Tareq Mahmod AlZubi
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
Tareq Mahmod AlZubi has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Umar Raza Mukhtar
3 shared publications- Omar. A. Alzubi
Faculty of Artificial Intelligence, Al-Balqa Applied University, Al-Salt, Jordan
2 shared publications - Ashish Singh
School of Computer Engineering, Kalinga Institute of Industrial Technology (KIIT), Bhubaneswar, India
1 shared publication Hamza Mukhtar
Department of Computer Science, University of Engineering and Technology Lahore (UET Lahore), Lahore, Pakistan
1 shared publication- Hamza Mukhtar
University of Engineering and Technology Lahore, Lahore, Pakistan
1 shared publication - Jafar A. Alzubi
Al-Balqa Applied University
1 shared publication
Latest Publications
- Open Access
- 12 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 83619-83642
Federated Knowledge Distillation With 3D Transformer Adaptation for Weakly Labeled Multi-Organ Medical Image Segmentation
The increasing reliance on medical image segmentation for disease diagnosis, treatment planning, and therapeutic assessment has highlighted the need for robust and generalized deep learning (DL)-based segmentation frameworks. However, existing models often suffer from task-specific limitations, catastrophic forgetting, and poor scalability due to their dependency on narrowly annotated datasets. This creates a significant gap in developing unified, multi-organ segmentation systems that leverage distributed and partially labeled datasets across diverse clinical institutions. To address these challenges, we propose the Federated 3D Knowledge Distillation Network (Fed3D-KDNet), a hybrid federated learning (FL) framework that integrates both global and local knowledge distillation mechanisms. Our model adapts the Segment Anything Model (SAM) for volumetric medical imaging by introducing architectural enhancements, including 3D spatial feature adapters and an Auto Prompt Generator (APG), to optimize spatial representation and reduce reliance on manually crafted prompts. Fed3D-KDNet employs a dual knowledge distillation strategy to mitigate catastrophic forgetting and improve cross-client knowledge transfer, ensuring robust generalization across heterogeneous datasets. The proposed methodology was evaluated on multi-organ CT datasets, including the BTCV benchmark, under centralized and federated settings. Experimental results demonstrate that Fed3D-KDNet achieves state-of-the-art performance with an average Dice score of 80.53% and an average Hausdorff Distance (HD) of 11.43 voxels in federated experiments involving seven clients, showing 5.04% improvement in Dice accuracy and a 4.35 voxel reduction in HD. Moreover, our model demonstrates superior efficiency with a computational cost of 371.3 GFLOPs, 26.53 million tuned parameters, and an inference time of 0.058 seconds per iteration. These results validate the efficacy, scalability, and computational efficiency of Fed3D-KDNet, positioning it as a robust solution for multi-organ medical image segmentation in federated environments.
- 12 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 83619-83642
Open AccessFederated Knowledge Distillation With 3D Transformer Adaptation for Weakly Labeled Multi-Organ Medical Image Segmentation
The increasing reliance on medical image segmentation for disease diagnosis, treatment planning, and therapeutic assessment has highlighted the need for robust and generalized deep learning (DL)-based segmentation frameworks. However, existing models often suffer from task-specific limitations, catastrophic forgetting, and poor scalability due to their dependency on narrowly annotated datasets. This creates a significant gap in developing unified, multi-organ segmentation systems that leverage distributed and partially labeled datasets across diverse clinical institutions. To address these challenges, we propose the Federated 3D Knowledge Distillation Network (Fed3D-KDNet), a hybrid federated learning (FL) framework that integrates both global and local knowledge distillation mechanisms. Our model adapts the Segment Anything Model (SAM) for volumetric medical imaging by introducing architectural enhancements, including 3D spatial feature adapters and an Auto Prompt Generator (APG), to optimize spatial representation and reduce reliance on manually crafted prompts. Fed3D-KDNet employs a dual knowledge distillation strategy to mitigate catastrophic forgetting and improve cross-client knowledge transfer, ensuring robust generalization across heterogeneous datasets. The proposed methodology was evaluated on multi-organ CT datasets, including the BTCV benchmark, under centralized and federated settings. Experimental results demonstrate that Fed3D-KDNet achieves state-of-the-art performance with an average Dice score of 80.53% and an average Hausdorff Distance (HD) of 11.43 voxels in federated experiments involving seven clients, showing 5.04% improvement in Dice accuracy and a 4.35 voxel reduction in HD. Moreover, our model demonstrates superior efficiency with a computational cost of 371.3 GFLOPs, 26.53 million tuned parameters, and an inference time of 0.058 seconds per iteration. These results validate the efficacy, scalability, and computational efficiency of Fed3D-KDNet, positioning it as a robust solution for multi-organ medical image segmentation in federated environments.
- Open Access
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 47146-47164
Transformer-Based Multi-Target Object Detection and Tracking Framework for Robust Spatio-Temporal Memory in Dynamic Environments
- 1 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 47146-47164
Open AccessTransformer-Based Multi-Target Object Detection and Tracking Framework for Robust Spatio-Temporal Memory in Dynamic Environments
- Open Access
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 7014-7026
MVR: Synergizing Large and Vision Transformer for Multimodal Natural Language-Driven Vehicle Retrieval
In recent years, intelligent transportation systems have played a pivotal role in the development of smart cities, with vehicle retrieval becoming a critical component of traffic management and surveillance. Traditional vehicle retrieval systems rely heavily on image-based matching techniques derived from vehicle re-identification (VReID) tasks. However, these approaches are limited by their dependency on image queries, which may not always be available in real-world scenarios. Natural language (NL)-based vehicle retrieval systems offer a more flexible and accessible alternative by enabling users to query vehicles using textual descriptions. Despite progress in NL-based retrieval, existing methods face challenges in fully capturing multi-granularity information and aligning heterogeneous visual and linguistic inputs. This paper addresses these limitations by proposing a robust Multimodal Vehicle Retrieval (MVR) model that integrates both visual and textual data through a dual-stream architecture. Our model captures complementary local features, alongside global information including motion and environmental context. We utilize InfoNCE and instance losses to align the visual and textual modalities within a shared feature space, while post-processing modules, including Granular Vehicle Feature Refinement and Spatial Relationship Modeling, further enhance retrieval performance by refining vehicle attributes and contextual relationships. Our experiments, conducted on the CityFlow-NL dataset, demonstrate that our model achieves a 35.6% improvement in Mean Reciprocal Rank (MRR), a 41.3% increase in recall at 5 (R@5), and a 22.9% improvement in recall at 10 (R@10) compared to the baseline, and overcomes the inherent challenges of cross-modal retrieval in improving real-world VReID.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 7014-7026
Open AccessMVR: Synergizing Large and Vision Transformer for Multimodal Natural Language-Driven Vehicle Retrieval
In recent years, intelligent transportation systems have played a pivotal role in the development of smart cities, with vehicle retrieval becoming a critical component of traffic management and surveillance. Traditional vehicle retrieval systems rely heavily on image-based matching techniques derived from vehicle re-identification (VReID) tasks. However, these approaches are limited by their dependency on image queries, which may not always be available in real-world scenarios. Natural language (NL)-based vehicle retrieval systems offer a more flexible and accessible alternative by enabling users to query vehicles using textual descriptions. Despite progress in NL-based retrieval, existing methods face challenges in fully capturing multi-granularity information and aligning heterogeneous visual and linguistic inputs. This paper addresses these limitations by proposing a robust Multimodal Vehicle Retrieval (MVR) model that integrates both visual and textual data through a dual-stream architecture. Our model captures complementary local features, alongside global information including motion and environmental context. We utilize InfoNCE and instance losses to align the visual and textual modalities within a shared feature space, while post-processing modules, including Granular Vehicle Feature Refinement and Spatial Relationship Modeling, further enhance retrieval performance by refining vehicle attributes and contextual relationships. Our experiments, conducted on the CityFlow-NL dataset, demonstrate that our model achieves a 35.6% improvement in Mean Reciprocal Rank (MRR), a 41.3% increase in recall at 5 (R@5), and a 22.9% improvement in recall at 10 (R@10) compared to the baseline, and overcomes the inherent challenges of cross-modal retrieval in improving real-world VReID.
- 7 February 2023
- Published by Springer Nature in Mobile Networks and Applications
- Vol. 28 (2) , 795-807
Quantum Mayfly Optimization with Encoder-Decoder Driven LSTM Networks for Malware Detection and Classification Model
- 7 February 2023
- Published by Springer Nature in Mobile Networks and Applications
- Vol. 28 (2) , 795-807
Quantum Mayfly Optimization with Encoder-Decoder Driven LSTM Networks for Malware Detection and Classification Model
- Open Access
- 17 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 53998-54009
Improving the Working Memory During Early Childhood Education Through the Use of an Interactive Gesture Game-Based Learning Approach
One of the most socially and culturally advantageous uses of human–computer interaction is enhancing playing and learning for children. In this paper, gesture interactive game-based learning (GIGL) is tested to see if these kinds of applications are suitable to stimulate working memory (WM) and basic mathematical skills (BMS) in early childhood (5–6 years old) using a hand gesture recognition system. Hand gesture is being performed by the user and to control a computer system by that incoming information. The research was developed using a quasi-experimental design with a pre-test and post-test, using both an experimental and control group through three phases: the first one was the prior evaluation of the learner’s skills; a second phase in which the use of the technology was developed; and a final phase of evaluation. In the evaluation phases, working memory was measured using the Corsi task, and the basic mathematical skills using the test for the diagnosis of basic mathematical competencies (TEDI-MATH). The results provide clear evidence that the use of these technologies improved both working memory and basic mathematical skills. We can conclude that the children who used GIGL technology showed a significant increase in their learning performance in WM and BMS, surpassing those who did normal school activities.
- 17 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 53998-54009
Open AccessImproving the Working Memory During Early Childhood Education Through the Use of an Interactive Gesture Game-Based Learning Approach
One of the most socially and culturally advantageous uses of human–computer interaction is enhancing playing and learning for children. In this paper, gesture interactive game-based learning (GIGL) is tested to see if these kinds of applications are suitable to stimulate working memory (WM) and basic mathematical skills (BMS) in early childhood (5–6 years old) using a hand gesture recognition system. Hand gesture is being performed by the user and to control a computer system by that incoming information. The research was developed using a quasi-experimental design with a pre-test and post-test, using both an experimental and control group through three phases: the first one was the prior evaluation of the learner’s skills; a second phase in which the use of the technology was developed; and a final phase of evaluation. In the evaluation phases, working memory was measured using the Corsi task, and the basic mathematical skills using the test for the diagnosis of basic mathematical competencies (TEDI-MATH). The results provide clear evidence that the use of these technologies improved both working memory and basic mathematical skills. We can conclude that the children who used GIGL technology showed a significant increase in their learning performance in WM and BMS, surpassing those who did normal school activities.