Shehzad Ali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Shehzad Ali has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Khan Muhammad
Sungkyunkwan University, Seoul, Republic of Korea
11 shared publications - Ik Hyun Lee
Department of Mechatronics Engineering, Tech University of Korea, Siheung, Republic of Korea
6 shared publications - Mohammad Hijji
University of Tabuk
5 shared publications - Tanvir Islam
Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea
5 shared publications - Muhammad Sajjad
Islamia College Peshawar
4 shared publications - Victor Hugo Costa de Albuquerque
Department of Teleinformatics Engineering, Federal University of Cear, Fortaleza, Brazil
4 shared publications
Latest Publications
- Open Access
- 29 September 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (19) , 3543
Learning to Expect the Unexpected: Benchmarking and Detecting Unexpected Road Hazards
Unexpected road hazards remain a critical challenge for driving safety, as they exhibit irregular appearances, vary widely in scale, and frequently arise under adverse environmental conditions. Existing detection approaches often struggle to achieve reliable localization under challenging conditions such as rain, fog, low-light environments, and small-hazard scenarios. To address these limitations, we propose ROAD-DETR, a difficulty-aware, transformer-based detection framework specifically designed for robust detection of unexpected road hazards. Specifically, it enhances a transformer encoder–decoder architecture by introducing three task-specific modules: (1) a Hazard-Aware Multi-Scale Fusion Module for multi-scale feature aggregation, (2) a Difficulty-Aware Feature Enhancement Module to enhance visually degraded hazard representations, and (3) a Hazard Query Refinement Module for adaptive refinement of transformer object queries. Training and evaluating such a model is challenging because most existing road-scene datasets focus on common traffic participants, while hazards such as Accident Vehicles, Fallen Trees, Icy Roads, Oil Spills, Road Debris, and Surface Water remain underrepresented. In response, we introduce ROAD-6-Det, a benchmark for unexpected road hazard detection with bounding-box annotations. Extensive experiments on ROAD-6-Det using a wide range of state-of-the-art YOLO-based and transformer-based detectors show that our ROAD-DETR achieves 94.2% mAP@50, 72.1% mAP@50:95, 93.2% precision, 91.1% recall, and an F1-score of 93.5%, outperforming existing models. The proposed ROAD-DETR framework and the ROAD-6-Det benchmark provide a strong foundation for future research on unexpected road hazard detection. For reproducibility, the code and dataset will be released publicly.
- 29 September 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (19) , 3543
Open AccessLearning to Expect the Unexpected: Benchmarking and Detecting Unexpected Road Hazards
Unexpected road hazards remain a critical challenge for driving safety, as they exhibit irregular appearances, vary widely in scale, and frequently arise under adverse environmental conditions. Existing detection approaches often struggle to achieve reliable localization under challenging conditions such as rain, fog, low-light environments, and small-hazard scenarios. To address these limitations, we propose ROAD-DETR, a difficulty-aware, transformer-based detection framework specifically designed for robust detection of unexpected road hazards. Specifically, it enhances a transformer encoder–decoder architecture by introducing three task-specific modules: (1) a Hazard-Aware Multi-Scale Fusion Module for multi-scale feature aggregation, (2) a Difficulty-Aware Feature Enhancement Module to enhance visually degraded hazard representations, and (3) a Hazard Query Refinement Module for adaptive refinement of transformer object queries. Training and evaluating such a model is challenging because most existing road-scene datasets focus on common traffic participants, while hazards such as Accident Vehicles, Fallen Trees, Icy Roads, Oil Spills, Road Debris, and Surface Water remain underrepresented. In response, we introduce ROAD-6-Det, a benchmark for unexpected road hazard detection with bounding-box annotations. Extensive experiments on ROAD-6-Det using a wide range of state-of-the-art YOLO-based and transformer-based detectors show that our ROAD-DETR achieves 94.2% mAP@50, 72.1% mAP@50:95, 93.2% precision, 91.1% recall, and an F1-score of 93.5%, outperforming existing models. The proposed ROAD-DETR framework and the ROAD-6-Det benchmark provide a strong foundation for future research on unexpected road hazard detection. For reproducibility, the code and dataset will be released publicly.
- 4 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. PP (15513203) , 1-12
Resource-Efficient Neural Network for Crop Damage Classification in Precision Agriculture
Timely and accurate crop damage classification (CDC) is vital for informed decision-making in the industry of precision agriculture. Traditional manual methods are slow and unreliable, whereas recent deep learning models, although accurate, are often too computationally intensive for resource-constrained environments. In this study, we present LNetCDC, a lightweight attention-based convolutional neural network tailored for CDC. The architecture integrates an EchoBlock for efficient feature extraction, combined with residual pathways enhanced by “Channelwise Refine” and “Dual Gate Attention” modules to emphasize critical spatial and channelwise features. Also, dilated convolutions are incorporated into deeper layers to capture multiscale contextual patterns. We evaluated our LNetCDC on a benchmark crop damage dataset, where it outperformed existing state-of-the-art (SOTA) models in terms of both accuracy and efficiency. Notably, it achieves around 2.3% gain in accuracy with only 0.86 million parameters compared with 1.13 million in the prior SOTA model for CDC. These results demonstrate the effectiveness and suitability of LNetCDC for real-time deployment on industrial edge devices.
- 4 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. PP (15513203) , 1-12
Resource-Efficient Neural Network for Crop Damage Classification in Precision Agriculture
Timely and accurate crop damage classification (CDC) is vital for informed decision-making in the industry of precision agriculture. Traditional manual methods are slow and unreliable, whereas recent deep learning models, although accurate, are often too computationally intensive for resource-constrained environments. In this study, we present LNetCDC, a lightweight attention-based convolutional neural network tailored for CDC. The architecture integrates an EchoBlock for efficient feature extraction, combined with residual pathways enhanced by “Channelwise Refine” and “Dual Gate Attention” modules to emphasize critical spatial and channelwise features. Also, dilated convolutions are incorporated into deeper layers to capture multiscale contextual patterns. We evaluated our LNetCDC on a benchmark crop damage dataset, where it outperformed existing state-of-the-art (SOTA) models in terms of both accuracy and efficiency. Notably, it achieves around 2.3% gain in accuracy with only 0.86 million parameters compared with 1.13 million in the prior SOTA model for CDC. These results demonstrate the effectiveness and suitability of LNetCDC for real-time deployment on industrial edge devices.
- Open Access
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6317-6322
IARD: Intruder Activity Recognition Dataset for Threat Detection
- 10 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 6317-6322
Open AccessIARD: Intruder Activity Recognition Dataset for Threat Detection
- 7 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (2) , 47-56
NeuroShield-IoE: A Cognitive, Quantum-Resilient, and Self-Evolving Cybersecurity Framework for the Internet of Energy
The Internet of Energy (IoE) is reshaping modern energy systems by connecting smart grids, distributed energy resources, and consumer devices. This shift enables efficiency and flexibility but also introduces critical security risks. Traditional cybersecurity models, built for static, centralized systems, are inefficient at protecting today’s dynamic and distributed energy environments. The rise of quantum computing threatens current cryptographic standards, while AI-powered attacks are becoming more adaptive and difficult to detect. Energy systems, often resource-constrained and latency-sensitive, lack the capacity to adopt conventional security solutions. There is a pressing need for a lightweight, adaptive, and future-ready security framework. This work contributes significantly by proposing NeuroShield-IoE, a conceptual framework that integrates cognitive intelligence and quantum-resilient mechanisms, tailored to strengthen the security posture of IoE systems against evolving threats. The framework combines neuro-symbolic reasoning for adaptive threat detection, post-quantum cryptography for secure communication, and a self-evolving architecture that learns from edge data without requiring centralized updates. This layered approach aims to ensure real-time responsiveness, resource-aware deployment, and long-term resilience across diverse IoE environments.
- 7 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. 40 (2) , 47-56
NeuroShield-IoE: A Cognitive, Quantum-Resilient, and Self-Evolving Cybersecurity Framework for the Internet of Energy
The Internet of Energy (IoE) is reshaping modern energy systems by connecting smart grids, distributed energy resources, and consumer devices. This shift enables efficiency and flexibility but also introduces critical security risks. Traditional cybersecurity models, built for static, centralized systems, are inefficient at protecting today’s dynamic and distributed energy environments. The rise of quantum computing threatens current cryptographic standards, while AI-powered attacks are becoming more adaptive and difficult to detect. Energy systems, often resource-constrained and latency-sensitive, lack the capacity to adopt conventional security solutions. There is a pressing need for a lightweight, adaptive, and future-ready security framework. This work contributes significantly by proposing NeuroShield-IoE, a conceptual framework that integrates cognitive intelligence and quantum-resilient mechanisms, tailored to strengthen the security posture of IoE systems against evolving threats. The framework combines neuro-symbolic reasoning for adaptive threat detection, post-quantum cryptography for secure communication, and a self-evolving architecture that learns from edge data without requiring centralized updates. This layered approach aims to ensure real-time responsiveness, resource-aware deployment, and long-term resilience across diverse IoE environments.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5326-5335
Towards Hazardous Activity Recognition for A Novel Real-World Dataset
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 5326-5335
Open AccessTowards Hazardous Activity Recognition for A Novel Real-World Dataset
- 18 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (9) , 17872-17879
IBN-Driven Rip Current Analysis Using AAVs for Next-Generation Coastal Surveillance
The unpredictable nature of rip currents makes them a leading cause of coastal drowning incidents globally. Traditional methods fall short, necessitating an advanced surveillance system that can prioritize critical threats, enable autonomous decision-making with adaptive network control, and optimize resource allocation for enhanced coastal safety. Intent-based networking (IBN) plays a pivotal role in converting high-level intents into automated processes, enabling dynamic control and intelligent resource allocation in critical applications such as the Internet of Things (IoT) and autonomous aerial vehicle (AAV)-based coastal surveillance. This study proposes an artificial intelligence (AI)-powered, IBN-driven framework for coastal surveillance that leverages AAVs and IoT devices to enable real-time rip current analysis through advanced segmentation techniques. In our framework, AAVs with AI-powered IoT systems perform initial rip current analysis using lightweight deep learning models. High-risk detections are prioritized through the closed-loop feedback mechanism of the IBN and transmitted to control rooms for validation and response, ensuring efficient resource utilization and adaptive surveillance. We expanded the rip current dataset to enhance the segmentation accuracy by incorporating additional samples from open-source platforms and applying diverse environmental conditions. We trained YOLO models and Mask R-CNN, which are suitable for real-time rip current analysis. In addition, we introduced a modified YOLOv11n-seg model, replacing the C3K2 block with C2F and optimizing the channels to reduce the parameters while maintaining accuracy. The best-performing models were tested on edge devices to evaluate the time complexity and reliability.
- 18 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (9) , 17872-17879
IBN-Driven Rip Current Analysis Using AAVs for Next-Generation Coastal Surveillance
The unpredictable nature of rip currents makes them a leading cause of coastal drowning incidents globally. Traditional methods fall short, necessitating an advanced surveillance system that can prioritize critical threats, enable autonomous decision-making with adaptive network control, and optimize resource allocation for enhanced coastal safety. Intent-based networking (IBN) plays a pivotal role in converting high-level intents into automated processes, enabling dynamic control and intelligent resource allocation in critical applications such as the Internet of Things (IoT) and autonomous aerial vehicle (AAV)-based coastal surveillance. This study proposes an artificial intelligence (AI)-powered, IBN-driven framework for coastal surveillance that leverages AAVs and IoT devices to enable real-time rip current analysis through advanced segmentation techniques. In our framework, AAVs with AI-powered IoT systems perform initial rip current analysis using lightweight deep learning models. High-risk detections are prioritized through the closed-loop feedback mechanism of the IBN and transmitted to control rooms for validation and response, ensuring efficient resource utilization and adaptive surveillance. We expanded the rip current dataset to enhance the segmentation accuracy by incorporating additional samples from open-source platforms and applying diverse environmental conditions. We trained YOLO models and Mask R-CNN, which are suitable for real-time rip current analysis. In addition, we introduced a modified YOLOv11n-seg model, replacing the C3K2 block with C2F and optimizing the channels to reduce the parameters while maintaining accuracy. The best-performing models were tested on edge devices to evaluate the time complexity and reliability.
- Open Access
- 21 July 2025
- Published by Elsevier in Alexandria Engineering Journal
- Vol. 127, 1143-1157
CABAD: A video dataset for benchmarking child aggression recognition
- 21 July 2025
- Published by Elsevier in Alexandria Engineering Journal
- Vol. 127, 1143-1157
Open AccessCABAD: A video dataset for benchmarking child aggression recognition
- Open Access
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1973-1977
ROAD-6: A Diverse Dataset for Unexpected Hazard Recognition in Autonomous Vehicles
- 30 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 1973-1977
Open AccessROAD-6: A Diverse Dataset for Unexpected Hazard Recognition in Autonomous Vehicles
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. PP (08908044) , 1
Generative AI-Enhanced Neuro-Symbolic Quantum Architectures for Secure Communications and Networking
The rapid convergence of generative AI (GAI), neuro-symbolic reasoning, and quantum computing has redefined secure communication and networking. Owing to the massive amount of data, the need for extensive computing power, and the necessity to find and mitigate threats in real time, traditional security measures cannot keep up with changing cyber threats as the communication infrastructure becomes more complicated. Therefore, this paper investigates the potential of a GAI-enhanced neuro-symbolic quantum framework for building security systems that are strong, scalable, and self-sufficient. This method improves threat detection, encryption, and real-time adversarial defense by combining symbolic reasoning for logic, deep learning for pattern recognition, and quantum intelligence to accelerate computations. This work has made progress in creating the next generation of secure networks that can automatically and adaptively make security decisions in real-time, providing robust protection in communication environments that change over time.
- 16 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Network
- Vol. PP (08908044) , 1
Generative AI-Enhanced Neuro-Symbolic Quantum Architectures for Secure Communications and Networking
The rapid convergence of generative AI (GAI), neuro-symbolic reasoning, and quantum computing has redefined secure communication and networking. Owing to the massive amount of data, the need for extensive computing power, and the necessity to find and mitigate threats in real time, traditional security measures cannot keep up with changing cyber threats as the communication infrastructure becomes more complicated. Therefore, this paper investigates the potential of a GAI-enhanced neuro-symbolic quantum framework for building security systems that are strong, scalable, and self-sufficient. This method improves threat detection, encryption, and real-time adversarial defense by combining symbolic reasoning for logic, deep learning for pattern recognition, and quantum intelligence to accelerate computations. This work has made progress in creating the next generation of secure networks that can automatically and adaptively make security decisions in real-time, providing robust protection in communication environments that change over time.