Majdi Sukkar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Majdi Sukkar has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Madhu Shukla
Marwadi University
3 shared publications - Rajendrasinh Jadeja
Department of Electrical Engineering, Marwadi University, Rajkot, Gujarat, India
2 shared publications - Abdullah Albuali
Department of Computer Networks and Communications, College of Computer Sciences and Information Technology, King Faisal University, Al-Ahsa 31982, Saudi Arabia
1 shared publication - Andreas Kanavos
Department of Informatics, Ionian University, 49100 Corfu, Greece
1 shared publication - Biswaranjan Acharya
Marwadi University
1 shared publication Dinesh Kumar
Marwadi University
1 shared publication
Latest Publications
- 28 September 2025
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 36 (10)
Dynamic Multi‐Objective Optimization in Vehicular Fog Computing With NSGA ‐ II +
Vehicular Fog Computing (VFC) presents a promising paradigm to reduce latency and energy usage through utilization of nearby edge resources by vehicles. Yet, efficient and scalable resource management is still a significant challenge particularly due to dynamic network topologies, resource, and high Quality of Service (QoS) requirements. Traditional metaheuristic methods such as GA and PSO are limited in convergence speed and solution quality under such restrictions. This research introduces Enhanced NSGA‐II+, a cutting‐edge multi‐objective evolutionary model enhancing NSGA‐II and NSGA‐III through dynamic population adaptation, Pareto‐front‐leveraged selection, and premature convergence prevention. Experimental comparisons in both common and ultra‐dense vehicular settings with up to 1000 vehicles and 2000 tasks show that NSGA‐II+ outperforms baseline algorithms by far, reducing average delay by 72.55% (compared to NSGA‐II) and 71.75% (vs. NSGA‐III), and energy cost by 70.96% (compared to NSGA‐II) and 70.75% (compared to NSGA‐III). This reinforces how NSGA‐II+ addresses both dynamic topologies and resource heterogeneity. Its strong exploration‐exploitation trade‐off and flexibility render it an appealing solution for real‐time, energy‐efficient deployment in smart transportation systems.
- 28 September 2025
- Published by Wiley in Transactions on Emerging Telecommunications Technologies
- Vol. 36 (10)
Dynamic Multi‐Objective Optimization in Vehicular Fog Computing With NSGA ‐ II +
Vehicular Fog Computing (VFC) presents a promising paradigm to reduce latency and energy usage through utilization of nearby edge resources by vehicles. Yet, efficient and scalable resource management is still a significant challenge particularly due to dynamic network topologies, resource, and high Quality of Service (QoS) requirements. Traditional metaheuristic methods such as GA and PSO are limited in convergence speed and solution quality under such restrictions. This research introduces Enhanced NSGA‐II+, a cutting‐edge multi‐objective evolutionary model enhancing NSGA‐II and NSGA‐III through dynamic population adaptation, Pareto‐front‐leveraged selection, and premature convergence prevention. Experimental comparisons in both common and ultra‐dense vehicular settings with up to 1000 vehicles and 2000 tasks show that NSGA‐II+ outperforms baseline algorithms by far, reducing average delay by 72.55% (compared to NSGA‐II) and 71.75% (vs. NSGA‐III), and energy cost by 70.96% (compared to NSGA‐II) and 70.75% (compared to NSGA‐III). This reinforces how NSGA‐II+ addresses both dynamic topologies and resource heterogeneity. Its strong exploration‐exploitation trade‐off and flexibility render it an appealing solution for real‐time, energy‐efficient deployment in smart transportation systems.
- Open Access
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 3994-4007
A Survey of Deep Learning Approaches for Pedestrian Detection in Autonomous Systems
This paper surveys real-time object detection literature critically and analytically, focusing particularly on pedestrian detection for safe autonomous vehicles. It addresses the challenges in the domain, some of the sources of which are variations in age, gender, clothing, lighting, backgrounds, and occlusion. The paper reviews object detection algorithms after providing an overview of deep learning basics and main architectures of neural networks, followed by discussion on existing algorithms along with their strengths, weaknesses, and future research directions. There is a need for pedestrian detection datasets with further complex annotations and multi-source integration, which captures interactions between pedestrians and their surroundings. Incorporating advanced sensors, including LiDAR, infrared, and depth sensors, as the foremost means to enhance the detection capabilities in more adverse conditions, such as low-light situations and occlusion. However, architectures such as YOLO, SSD, and Faster R-CNN, which have led to current improvements in performance, still allow room for improving pedestrian detection accuracy. By filling in these insights and proposed solutions, the paper focus on the development of pedestrian detection technology, how it can be brought into a safer, reliable, real-world applicability towards the system of autonomous driving. All of these results point to continued innovation towards deep learning, multi-sensor integration, and developing datasets to achieve optimal performance levels in real world conditions for autonomous driving systems.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 3994-4007
Open AccessA Survey of Deep Learning Approaches for Pedestrian Detection in Autonomous Systems
This paper surveys real-time object detection literature critically and analytically, focusing particularly on pedestrian detection for safe autonomous vehicles. It addresses the challenges in the domain, some of the sources of which are variations in age, gender, clothing, lighting, backgrounds, and occlusion. The paper reviews object detection algorithms after providing an overview of deep learning basics and main architectures of neural networks, followed by discussion on existing algorithms along with their strengths, weaknesses, and future research directions. There is a need for pedestrian detection datasets with further complex annotations and multi-source integration, which captures interactions between pedestrians and their surroundings. Incorporating advanced sensors, including LiDAR, infrared, and depth sensors, as the foremost means to enhance the detection capabilities in more adverse conditions, such as low-light situations and occlusion. However, architectures such as YOLO, SSD, and Faster R-CNN, which have led to current improvements in performance, still allow room for improving pedestrian detection accuracy. By filling in these insights and proposed solutions, the paper focus on the development of pedestrian detection technology, how it can be brought into a safer, reliable, real-world applicability towards the system of autonomous driving. All of these results point to continued innovation towards deep learning, multi-sensor integration, and developing datasets to achieve optimal performance levels in real world conditions for autonomous driving systems.
- Open Access
- 9 February 2024
- Published by MDPI AG in Information
- Vol. 15 (2) , 104
Enhancing Pedestrian Tracking in Autonomous Vehicles by Using Advanced Deep Learning Techniques
Effective collision risk reduction in autonomous vehicles relies on robust and straightforward pedestrian tracking. Challenges posed by occlusion and switching scenarios significantly impede the reliability of pedestrian tracking. In the current study, we strive to enhance the reliability and also the efficacy of pedestrian tracking in complex scenarios. Particularly, we introduce a new pedestrian tracking algorithm that leverages both the YOLOv8 (You Only Look Once) object detector technique and the StrongSORT algorithm, which is an advanced deep learning multi-object tracking (MOT) method. Our findings demonstrate that StrongSORT, an enhanced version of the DeepSORT MOT algorithm, substantially improves tracking accuracy through meticulous hyperparameter tuning. Overall, the experimental results reveal that the proposed algorithm is an effective and efficient method for pedestrian tracking, particularly in complex scenarios encountered in the MOT16 and MOT17 datasets. The combined use of Yolov8 and StrongSORT contributes to enhanced tracking results, emphasizing the synergistic relationship between detection and tracking modules.
- 9 February 2024
- Published by MDPI AG in Information
- Vol. 15 (2) , 104
Open AccessEnhancing Pedestrian Tracking in Autonomous Vehicles by Using Advanced Deep Learning Techniques
Effective collision risk reduction in autonomous vehicles relies on robust and straightforward pedestrian tracking. Challenges posed by occlusion and switching scenarios significantly impede the reliability of pedestrian tracking. In the current study, we strive to enhance the reliability and also the efficacy of pedestrian tracking in complex scenarios. Particularly, we introduce a new pedestrian tracking algorithm that leverages both the YOLOv8 (You Only Look Once) object detector technique and the StrongSORT algorithm, which is an advanced deep learning multi-object tracking (MOT) method. Our findings demonstrate that StrongSORT, an enhanced version of the DeepSORT MOT algorithm, substantially improves tracking accuracy through meticulous hyperparameter tuning. Overall, the experimental results reveal that the proposed algorithm is an effective and efficient method for pedestrian tracking, particularly in complex scenarios encountered in the MOT16 and MOT17 datasets. The combined use of Yolov8 and StrongSORT contributes to enhanced tracking results, emphasizing the synergistic relationship between detection and tracking modules.
- Open Access
- 30 September 2022
- Published by Ton Duc Thang University in Journal of Advanced Engineering and Computation
- Vol. 6 (3) , 215-223
Improve Detection and Tracking of Pedestrian Subclasses by Pre-Trained Models
There are sub-classes of pedestrians that can be defined and it is important to distinguish between them for the detection in autonomous vehicle applications, such as elderly, and children, to reduce the risk of collision. It is necessary to talk about effective pedestrian tracking besides detection so that object remains accurately monitored, here the effective pre-trained algorithms come to achieve this goal in real-time. In this paper, we make a comparison between the detection and tracking algorithms, we applied the transfer learning technique to train the detection model on new sub-classes, after making Images augmentation in previous work, we got better results in detection, reached 0.81 mAP in real-time by using Yolov5 model, with a good tracking performance by the tracking algorithm dependent on detection Deep-SORT.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.
- 30 September 2022
- Published by Ton Duc Thang University in Journal of Advanced Engineering and Computation
- Vol. 6 (3) , 215-223
Open AccessImprove Detection and Tracking of Pedestrian Subclasses by Pre-Trained Models
There are sub-classes of pedestrians that can be defined and it is important to distinguish between them for the detection in autonomous vehicle applications, such as elderly, and children, to reduce the risk of collision. It is necessary to talk about effective pedestrian tracking besides detection so that object remains accurately monitored, here the effective pre-trained algorithms come to achieve this goal in real-time. In this paper, we make a comparison between the detection and tracking algorithms, we applied the transfer learning technique to train the detection model on new sub-classes, after making Images augmentation in previous work, we got better results in detection, reached 0.81 mAP in real-time by using Yolov5 model, with a good tracking performance by the tracking algorithm dependent on detection Deep-SORT.This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium provided the original work is properly cited.