Ahmed Bali
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
Ahmed Bali has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Abdelouahed Gherbi
Department of Software and IT Engineering, École de Technologie Supérieure, Montreal, Canada
5 shared publications - Mohamed Cheriet
University of Quebec
2 shared publications - Mohammed Hamdan
Synchromedia Lab, System Engineering, University of Quebec (ETS), Montreal, Canada
2 shared publications - Alvine Boaye Belle
Lassonde School of Engineering, York University, Toronto, Canada
1 shared publication - Chamseddine Talhi
Université du Québec
1 shared publication Fares Ghaleb
1 shared publication
Latest Publications
- Open Access
- 29 July 2026
- Published by Elsevier in SSRN Electronic Journal
MARL-IoTP: Heterogeneous Multi-Agent Learning for Perception-Aware Edge Orchestration
The deployment of perception-intensive applications on IoT devices imposes substantial computational demands at the network edge. A key challenge lies in the interdependence between perception model selection at IoT devices and resource orchestration at edge servers: the choice of model directly affects computational requirements, while resource availability constrains the set of feasible models. This paper presents MARL-IoTP, a hierarchical multi-agent reinforcement learning framework designed for joint optimization of perception model selection and resource orchestration. The proposed approach employs heterogeneous agent architectures-perception agents for model selection and frame rate control, and orchestration agents for task offloading and resource allocation-together with a learned communication protocol featuring attentionbased message aggregation. Using Multi-Agent Proximal Policy Optimization under the Centralized Training with Decentralized Execution paradigm, simulation-based experiments demonstrate that MARL-IoTP achieves 90.4% classification accuracy with 100.9ms mean latency and a Jain's fairness index of 0.998. Relative to Independent PPO, the proposed approach yields a 41% improvement in cumulative reward. Ablation studies indicate that inter-agent communication contributes approximately 38% of performance gains, attention-based aggregation provides 22% improvement over mean pooling, and a message dimension of 12 achieves optimal performance (reward:-415.3). The framework maintains 78.5% accuracy when scaling to 50 devices with nearlinear throughput growth in simulation.
- 29 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMARL-IoTP: Heterogeneous Multi-Agent Learning for Perception-Aware Edge Orchestration
The deployment of perception-intensive applications on IoT devices imposes substantial computational demands at the network edge. A key challenge lies in the interdependence between perception model selection at IoT devices and resource orchestration at edge servers: the choice of model directly affects computational requirements, while resource availability constrains the set of feasible models. This paper presents MARL-IoTP, a hierarchical multi-agent reinforcement learning framework designed for joint optimization of perception model selection and resource orchestration. The proposed approach employs heterogeneous agent architectures-perception agents for model selection and frame rate control, and orchestration agents for task offloading and resource allocation-together with a learned communication protocol featuring attentionbased message aggregation. Using Multi-Agent Proximal Policy Optimization under the Centralized Training with Decentralized Execution paradigm, simulation-based experiments demonstrate that MARL-IoTP achieves 90.4% classification accuracy with 100.9ms mean latency and a Jain's fairness index of 0.998. Relative to Independent PPO, the proposed approach yields a 41% improvement in cumulative reward. Ablation studies indicate that inter-agent communication contributes approximately 38% of performance gains, attention-based aggregation provides 22% improvement over mean pooling, and a message dimension of 12 achieves optimal performance (reward:-415.3). The framework maintains 78.5% accuracy when scaling to 50 devices with nearlinear throughput growth in simulation.
- Open Access
- 1 February 2024
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 36 (2)
Automatic data featurization for enhanced proactive service auto-scaling: Boosting forecasting accuracy and mitigating oscillation
- 1 February 2024
- Published by Springer Nature in Journal of King Saud University Computer and Information Sciences
- Vol. 36 (2)
Open AccessAutomatic data featurization for enhanced proactive service auto-scaling: Boosting forecasting accuracy and mitigating oscillation
- 25 December 2022
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 26 (2) , 131-147
Refocus attention span networks for handwriting line recognition
- 25 December 2022
- Published by Springer Nature in International Journal on Document Analysis and Recognition (IJDAR)
- Vol. 26 (2) , 131-147
Refocus attention span networks for handwriting line recognition
- Open Access
- 17 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (16) , 7538
Deep Learning Based Android Anomaly Detection Using a Combination of Vulnerabilities Dataset
As the leading mobile phone operating system, Android is an attractive target for malicious applications trying to exploit the system’s security vulnerabilities. Although several approaches have been proposed in the research literature for the detection of Android malwares, many of them suffer from issues such as small training datasets, there are few features (most studies are limited to permissions) that ultimately affect their performance. In order to address these issues, we propose an approach combining advanced machine learning techniques and Android vulnerabilities taken from the AndroVul dataset, which contains a novel combination of features for three different vulnerability levels, including dangerous permissions, code smells, and AndroBugs vulnerabilities. Our approach relies on that dataset to train Deep Learning (DL) and Support Vector Machine (SVM) models for the detection of Android malware. Our results show that both models are capable of detecting malware encoded in Android APK files with about 99% accuracy, which is better than the current state-of-the-art approaches.
- 17 August 2021
- Published by MDPI AG in Applied Sciences
- Vol. 11 (16) , 7538
Open AccessDeep Learning Based Android Anomaly Detection Using a Combination of Vulnerabilities Dataset
As the leading mobile phone operating system, Android is an attractive target for malicious applications trying to exploit the system’s security vulnerabilities. Although several approaches have been proposed in the research literature for the detection of Android malwares, many of them suffer from issues such as small training datasets, there are few features (most studies are limited to permissions) that ultimately affect their performance. In order to address these issues, we propose an approach combining advanced machine learning techniques and Android vulnerabilities taken from the AndroVul dataset, which contains a novel combination of features for three different vulnerability levels, including dangerous permissions, code smells, and AndroBugs vulnerabilities. Our approach relies on that dataset to train Deep Learning (DL) and Support Vector Machine (SVM) models for the detection of Android malware. Our results show that both models are capable of detecting malware encoded in Android APK files with about 99% accuracy, which is better than the current state-of-the-art approaches.
- 5 June 2020
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 11 (12) , 5895-5912
Rule based auto-scalability of IoT services for efficient edge device resource utilization
- 5 June 2020
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 11 (12) , 5895-5912
Rule based auto-scalability of IoT services for efficient edge device resource utilization
- Open Access
- 9 December 2019
- Published by Association for Computing Machinery (ACM)
- p. 43-48
Rule based lightweight approach for resources monitoring on IoT Edge devices
Edge computing is a recent tendency in the IoT domain that contributes to reduce the reliance on Cloud. This is due to the cost efficiency and the improvement of the system responsivity since services are deployed close to the data source as well as actuator nodes. However, IoT services are created on the top of a diverse and heterogeneous stack of technologies in terms of their representative hardware components. Thus, leading to some kind of barrier to accomplish system interoperability. To mitigate this heterogeneity issue, lightweight virtualization techniques such as containers have been widely adopted for IoT service deployment. However, edge devices (e.g., gateway devices) are likely to be resource-constrained, which in some cases limits their abilities to support the deployment of multiple containers. In fact, this raises the need for an effective management of resources at the edge devices. To achieve that, tools for monitoring resources consumption of container based IoT systems at the network edge level, and to launch notifications in case of any change that requires intervention are of utmost necessity. However, the current efficient monitoring tools are greedy for computing and storage resources; especially when a considerable number of IoT microservices are needed to be deployed on the same gateway. Therefore, they do not meet the constraint of limited resources when scalability is required. This work proposes a lightweight rule-based monitoring approach, taking into consideration resources needed for the monitoring process, especially with the increased number of containers deployed on IoT gateways. Our evaluation shows a significant reduction in the communication of monitoring metrics.
- 9 December 2019
- Published by Association for Computing Machinery (ACM)
- p. 43-48
Open AccessRule based lightweight approach for resources monitoring on IoT Edge devices
Edge computing is a recent tendency in the IoT domain that contributes to reduce the reliance on Cloud. This is due to the cost efficiency and the improvement of the system responsivity since services are deployed close to the data source as well as actuator nodes. However, IoT services are created on the top of a diverse and heterogeneous stack of technologies in terms of their representative hardware components. Thus, leading to some kind of barrier to accomplish system interoperability. To mitigate this heterogeneity issue, lightweight virtualization techniques such as containers have been widely adopted for IoT service deployment. However, edge devices (e.g., gateway devices) are likely to be resource-constrained, which in some cases limits their abilities to support the deployment of multiple containers. In fact, this raises the need for an effective management of resources at the edge devices. To achieve that, tools for monitoring resources consumption of container based IoT systems at the network edge level, and to launch notifications in case of any change that requires intervention are of utmost necessity. However, the current efficient monitoring tools are greedy for computing and storage resources; especially when a considerable number of IoT microservices are needed to be deployed on the same gateway. Therefore, they do not meet the constraint of limited resources when scalability is required. This work proposes a lightweight rule-based monitoring approach, taking into consideration resources needed for the monitoring process, especially with the increased number of containers deployed on IoT gateways. Our evaluation shows a significant reduction in the communication of monitoring metrics.
- 7 September 2017
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 61-79
An Ontology-Based Approach for IoT Data Processing Using Semantic Rules
- 7 September 2017
- Published by Springer Nature in Lecture Notes in Computer Science
- p. 61-79
An Ontology-Based Approach for IoT Data Processing Using Semantic Rules
- Open Access
- 1 January 2017
- Published by Elsevier in Procedia Computer Science
- Vol. 109, 592-599
Semantic-based Approach to Context Management in Ubiquitous Environment
- 1 January 2017
- Published by Elsevier in Procedia Computer Science
- Vol. 109, 592-599
Open AccessSemantic-based Approach to Context Management in Ubiquitous Environment