Barcelona
3 shared publications- Debasish Ghose
Kristiania University of Applied Sciences, Bergen, Norway
3 shared publications M. F. Mridha
Department of Computer Science, American International University-Bangladesh (AIUB), Dhaka, Bangladesh
3 shared publications
Latest Publications
- 2 October 2026
- Published by IGI Global Scientific Publishing
- p. 1-44
A Comprehensive Study on the Real-Time and Ethical Perspective of Integrating GeoAI for Multi-Hazard Disaster Risk Monitoring
This chapter by the authors introduces a practice oriented framework to the application of Geospatial Artificial Intelligence (GeoAI) to disaster risk intelligence and monitoring along the disaster management continuum. It explores the use of remote sensing, IoT and edge computing, machine learning, multi-hazard ensemble modelling, natural language processing and federated learning in hazard detection, vulnerability assessment, emergency communication and distributed decision support. Uncertainty, explainability, spatial fairness, privacy, and ethical governance are essential system requirements that are covered in the chapter. A GeoAI framework and implementation roadmap of eight layers is depicted that links multi-source data, predictive models, real-time monitoring, privacy-preserving collaboration, fairness auditing, and operational dashboards. Case studies from around the world demonstrate practical use cases, and future trends encompass digital twins, geospatial foundation models, compound-hazard intelligence, edge AI, and responsible deployment.
- 2 October 2026
- Published by IGI Global Scientific Publishing
- p. 1-44
A Comprehensive Study on the Real-Time and Ethical Perspective of Integrating GeoAI for Multi-Hazard Disaster Risk Monitoring
This chapter by the authors introduces a practice oriented framework to the application of Geospatial Artificial Intelligence (GeoAI) to disaster risk intelligence and monitoring along the disaster management continuum. It explores the use of remote sensing, IoT and edge computing, machine learning, multi-hazard ensemble modelling, natural language processing and federated learning in hazard detection, vulnerability assessment, emergency communication and distributed decision support. Uncertainty, explainability, spatial fairness, privacy, and ethical governance are essential system requirements that are covered in the chapter. A GeoAI framework and implementation roadmap of eight layers is depicted that links multi-source data, predictive models, real-time monitoring, privacy-preserving collaboration, fairness auditing, and operational dashboards. Case studies from around the world demonstrate practical use cases, and future trends encompass digital twins, geospatial foundation models, compound-hazard intelligence, edge AI, and responsible deployment.
- 28 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
SIREX-Net: A two-stage fusion framework using UNet and RRDB for satellite image restoration with explainable AI
- 28 August 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 333
SIREX-Net: A two-stage fusion framework using UNet and RRDB for satellite image restoration with explainable AI
- Open Access
- 13 June 2026
- Published by Elsevier in Systems and Soft Computing
- Vol. 9
HCF-Net: Hierarchical and conflict-aware fusion for robust multimodal sentiment understanding
- 13 June 2026
- Published by Elsevier in Systems and Soft Computing
- Vol. 9
Open AccessHCF-Net: Hierarchical and conflict-aware fusion for robust multimodal sentiment understanding
- Open Access
- 10 April 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (4) , e0343669
Privacy-preserving multimodal federated learning pipeline for cyber-resilient healthcare systems
The integration of Internet of Things (IoT) devices and electronic medical records (EMRs) has transformed healthcare delivery but has also created new vulnerabilities to cyberattacks that threaten both data confidentiality and patient safety. Conventional centralized machine learning approaches for intrusion detection are impractical in this domain due to strict privacy regulations, heterogeneous data sources, and the risk of single points of failure. To address these challenges, we propose a secure distributed machine learning pipeline for cyber-resilient healthcare systems. The framework combines federated optimization with split learning for sensitive EMR data, robust aggregation to mitigate poisoned updates, and differential privacy with secure aggregation to protect against inference attacks. Multimodal fusion is enabled through temporal consistency regularization for IoT traffic and cross-layer contrastive alignment to link EMR representations, ensuring improved anomaly detection across diverse healthcare environments. Experiments conducted on representative IoT and EMR datasets demonstrate that the proposed pipeline achieves accuracy of 0.942 on IoT data, 0.931 on EMR data, and 0.953 in the combined setting, with corresponding F1-scores of 0.921, 0.908, and 0.932. Ranking metrics further confirm superiority with AUROC up to 0.961 and AUPRC up to 0.947, outperforming deep baselines by margins of +0.025 to +0.033. Robustness analysis shows graceful degradation under client poisoning ( 0.953 → 0.879 at 30% malicious clients) and resilience under severe communication constraints (accuracy 0.953 → 0.861 at 90% update sparsification). Detection latency is reduced to an average of 5.9 time steps, compared to 7.8 for the strongest deep baseline. These results highlight that secure distributed pipelines can deliver both strong detection capabilities and regulatory compliance, providing a practical path toward safeguarding next-generation healthcare infrastructures against evolving cyber threats.
- 10 April 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (4) , e0343669
Open AccessPrivacy-preserving multimodal federated learning pipeline for cyber-resilient healthcare systems
The integration of Internet of Things (IoT) devices and electronic medical records (EMRs) has transformed healthcare delivery but has also created new vulnerabilities to cyberattacks that threaten both data confidentiality and patient safety. Conventional centralized machine learning approaches for intrusion detection are impractical in this domain due to strict privacy regulations, heterogeneous data sources, and the risk of single points of failure. To address these challenges, we propose a secure distributed machine learning pipeline for cyber-resilient healthcare systems. The framework combines federated optimization with split learning for sensitive EMR data, robust aggregation to mitigate poisoned updates, and differential privacy with secure aggregation to protect against inference attacks. Multimodal fusion is enabled through temporal consistency regularization for IoT traffic and cross-layer contrastive alignment to link EMR representations, ensuring improved anomaly detection across diverse healthcare environments. Experiments conducted on representative IoT and EMR datasets demonstrate that the proposed pipeline achieves accuracy of 0.942 on IoT data, 0.931 on EMR data, and 0.953 in the combined setting, with corresponding F1-scores of 0.921, 0.908, and 0.932. Ranking metrics further confirm superiority with AUROC up to 0.961 and AUPRC up to 0.947, outperforming deep baselines by margins of +0.025 to +0.033. Robustness analysis shows graceful degradation under client poisoning ( 0.953 → 0.879 at 30% malicious clients) and resilience under severe communication constraints (accuracy 0.953 → 0.861 at 90% update sparsification). Detection latency is reduced to an average of 5.9 time steps, compared to 7.8 for the strongest deep baseline. These results highlight that secure distributed pipelines can deliver both strong detection capabilities and regulatory compliance, providing a practical path toward safeguarding next-generation healthcare infrastructures against evolving cyber threats.
- Open Access
- 4 March 2026
- Published by Springer Nature in International Journal of Information Security
- Vol. 25 (2) , 65
A systematic review on privacy preservation in federated learning
- 4 March 2026
- Published by Springer Nature in International Journal of Information Security
- Vol. 25 (2) , 65
Open AccessA systematic review on privacy preservation in federated learning
- Open Access
- 2 February 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (2) , e0339239
Physics-informed self-supervised diagnosis of rotating machinery using latent ODEs and transformer encoders
This paper proposes a novel Physics-Informed Self-Supervised Diagnosis (PI-SSD) framework for rotating machinery fault detection, combining physical modeling, self-supervised representation learning, and uncertainty-aware classification. The architecture integrates a multi-resolution convolutional encoder, a windowed Transformer for temporal context modeling, and a latent neural ordinary differential equation (ODE) module that embeds mechanical priors, such as Jeffcott rotor dynamics, directly into the learning process. A masked segment reconstruction objective enables self-supervised pretraining using unlabeled healthy signals, while an evidential classifier head produces fault probabilities with calibrated uncertainty. We evaluate PI-SSD on two publicly available datasets, the NASA PHM’09 Gearbox dataset and the Aalto Rotor dataset, covering 6 fault types and over 5,500 multichannel vibration recordings. Compared to seven strong baselines, PI-SSD achieves the highest Macro-F1 score (0.91) and lowest Expected Calibration Error (ECE = 0.022) on the NASA dataset, while maintaining strong domain transfer performance on Aalto (Macro-F1 = 0.81, PR-MSE = 0.067) without fine-tuning. Ablation studies confirm the contribution of each component, and physics consistency analysis demonstrates low violation rates under varying speeds. These results highlight the potential of embedding physics knowledge into self-supervised neural systems for robust, interpretable, and transferable fault diagnosis in industrial applications.
- 2 February 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (2) , e0339239
Open AccessPhysics-informed self-supervised diagnosis of rotating machinery using latent ODEs and transformer encoders
This paper proposes a novel Physics-Informed Self-Supervised Diagnosis (PI-SSD) framework for rotating machinery fault detection, combining physical modeling, self-supervised representation learning, and uncertainty-aware classification. The architecture integrates a multi-resolution convolutional encoder, a windowed Transformer for temporal context modeling, and a latent neural ordinary differential equation (ODE) module that embeds mechanical priors, such as Jeffcott rotor dynamics, directly into the learning process. A masked segment reconstruction objective enables self-supervised pretraining using unlabeled healthy signals, while an evidential classifier head produces fault probabilities with calibrated uncertainty. We evaluate PI-SSD on two publicly available datasets, the NASA PHM’09 Gearbox dataset and the Aalto Rotor dataset, covering 6 fault types and over 5,500 multichannel vibration recordings. Compared to seven strong baselines, PI-SSD achieves the highest Macro-F1 score (0.91) and lowest Expected Calibration Error (ECE = 0.022) on the NASA dataset, while maintaining strong domain transfer performance on Aalto (Macro-F1 = 0.81, PR-MSE = 0.067) without fine-tuning. Ablation studies confirm the contribution of each component, and physics consistency analysis demonstrates low violation rates under varying speeds. These results highlight the potential of embedding physics knowledge into self-supervised neural systems for robust, interpretable, and transferable fault diagnosis in industrial applications.
- 12 January 2026
- Published by Elsevier in Renewable Energy
- Vol. 261
SPFNet2: A lightweight solar panel fault detection framework using parallel U-Net and MobileNetV3Large
- 12 January 2026
- Published by Elsevier in Renewable Energy
- Vol. 261
SPFNet2: A lightweight solar panel fault detection framework using parallel U-Net and MobileNetV3Large
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Data Descriptions
- Vol. 3, 553-562
Descriptor: RGB Video of Natural Hand Gestures Dataset (RGB-NHG)
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Data Descriptions
- Vol. 3, 553-562
Open AccessDescriptor: RGB Video of Natural Hand Gestures Dataset (RGB-NHG)
- 2 December 2025
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 21 (1) , 36
DeepBERT-XAI: a dual BERT approach with XAI for sentiment analysis of airline tweet data
- 2 December 2025
- Published by Springer Nature in International Journal of Data Science and Analytics
- Vol. 21 (1) , 36
DeepBERT-XAI: a dual BERT approach with XAI for sentiment analysis of airline tweet data