Ahmad Ali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ahmad Ali has a total of 66 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoshan Bai
College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen, China
9 shared publications - Inam Ullah
Gachon University
7 shared publications Amin Sharafian
4 shared publications- Riaz Ali
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China
4 shared publications - Amin Sharafian
Shenzhen University
3 shared publications - Tamam Alsarhan
King Abdullah II School of Information Technology, The University of Jordan, Amman, Jordan
3 shared publications
Latest Publications
- Open Access
- 10 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 933-946
SingSprite: Non-Tactile Appliance Interaction for the Blind through Power-Supply Acoustic Signatures
- 10 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 933-946
Open AccessSingSprite: Non-Tactile Appliance Interaction for the Blind through Power-Supply Acoustic Signatures
- Top Cited Papers
- 30 April 2026
- Published by Elsevier in Future Generation Computer Systems
- Vol. 183
Exploiting attention-driven weather-aware multimodal spatio-temporal fusion for urban traffic flow prediction
- 30 April 2026
- Published by Elsevier in Future Generation Computer Systems
- Vol. 183
Top Cited PapersExploiting attention-driven weather-aware multimodal spatio-temporal fusion for urban traffic flow prediction
- Top Cited Papers
- 24 December 2025
- Published by Elsevier in Computer Science Review
- Vol. 60
Advanced computational models for urban traffic flow prediction: A comprehensive review and future directions
- 24 December 2025
- Published by Elsevier in Computer Science Review
- Vol. 60
Top Cited PapersAdvanced computational models for urban traffic flow prediction: A comprehensive review and future directions
- 3 November 2025
- Published by Springer Nature in Earth Systems and Environment
- Vol. 10 (5) , 5335-5350
AI-Driven Ensemble Learning for Tropical Cyclone-Induced Storm Surge Prediction along the Guangdong and Hong Kong Coast
- 3 November 2025
- Published by Springer Nature in Earth Systems and Environment
- Vol. 10 (5) , 5335-5350
AI-Driven Ensemble Learning for Tropical Cyclone-Induced Storm Surge Prediction along the Guangdong and Hong Kong Coast
- Open Access
- 28 October 2025
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Advanced Computing and Systems
- Vol. 1 (4) , 258-274
An Efficient Algorithm for Weather Forecasting Using Causal Graph Neural Network
The rapid accumulation of large-scale, long-term meteorological data presents unprecedented opportunities for data-driven weather modeling and high-resolution numerical weather prediction. While various deep learning techniques—such as Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNNs), and Graph Neural Networks (GNNs)—have been explored for weather forecasting, the complex spatial dependencies within historical meteorological data, particularly dynamic spatial correlations, remain insufficiently addressed. To tackle this challenge, we propose a Dynamic Spatio-Temporal Fusion Graph Network (DSTFGN), a novel module that integrates multivariate time-series analysis with graph-based causal inference to capture intricate and time-varying interdependencies among weather variables. The DSTFGN module fuses real-time inputs (e.g., sensor data, live weather feeds, external events) with historical records to model the propagation of disruptions—such as accidents or road closures—through the meteorological network. By effectively capturing dynamic spatial-temporal interactions, our approach significantly enhances forecasting accuracy and supports adaptive weather management strategies. Experimental evaluations on two real-world datasets demonstrate that DSTFGN consistently outperforms existing baseline models across short, medium, and long-term forecasting horizons.
- 28 October 2025
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Advanced Computing and Systems
- Vol. 1 (4) , 258-274
Open AccessAn Efficient Algorithm for Weather Forecasting Using Causal Graph Neural Network
The rapid accumulation of large-scale, long-term meteorological data presents unprecedented opportunities for data-driven weather modeling and high-resolution numerical weather prediction. While various deep learning techniques—such as Long Short-Term Memory (LSTM), Recurrent Neural Networks (RNNs), and Graph Neural Networks (GNNs)—have been explored for weather forecasting, the complex spatial dependencies within historical meteorological data, particularly dynamic spatial correlations, remain insufficiently addressed. To tackle this challenge, we propose a Dynamic Spatio-Temporal Fusion Graph Network (DSTFGN), a novel module that integrates multivariate time-series analysis with graph-based causal inference to capture intricate and time-varying interdependencies among weather variables. The DSTFGN module fuses real-time inputs (e.g., sensor data, live weather feeds, external events) with historical records to model the propagation of disruptions—such as accidents or road closures—through the meteorological network. By effectively capturing dynamic spatial-temporal interactions, our approach significantly enhances forecasting accuracy and supports adaptive weather management strategies. Experimental evaluations on two real-world datasets demonstrate that DSTFGN consistently outperforms existing baseline models across short, medium, and long-term forecasting horizons.
- 1 August 2025
- Published by IOP Publishing in Physica Scripta
- Vol. 100 (8) , 085260
Consensus tracking control of incommensurate fractional order multiagent systems using sliding mode for secure communication systems
This paper presents a novel approach to secure communication systems leveraging the chaotic behavior of incommensurate fractional-order systems. The primary challenge addressed is the design of a secure and cost-efficient communication framework that ensures robust performance under uncertainties and disturbances. Unlike conventional methods that rely on single long-range transmitters, we propose a distributed system with multiple short-range transmitters. This innovation significantly enhances reliability by reducing the risk of single-point failure and lowers operational costs. To ensure security, we introduce a unique technique wherein the parameters and fractional orders of incommensurate chaotic systems are used as cryptographic keys for message encoding and decoding. To realize this, we develop a leader-follower consensus tracking methodology tailored for incommensurate fractional-order multi-agent systems. An adaptive Radial Basis Function (RBF) neural network-based sliding mode control is designed under a Lyapunov framework to estimate system uncertainties and compensate for dynamic disturbances. The effectiveness of the proposed system is demonstrated through simulations utilizing fractional Duffing and Arneodo systems. Results highlight rapid system response, the absence of overshoot in the closed-loop system, and the successful elimination of external disturbances in control design. These findings validate the practicality and robustness of the proposed approach, establishing a secure and stable communication framework based on incommensurate fractional-order chaotic systems. These results confirm the viability of our approach to ensure a stable and secure communication based on chaotic systems.
- 1 August 2025
- Published by IOP Publishing in Physica Scripta
- Vol. 100 (8) , 085260
Consensus tracking control of incommensurate fractional order multiagent systems using sliding mode for secure communication systems
This paper presents a novel approach to secure communication systems leveraging the chaotic behavior of incommensurate fractional-order systems. The primary challenge addressed is the design of a secure and cost-efficient communication framework that ensures robust performance under uncertainties and disturbances. Unlike conventional methods that rely on single long-range transmitters, we propose a distributed system with multiple short-range transmitters. This innovation significantly enhances reliability by reducing the risk of single-point failure and lowers operational costs. To ensure security, we introduce a unique technique wherein the parameters and fractional orders of incommensurate chaotic systems are used as cryptographic keys for message encoding and decoding. To realize this, we develop a leader-follower consensus tracking methodology tailored for incommensurate fractional-order multi-agent systems. An adaptive Radial Basis Function (RBF) neural network-based sliding mode control is designed under a Lyapunov framework to estimate system uncertainties and compensate for dynamic disturbances. The effectiveness of the proposed system is demonstrated through simulations utilizing fractional Duffing and Arneodo systems. Results highlight rapid system response, the absence of overshoot in the closed-loop system, and the successful elimination of external disturbances in control design. These findings validate the practicality and robustness of the proposed approach, establishing a secure and stable communication framework based on incommensurate fractional-order chaotic systems. These results confirm the viability of our approach to ensure a stable and secure communication based on chaotic systems.
- Top Cited Papers
- 25 July 2025
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 199
Dynamic multi-graph spatio-temporal learning for citywide traffic flow prediction in transportation systems
- 25 July 2025
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 199
Top Cited PapersDynamic multi-graph spatio-temporal learning for citywide traffic flow prediction in transportation systems
- Open Access
- 8 July 2025
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Advanced Computing and Systems
- Vol. 1 (3) , 117-137
A Comprehensive Survey of Deep Learning-Based Traffic Flow Prediction Models for Intelligent Transportation Systems
Traffic flow prediction is a critical component of Intelligent Transportation Systems (ITS) and smart city infrastructures. This survey paper provides a comprehensive analysis of recent advancements in deep learning-based approaches for traffic flow prediction, focusing on spatiotemporal correlations and attention mechanisms. We systematically review key representative works that propose innovative neural network architectures including DHSTNet, Att-DHSTNet, and ASTMGCNet for citywide traffic prediction. Our survey examines their methodologies, key contributions, experimental results, and comparative performance. We organize the discussion around three main themes: (1) modeling dynamic spatiotemporal dependencies, (2) attention mechanisms for traffic prediction, and (3) hybrid neural network architectures. The paper includes detailed comparison tables and conceptual figures synthesized from the reviewed works. Our analysis shows that attention-based hybrid models outperform traditional techniques, with ASTMGCNet having the lowest RMSE (4.06) and MAPE (12.56%) on benchmark datasets. We end by outlining current issues and potential research directions in this rapidly changing subject.
- 8 July 2025
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Advanced Computing and Systems
- Vol. 1 (3) , 117-137
Open AccessA Comprehensive Survey of Deep Learning-Based Traffic Flow Prediction Models for Intelligent Transportation Systems
Traffic flow prediction is a critical component of Intelligent Transportation Systems (ITS) and smart city infrastructures. This survey paper provides a comprehensive analysis of recent advancements in deep learning-based approaches for traffic flow prediction, focusing on spatiotemporal correlations and attention mechanisms. We systematically review key representative works that propose innovative neural network architectures including DHSTNet, Att-DHSTNet, and ASTMGCNet for citywide traffic prediction. Our survey examines their methodologies, key contributions, experimental results, and comparative performance. We organize the discussion around three main themes: (1) modeling dynamic spatiotemporal dependencies, (2) attention mechanisms for traffic prediction, and (3) hybrid neural network architectures. The paper includes detailed comparison tables and conceptual figures synthesized from the reviewed works. Our analysis shows that attention-based hybrid models outperform traditional techniques, with ASTMGCNet having the lowest RMSE (4.06) and MAPE (12.56%) on benchmark datasets. We end by outlining current issues and potential research directions in this rapidly changing subject.
- Open Access
- 8 July 2025
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Advanced Computing and Systems
- Vol. 1 (3) , 138-153
Advanced Hyperelliptic Curve-Based Authentication Protocols for Secure Internet of Drones Communication
The concept of an Internet of Drones (IoD) is becoming increasingly important in various domains, including surveillance and logistics. Effective communication between the interconnected systems is the essence of the Internet of Drones, however, due to the resource constraints of drones and the dynamic nature of the operating environment, security of communication within IoD networks is indeed the top priority. Considering these challenges on the part of IoD communication, a novel Hyperelliptic Curve Cryptography (HECC)-based authentication protocol is proposed in this paper to secure the data exchange between drones and their control servers and to ensure efficient communication. The proposed HECC protocol is compared with three existing protocols, Elliptic curve cryptography-based protocol with public secure authentication scheme (ECCCPSAS), Non-linear wireless unmanned aerial systems authentication scheme (NLWUAS), and the Multi-Agent System (MAS). The comparison is made among average performance metrics such as communication overhead, packet delivery ratio, throughput, and end-to-end delay. The experimental outcome assures that the HECC protocol outperforms the other protocols in terms of all metrics. The HECC-based authentication protocol reduces communication overhead by up to 30% and end-to-end delay to 75 ms while achieving a 95% packet delivery ratio and 8 Mbps throughput, outperforming ECCCPSAS, NLWUAS, and MAS across all evaluated metrics. These results confirm that HECC is a viable cryptographic solution for resource-constrained IoD deployments. Future work will focus on real-world protocol deployment and integration with quantum-resistant algorithms.
- 8 July 2025
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Advanced Computing and Systems
- Vol. 1 (3) , 138-153
Open AccessAdvanced Hyperelliptic Curve-Based Authentication Protocols for Secure Internet of Drones Communication
The concept of an Internet of Drones (IoD) is becoming increasingly important in various domains, including surveillance and logistics. Effective communication between the interconnected systems is the essence of the Internet of Drones, however, due to the resource constraints of drones and the dynamic nature of the operating environment, security of communication within IoD networks is indeed the top priority. Considering these challenges on the part of IoD communication, a novel Hyperelliptic Curve Cryptography (HECC)-based authentication protocol is proposed in this paper to secure the data exchange between drones and their control servers and to ensure efficient communication. The proposed HECC protocol is compared with three existing protocols, Elliptic curve cryptography-based protocol with public secure authentication scheme (ECCCPSAS), Non-linear wireless unmanned aerial systems authentication scheme (NLWUAS), and the Multi-Agent System (MAS). The comparison is made among average performance metrics such as communication overhead, packet delivery ratio, throughput, and end-to-end delay. The experimental outcome assures that the HECC protocol outperforms the other protocols in terms of all metrics. The HECC-based authentication protocol reduces communication overhead by up to 30% and end-to-end delay to 75 ms while achieving a 95% packet delivery ratio and 8 Mbps throughput, outperforming ECCCPSAS, NLWUAS, and MAS across all evaluated metrics. These results confirm that HECC is a viable cryptographic solution for resource-constrained IoD deployments. Future work will focus on real-world protocol deployment and integration with quantum-resistant algorithms.
- Open Access
- 25 May 2025
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Advanced Computing and Systems
- Vol. 1 (2) , 78-96
Comparing Fine-Tuned RoBERTa with Traditional Machine Learning Models for Stance Detection in Political Tweets
Stance detection identifies a text’s position or attitude toward a given subject. A major challenge in Roman Urdu is the lack of a publicly available dataset for political stance detection. To address this gap, we constructed a high-quality dataset of 8,374 political tweets and comments using the Twitter API, annotated with stance labels: agree, disagree, and unrelated. The dataset captures diverse political viewpoints and user interactions. For feature representation, we employed TF-IDF due to its effectiveness in handling high-dimensional, context-sensitive Roman Urdu text. Several machine learning classifiers were evaluated, with Random Forest achieving the highest accuracy of 95%. Additionally, we fine-tuned the transformer-based RoBERTa model, which outperformed traditional methods with 97% accuracy. Our results demonstrate the potential of combining machine learning and deep learning for stance detection in low-resource languages. This study not only introduces a novel dataset but also provides a robust evaluation of methods, highlighting the importance of modern AI techniques in processing informal and multilingual text data.
- 25 May 2025
- Published by Institute of Central Computation and Knowledge Inc. in ICCK Transactions on Advanced Computing and Systems
- Vol. 1 (2) , 78-96
Open AccessComparing Fine-Tuned RoBERTa with Traditional Machine Learning Models for Stance Detection in Political Tweets
Stance detection identifies a text’s position or attitude toward a given subject. A major challenge in Roman Urdu is the lack of a publicly available dataset for political stance detection. To address this gap, we constructed a high-quality dataset of 8,374 political tweets and comments using the Twitter API, annotated with stance labels: agree, disagree, and unrelated. The dataset captures diverse political viewpoints and user interactions. For feature representation, we employed TF-IDF due to its effectiveness in handling high-dimensional, context-sensitive Roman Urdu text. Several machine learning classifiers were evaluated, with Random Forest achieving the highest accuracy of 95%. Additionally, we fine-tuned the transformer-based RoBERTa model, which outperformed traditional methods with 97% accuracy. Our results demonstrate the potential of combining machine learning and deep learning for stance detection in low-resource languages. This study not only introduces a novel dataset but also provides a robust evaluation of methods, highlighting the importance of modern AI techniques in processing informal and multilingual text data.