Harun Ur Rashid
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
Harun Ur Rashid has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Seong-Ho Jeong
Department of Information and Communications Engineering, Hankuk University of Foreign Studies (HUFS), Seoul, South Korea
3 shared publications - Turgay Ibrikci
Çukurova University
2 shared publications Aasim Ahmad
Kidney Centre Post Graduate Training Institute (Pakistan)
1 shared publication- Abate Selamawit Chane
Department of Information and Communications Engineering, Hankuk University of Foreign Studies (HUFS), Seoul, Korea
1 shared publication - Amit Bari
Department of Nephrology Kidney Foundation Hospital and Research Institute Dhaka Bangladesh
1 shared publication - Bebe Loff
Department of Epidemiology and Preventive Medicine, Monash University, Melbourne, Australia
1 shared publication
Latest Publications
- 26 August 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (8) , 543
Machine learning for 360° video streaming over 5G and B5G networks: emerging applications and challenges
- 26 August 2026
- Published by Springer Nature in Multimedia Systems
- Vol. 32 (8) , 543
Machine learning for 360° video streaming over 5G and B5G networks: emerging applications and challenges
- Open Access
- 30 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 53654-53666
Federated Few-Shot Prototypical Learning for Personalized WiFi-Based Human Activity Recognition
Wi-Fi channel state information (CSI) has emerged as a promising alternative to wearable sensors for passive human activity recognition (HAR). However, its sensitivity to environmental layouts and device heterogeneity leads to highly non-IID data across users. Also, combined with the limited number of labeled CSI samples available on each device, existing federated learning (FL) approaches often suffer from representation drift and poor convergence. To address these challenges, this paper introduces a federated few-shot learning framework that incorporates prototypical learning to promote consistent and discriminative CSI embeddings across clients. Each client extracts magnitude–phase statistical features, conducts episodic N-way K-shot training, and updates its local encoder using a prototypical loss. Unlike FedAvg, the server employs an Adam-based aggregation strategy that integrates prototype-induced parameter updates, providing more stable global alignment under heterogeneous data distributions. Experiments on a multi-configuration CSI dataset demonstrate that the proposed federated prototypical learning method significantly improves recognition accuracy, training stability, and cross-environment generalization compared with state-of-the-art FL baselines. These results highlight the potential of few-shot prototypical learning as a scalable and robust solution for CSI-based human activity recognition.
- 30 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 53654-53666
Open AccessFederated Few-Shot Prototypical Learning for Personalized WiFi-Based Human Activity Recognition
Wi-Fi channel state information (CSI) has emerged as a promising alternative to wearable sensors for passive human activity recognition (HAR). However, its sensitivity to environmental layouts and device heterogeneity leads to highly non-IID data across users. Also, combined with the limited number of labeled CSI samples available on each device, existing federated learning (FL) approaches often suffer from representation drift and poor convergence. To address these challenges, this paper introduces a federated few-shot learning framework that incorporates prototypical learning to promote consistent and discriminative CSI embeddings across clients. Each client extracts magnitude–phase statistical features, conducts episodic N-way K-shot training, and updates its local encoder using a prototypical loss. Unlike FedAvg, the server employs an Adam-based aggregation strategy that integrates prototype-induced parameter updates, providing more stable global alignment under heterogeneous data distributions. Experiments on a multi-configuration CSI dataset demonstrate that the proposed federated prototypical learning method significantly improves recognition accuracy, training stability, and cross-environment generalization compared with state-of-the-art FL baselines. These results highlight the potential of few-shot prototypical learning as a scalable and robust solution for CSI-based human activity recognition.
- 18 February 2026
- Published by Springer Nature in Journal of Network and Systems Management
- Vol. 34 (2) , 57
Position-Aided Channel Quality Indicator Prediction in V2X Scenarios using Attention-LSTM with Fully Convolutional Networks
- 18 February 2026
- Published by Springer Nature in Journal of Network and Systems Management
- Vol. 34 (2) , 57
Position-Aided Channel Quality Indicator Prediction in V2X Scenarios using Attention-LSTM with Fully Convolutional Networks
- 26 September 2025
- Published by Cukurova Universitesi Muhendislik-Mimarlik Fakultesi Dergisi in Çukurova Üniversitesi Mühendislik Fakültesi Dergisi
- Vol. 40 (3) , 531-544
Diagnosis of Hepatocellular Carcinoma - HCC Liver Cancer Using Federated Learning on MR Images
In recent years, Federated Learning has emerged as a powerful paradigm for training machine learning models across decentralized data sources while preserving data privacy. This study proposes a Federated Learning framework for the classification of liver tumors using Magnetic Resonance Imaging obtained from the ATLAS dataset, which provides contrast-enhanced images of hepatocellular carcinoma cases. A comparative evaluation was performed utilizing Convolutional Neural Network, EfficientNet, MobileNetV3, ResNet50, and VGG16 architectures within the federated environment. Among these models, the Federated Learning implementation based on EfficientNet achieved superior performance, reaching an accuracy of 93.75% and a ROC-AUC score of 99.19%. The results demonstrate that federated approaches can attain performance levels comparable to centralized learning while ensuring patient data confidentiality. This study highlights the applicability of Federated Learning in sensitive medical imaging tasks and emphasizes its potential for privacy-preserving collaborative model development. Future work may explore real-world deployment and scalability across heterogeneous clinical settings.
- 26 September 2025
- Published by Cukurova Universitesi Muhendislik-Mimarlik Fakultesi Dergisi in Çukurova Üniversitesi Mühendislik Fakültesi Dergisi
- Vol. 40 (3) , 531-544
Diagnosis of Hepatocellular Carcinoma - HCC Liver Cancer Using Federated Learning on MR Images
In recent years, Federated Learning has emerged as a powerful paradigm for training machine learning models across decentralized data sources while preserving data privacy. This study proposes a Federated Learning framework for the classification of liver tumors using Magnetic Resonance Imaging obtained from the ATLAS dataset, which provides contrast-enhanced images of hepatocellular carcinoma cases. A comparative evaluation was performed utilizing Convolutional Neural Network, EfficientNet, MobileNetV3, ResNet50, and VGG16 architectures within the federated environment. Among these models, the Federated Learning implementation based on EfficientNet achieved superior performance, reaching an accuracy of 93.75% and a ROC-AUC score of 99.19%. The results demonstrate that federated approaches can attain performance levels comparable to centralized learning while ensuring patient data confidentiality. This study highlights the applicability of Federated Learning in sensitive medical imaging tasks and emphasizes its potential for privacy-preserving collaborative model development. Future work may explore real-world deployment and scalability across heterogeneous clinical settings.
- Open Access
- 17 November 2022
- Published by The Korean Society for Transplantation in Korean Journal of Transplantation
- Vol. 36 (1) , S250
QuantiFERON cytomegalovirus assay for evaluation of CMV reactivity among renal transplant recipient and donor in Bangladesh
Farnaz Nobi, Amit Bari, Nura Afza Salma Begum, Tasnuva Sarah Kashem, Mohammad Shakib Uz-Zaman Arefin, Shoeb Nomany, Mitali Rahman, Niyoti Akhter, Eshaba Yousuf, Harun Ur Rashid. Korean J Transplant 2022;36:250. https://doi.org/10.4285/ATW2022.F-3896
- 17 November 2022
- Published by The Korean Society for Transplantation in Korean Journal of Transplantation
- Vol. 36 (1) , S250
Open AccessQuantiFERON cytomegalovirus assay for evaluation of CMV reactivity among renal transplant recipient and donor in Bangladesh
Farnaz Nobi, Amit Bari, Nura Afza Salma Begum, Tasnuva Sarah Kashem, Mohammad Shakib Uz-Zaman Arefin, Shoeb Nomany, Mitali Rahman, Niyoti Akhter, Eshaba Yousuf, Harun Ur Rashid. Korean J Transplant 2022;36:250. https://doi.org/10.4285/ATW2022.F-3896
- 28 April 2022
- Published by Wiley in Expert Systems
- Vol. 39 (8)
Analysis of breast cancer classification robustness with radiomics feature extraction and deep learning techniques
Breast cancer and breast imaging diagnostic procedures are typically carried out using a variety of imaging modalities, including mammography, MRI, and ultrasound. However, ultrasound and mammography have limitations and MRI is recognized as better than other procedures. Recent computational approaches, such as radiomics, applied to image analysis have shown remarkable progress in lowering diagnostic difficulties. This research analysed the robustness of breast tumour classification with feature extraction (radiomics) and a featureless method (deep learning). The proposal consists of two stages: the first stage introduced and explored radiomics‐based steps. A total of 111 tumour lesions were used to derive 74 radiomic features consisting of shape, and three separate second‐order metrics. Associations of these features were used to classify tumour lesions with four different kernels from support vector machine algorithm. In the confusion matrix analysis, the SVM‐RBF kernel developed optimal diagnostic efficiency with a maximum test accuracy of 97.06% on the combination of feature analysis. The second stage developed with deep learning techniques (InceptionV3 and CNN‐SVM). A total of 2998 images were used to create the models. In this portion, the CNN‐SVM model achieved the highest accuracy, 95.28%, with an AUC of 0.974, where the pre‐trained InceptionV3 achieved an AUC of only 0.932. Finally, the obtained result in both stages was discussed together and other related studies.
- 28 April 2022
- Published by Wiley in Expert Systems
- Vol. 39 (8)
Analysis of breast cancer classification robustness with radiomics feature extraction and deep learning techniques
Breast cancer and breast imaging diagnostic procedures are typically carried out using a variety of imaging modalities, including mammography, MRI, and ultrasound. However, ultrasound and mammography have limitations and MRI is recognized as better than other procedures. Recent computational approaches, such as radiomics, applied to image analysis have shown remarkable progress in lowering diagnostic difficulties. This research analysed the robustness of breast tumour classification with feature extraction (radiomics) and a featureless method (deep learning). The proposal consists of two stages: the first stage introduced and explored radiomics‐based steps. A total of 111 tumour lesions were used to derive 74 radiomic features consisting of shape, and three separate second‐order metrics. Associations of these features were used to classify tumour lesions with four different kernels from support vector machine algorithm. In the confusion matrix analysis, the SVM‐RBF kernel developed optimal diagnostic efficiency with a maximum test accuracy of 97.06% on the combination of feature analysis. The second stage developed with deep learning techniques (InceptionV3 and CNN‐SVM). A total of 2998 images were used to create the models. In this portion, the CNN‐SVM model achieved the highest accuracy, 95.28%, with an AUC of 0.974, where the pre‐trained InceptionV3 achieved an AUC of only 0.932. Finally, the obtained result in both stages was discussed together and other related studies.
- Open Access
- 30 April 2020
- Published by SASPR Edu International Pvt. Ltd in Scholars Journal of Applied Medical Sciences
- Vol. 08 (04) , 1108-1111
Role of Hla-A and Hla-B Antigen Matching in Renal Aloograft Survival
- 30 April 2020
- Published by SASPR Edu International Pvt. Ltd in Scholars Journal of Applied Medical Sciences
- Vol. 08 (04) , 1108-1111
Open AccessRole of Hla-A and Hla-B Antigen Matching in Renal Aloograft Survival
- 1 April 2014
- Published by SAGE Publications in Journal of Empirical Research on Human Research Ethics
- Vol. 9 (2) , 52-67
Perspectives from South and East Asia on Clinical and Research Ethics: A Literature Review
A review was conducted of english-language peer-reviewed and gray literature on health and ethics written by authors from Bangladesh, China, India, and Pakistan. This was supplemented by the knowledge of co-authors who are involved in bioethics capacity building in these countries. Of the identified literature that focused on the application of Western principles, it largely discussed informed consent and revealed norms in clinical decision-making that include physician paternalism, family involvement in decision-making, and reluctance to provide information that might upset patients. It appears that Western ethical principles may be interpreted and applied in unexpected ways. The literature further indicates that, although there is some consistency with Western ideas, Islamic, Confucian, and Indian religious and philosophical traditions contain concepts not reflected in international guidance. Findings suggest scholars from these countries seek to enter into a bioethics dialogue with the potential to enrich and inform “international” frameworks.
- 1 April 2014
- Published by SAGE Publications in Journal of Empirical Research on Human Research Ethics
- Vol. 9 (2) , 52-67
Perspectives from South and East Asia on Clinical and Research Ethics: A Literature Review
A review was conducted of english-language peer-reviewed and gray literature on health and ethics written by authors from Bangladesh, China, India, and Pakistan. This was supplemented by the knowledge of co-authors who are involved in bioethics capacity building in these countries. Of the identified literature that focused on the application of Western principles, it largely discussed informed consent and revealed norms in clinical decision-making that include physician paternalism, family involvement in decision-making, and reluctance to provide information that might upset patients. It appears that Western ethical principles may be interpreted and applied in unexpected ways. The literature further indicates that, although there is some consistency with Western ideas, Islamic, Confucian, and Indian religious and philosophical traditions contain concepts not reflected in international guidance. Findings suggest scholars from these countries seek to enter into a bioethics dialogue with the potential to enrich and inform “international” frameworks.