Amrou Zyad Benelhaouare
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Amrou Zyad Benelhaouare has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Ahmed Lakhssassi
Department of Engineering and Computer Science, University of Quebec in Outaouais, Gatineau, QC J9A 1L8, Canada
6 shared publications - Aziz Oukaira
Electrical Engineering Department, Université de Moncton, Moncton, NB E1A 3E9, Canada
2 shared publications - Emmanuel Kengne
College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua, China
2 shared publications - Idir Mellal
Department of Engineering and Computer Science, University of Quebec in Outaouais, Gatineau, QC J9A 1L8, Canada
2 shared publications - Maroua Oumlaz
Department of Computer Science and Engineering, Université du Québec en Outaouais, Gatineau, QC J8X 3X7, Canada
2 shared publications - Mohamed En-Nouar
Department of Engineering and Computer Science, University of Quebec in Outaouais (UQO), Gatineau, QC J9A 1L8, Canada
2 shared publications
Latest Publications
- Open Access
- 16 October 2026
- Published by MDPI AG in Digital Health and Innovation
- Vol. 1 (2) , 7
ExSmokerApp: An End-to-End Design Framework for Digital Phenotyping and Privacy-Aware Adaptive Smoking Cessation Support
Background: Smoking cessation remains a major public health challenge, with more than 75% of individuals returning to smoking within six months of a quit attempt. Despite the growing availability of mobile health (mHealth) applications, many existing solutions lack integrated behavioral monitoring, privacy-aware data processing, and adaptive intervention mechanisms. Methods: This study presents ExSmokerApp, an end-to-end design framework for smoking cessation support and relapse prevention based on Digital Phenotyping. The framework combines a structured pre-quit preparation phase with post-quit behavioral monitoring, Ecological Momentary Assessment (EMA), and a crisis-support module. It further defines a privacy-aware edge–cloud architecture and outlines a future on-device machine learning pipeline for relapse-risk estimation and Just-in-Time Adaptive Interventions (JITAIs). Results: The ExSmokerApp design framework has been developed with a functional mobile application and supporting backend infrastructure, incorporating behavioral data collection, local storage, cloud synchronization, and preliminary technical testing. The resulting architecture establishes a methodological foundation for future machine-learning development, while predictive models, automated risk detection, and clinical effectiveness remain to be evaluated. Conclusions: ExSmokerApp establishes a clearly defined and reproducible architectural and methodological framework that other engineers and researchers can adapt and implement for smoking cessation applications. Future beta testing will assess technical feasibility, usability, behavioral data collection, and the potential for subsequent predictive-model development and validation.
- 16 October 2026
- Published by MDPI AG in Digital Health and Innovation
- Vol. 1 (2) , 7
Open AccessExSmokerApp: An End-to-End Design Framework for Digital Phenotyping and Privacy-Aware Adaptive Smoking Cessation Support
Background: Smoking cessation remains a major public health challenge, with more than 75% of individuals returning to smoking within six months of a quit attempt. Despite the growing availability of mobile health (mHealth) applications, many existing solutions lack integrated behavioral monitoring, privacy-aware data processing, and adaptive intervention mechanisms. Methods: This study presents ExSmokerApp, an end-to-end design framework for smoking cessation support and relapse prevention based on Digital Phenotyping. The framework combines a structured pre-quit preparation phase with post-quit behavioral monitoring, Ecological Momentary Assessment (EMA), and a crisis-support module. It further defines a privacy-aware edge–cloud architecture and outlines a future on-device machine learning pipeline for relapse-risk estimation and Just-in-Time Adaptive Interventions (JITAIs). Results: The ExSmokerApp design framework has been developed with a functional mobile application and supporting backend infrastructure, incorporating behavioral data collection, local storage, cloud synchronization, and preliminary technical testing. The resulting architecture establishes a methodological foundation for future machine-learning development, while predictive models, automated risk detection, and clinical effectiveness remain to be evaluated. Conclusions: ExSmokerApp establishes a clearly defined and reproducible architectural and methodological framework that other engineers and researchers can adapt and implement for smoking cessation applications. Future beta testing will assess technical feasibility, usability, behavioral data collection, and the potential for subsequent predictive-model development and validation.
- Open Access
AI-Enabled Digital Twin Framework for TSCA-like Anomaly Detection in FPGA-SoC-Based Industrial Cyber-Physical Systems
Field-Programmable Gate Array System-on-Chip (FPGA-SoC) platforms are increasingly adopted in modern industrial Cyber-Physical Systems (CPSs), enabling real-time control, monitoring, and automation of critical industrial processes. The increasing integration density of modern FPGA-SoC architectures introduces new thermal security challenges, where heat evolves from a reliability concern into a potential source of information leakage. Thermal Side-Channel Attacks (TSCAs) exploit runtime thermal variations to infer sensitive operational, architectural, or cryptographic information from the underlying hardware. While this study is centered on FPGA-SoC platforms, comparable thermal security challenges are increasingly reported across other densely integrated computing architectures, including Multiprocessor System-on-Chip (MPSoC), System-in-Package (SiP), and emerging Three-Dimensional Integrated Circuit (3D-IC) technologies. Consequently, the detection of thermal side-channel intrusions has become a critical hardware security challenge for next generation industrial CPS infrastructures. To address this challenge, an AI-enabled Digital Twin (DT) framework is introduced for TSCA detection in densely integrated FPGA-SoC microarchitectures. By combining thermal behavioral modeling, feature engineering, and machine learning-based anomaly detection, the proposed framework extends conventional Thermal Digital Twin (TDT) approaches beyond monitoring and mitigation toward autonomous thermal threat detection. The proposed framework is experimentally validated using an NI myRIO-1900 platform integrating a Xilinx Zynq-7010 FPGA-SoC representative of modern industrial embedded control architectures. Experimental results demonstrate the feasibility of the proposed framework, achieving an accuracy of approximately 75% with an Area Under the ROC Curve (AUC) of 0.76 using a lightweight Isolation Forest model. These results validate the capability of the proposed AI-enabled Digital Twin framework to learn normal thermal behavioral patterns and autonomously detect anomalous thermal activities potentially related to TSCAs.
Open AccessAI-Enabled Digital Twin Framework for TSCA-like Anomaly Detection in FPGA-SoC-Based Industrial Cyber-Physical Systems
Field-Programmable Gate Array System-on-Chip (FPGA-SoC) platforms are increasingly adopted in modern industrial Cyber-Physical Systems (CPSs), enabling real-time control, monitoring, and automation of critical industrial processes. The increasing integration density of modern FPGA-SoC architectures introduces new thermal security challenges, where heat evolves from a reliability concern into a potential source of information leakage. Thermal Side-Channel Attacks (TSCAs) exploit runtime thermal variations to infer sensitive operational, architectural, or cryptographic information from the underlying hardware. While this study is centered on FPGA-SoC platforms, comparable thermal security challenges are increasingly reported across other densely integrated computing architectures, including Multiprocessor System-on-Chip (MPSoC), System-in-Package (SiP), and emerging Three-Dimensional Integrated Circuit (3D-IC) technologies. Consequently, the detection of thermal side-channel intrusions has become a critical hardware security challenge for next generation industrial CPS infrastructures. To address this challenge, an AI-enabled Digital Twin (DT) framework is introduced for TSCA detection in densely integrated FPGA-SoC microarchitectures. By combining thermal behavioral modeling, feature engineering, and machine learning-based anomaly detection, the proposed framework extends conventional Thermal Digital Twin (TDT) approaches beyond monitoring and mitigation toward autonomous thermal threat detection. The proposed framework is experimentally validated using an NI myRIO-1900 platform integrating a Xilinx Zynq-7010 FPGA-SoC representative of modern industrial embedded control architectures. Experimental results demonstrate the feasibility of the proposed framework, achieving an accuracy of approximately 75% with an Area Under the ROC Curve (AUC) of 0.76 using a lightweight Isolation Forest model. These results validate the capability of the proposed AI-enabled Digital Twin framework to learn normal thermal behavioral patterns and autonomously detect anomalous thermal activities potentially related to TSCAs.
- Open Access
- 11 October 2025
- Published by MDPI AG in Micromachines
- Vol. 16 (10) , 1152
Thermal Side-Channel Threats in Densely Integrated Microarchitectures: A Comprehensive Review for Cyber–Physical System Security
Densely integrated microarchitectures spanning three-dimensional integrated circuits (3D-ICs), chiplet-based designs, and system-in-package (SiP) assemblies make heat a first-order security concern rather than a mere reliability issue. This review consolidates the landscape of thermal side-channel attacks (TSCAs) on densely integrated microarchitectures: we systematize observation vectors and threat models, clarify core concepts and assumptions, compare the most credible evidence from the past decade, and distill the main classes of defenses across the hardware–software stack. We also explain why hardening against thermal leakage is integral to cyber–physical system (CPS) security and outline the most promising research directions for the field. The strategic relevance of this agenda is reflected in current policy and funding momentum, including initiatives by the United States Department of Homeland Security and the Cybersecurity and Infrastructure Security Agency (DHS/CISA) on operational technology (OT) security, programs by the National Science Foundation (NSF) on CPS, and Canada’s Regional Artificial Intelligence Initiative and Cyber-Physical Resilience Program (RAII, >CAD 35 million), to bridge advanced microelectronics with next-generation cybersecurity. This survey offers a clear, high-level map of the problem space and a focused baseline for future work.
- 11 October 2025
- Published by MDPI AG in Micromachines
- Vol. 16 (10) , 1152
Open AccessThermal Side-Channel Threats in Densely Integrated Microarchitectures: A Comprehensive Review for Cyber–Physical System Security
Densely integrated microarchitectures spanning three-dimensional integrated circuits (3D-ICs), chiplet-based designs, and system-in-package (SiP) assemblies make heat a first-order security concern rather than a mere reliability issue. This review consolidates the landscape of thermal side-channel attacks (TSCAs) on densely integrated microarchitectures: we systematize observation vectors and threat models, clarify core concepts and assumptions, compare the most credible evidence from the past decade, and distill the main classes of defenses across the hardware–software stack. We also explain why hardening against thermal leakage is integral to cyber–physical system (CPS) security and outline the most promising research directions for the field. The strategic relevance of this agenda is reflected in current policy and funding momentum, including initiatives by the United States Department of Homeland Security and the Cybersecurity and Infrastructure Security Agency (DHS/CISA) on operational technology (OT) security, programs by the National Science Foundation (NSF) on CPS, and Canada’s Regional Artificial Intelligence Initiative and Cyber-Physical Resilience Program (RAII, >CAD 35 million), to bridge advanced microelectronics with next-generation cybersecurity. This survey offers a clear, high-level map of the problem space and a focused baseline for future work.
- Open Access
- 7 November 2024
- Published by MDPI AG in Electronics
- Vol. 13 (22) , 4369
Advancing Pulmonary Nodule Detection with ARSGNet: EfficientNet and Transformer Synergy
Lung cancer, the leading cause of cancer-related deaths globally, presents significant challenges in early detection and diagnosis. The effective analysis of pulmonary medical imaging, particularly computed tomography (CT) scans, is critical in this endeavor. Traditional diagnostic methods, which are manual and time-intensive, underscore the need for innovative, efficient, and accurate detection approaches. To address this need, we introduce the Adaptive Range Slice Grouping Network (ARSGNet), a novel deep learning framework that enhances early lung cancer diagnosis through advanced segmentation and classification techniques in CT imaging. ARSGNet synergistically integrates the strengths of EfficientNet and Transformer architectures, leveraging their superior feature extraction and contextual processing capabilities. This hybrid model proficiently handles the complexities of 3D CT images, ensuring precise and reliable lung nodule detection. The algorithm processes CT scans using short slice grouping (SSG) and long slice grouping (LSG) techniques to extract critical features from each slice, culminating in the generation of nodule probabilities and the identification of potential nodular regions. Incorporating shapley additive explanations (SHAP) analysis further enhances model interpretability by highlighting the contributory features. Our extensive experimentation demonstrated a significant improvement in diagnostic accuracy, with training accuracy increasing from 0.9126 to 0.9817. This advancement not only reflects the model’s efficient learning curve but also its high proficiency in accurately classifying a majority of training samples. Given its high accuracy, interpretability, and consistent reduction in training loss, ARSGNet holds substantial potential as a groundbreaking tool for early lung cancer detection and diagnosis.
- 7 November 2024
- Published by MDPI AG in Electronics
- Vol. 13 (22) , 4369
Open AccessAdvancing Pulmonary Nodule Detection with ARSGNet: EfficientNet and Transformer Synergy
Lung cancer, the leading cause of cancer-related deaths globally, presents significant challenges in early detection and diagnosis. The effective analysis of pulmonary medical imaging, particularly computed tomography (CT) scans, is critical in this endeavor. Traditional diagnostic methods, which are manual and time-intensive, underscore the need for innovative, efficient, and accurate detection approaches. To address this need, we introduce the Adaptive Range Slice Grouping Network (ARSGNet), a novel deep learning framework that enhances early lung cancer diagnosis through advanced segmentation and classification techniques in CT imaging. ARSGNet synergistically integrates the strengths of EfficientNet and Transformer architectures, leveraging their superior feature extraction and contextual processing capabilities. This hybrid model proficiently handles the complexities of 3D CT images, ensuring precise and reliable lung nodule detection. The algorithm processes CT scans using short slice grouping (SSG) and long slice grouping (LSG) techniques to extract critical features from each slice, culminating in the generation of nodule probabilities and the identification of potential nodular regions. Incorporating shapley additive explanations (SHAP) analysis further enhances model interpretability by highlighting the contributory features. Our extensive experimentation demonstrated a significant improvement in diagnostic accuracy, with training accuracy increasing from 0.9126 to 0.9817. This advancement not only reflects the model’s efficient learning curve but also its high proficiency in accurately classifying a majority of training samples. Given its high accuracy, interpretability, and consistent reduction in training loss, ARSGNet holds substantial potential as a groundbreaking tool for early lung cancer detection and diagnosis.
- Open Access
- 24 October 2024
- Published by MDPI AG in Electronics
- Vol. 13 (21) , 4176
Mitigating Thermal Side-Channel Vulnerabilities in FPGA-Based SiP Systems Through Advanced Thermal Management and Security Integration Using Thermal Digital Twin (TDT) Technology
Side-channel attacks (SCAs) are powerful techniques used to recover keys from electronic devices by exploiting various physical leakages, such as power, timing, and heat. Although heat is one of the less frequently analyzed channels due to the high noise associated with thermal traces, it poses a significant and growing threat to the security of very large-scale integrated (VLSI) microsystems, particularly system in package (SiP) technologies. Thermal side-channel attacks (TSCAs) exploit temperature variations, risking not only hardware damage from excessive heat dissipation but also enabling the extraction of sensitive data, like cryptographic keys, by observing thermal patterns. This dual threat underscores the need for a synergistic approach to thermal management and security in designing integrated microsystems. In response, this paper presents a novel approach that improves the early detection of abnormal thermal fluctuations in SiP designs, preventing cybercriminals from exploiting such anomalies to extract sensitive information for malicious purposes. Our approach employs a new concept called Thermal Digital Twin (TDT), which integrates two previously separate methods and techniques, resulting in successful outcomes. It combines the gradient direction sensor scan (GDSSCAN) to capture thermal data from the physical field programmable gate array (FPGA), which guarantees rapid thermal scan with a measurement period that could be close to a resolution of C, and a temperature range from −C to C; once the data are transmitted in real time to a Digital Twin created in COMSOL Multiphysics® 6.0 for simulation using the Finite Element Method (FEM), the real time required by the CPU to perform all the necessary calculations can extend to several seconds or minutes. This integration allows for a detailed analysis of thermal transfer within the SiP model of our FPGA. Implementation and simulations demonstrate that the Thermal Digital Twin (TDT) approach could reduce the risks associated with TSCA by a significant percentage, thereby enhancing the security of FPGA systems against thermal threats.- 24 October 2024
- Published by MDPI AG in Electronics
- Vol. 13 (21) , 4176
Open AccessMitigating Thermal Side-Channel Vulnerabilities in FPGA-Based SiP Systems Through Advanced Thermal Management and Security Integration Using Thermal Digital Twin (TDT) Technology
Side-channel attacks (SCAs) are powerful techniques used to recover keys from electronic devices by exploiting various physical leakages, such as power, timing, and heat. Although heat is one of the less frequently analyzed channels due to the high noise associated with thermal traces, it poses a significant and growing threat to the security of very large-scale integrated (VLSI) microsystems, particularly system in package (SiP) technologies. Thermal side-channel attacks (TSCAs) exploit temperature variations, risking not only hardware damage from excessive heat dissipation but also enabling the extraction of sensitive data, like cryptographic keys, by observing thermal patterns. This dual threat underscores the need for a synergistic approach to thermal management and security in designing integrated microsystems. In response, this paper presents a novel approach that improves the early detection of abnormal thermal fluctuations in SiP designs, preventing cybercriminals from exploiting such anomalies to extract sensitive information for malicious purposes. Our approach employs a new concept called Thermal Digital Twin (TDT), which integrates two previously separate methods and techniques, resulting in successful outcomes. It combines the gradient direction sensor scan (GDSSCAN) to capture thermal data from the physical field programmable gate array (FPGA), which guarantees rapid thermal scan with a measurement period that could be close to a resolution of C, and a temperature range from −C to C; once the data are transmitted in real time to a Digital Twin created in COMSOL Multiphysics® 6.0 for simulation using the Finite Element Method (FEM), the real time required by the CPU to perform all the necessary calculations can extend to several seconds or minutes. This integration allows for a detailed analysis of thermal transfer within the SiP model of our FPGA. Implementation and simulations demonstrate that the Thermal Digital Twin (TDT) approach could reduce the risks associated with TSCA by a significant percentage, thereby enhancing the security of FPGA systems against thermal threats. - Open Access
FPGA-Embedded Smart Monitoring System for Irrigation Decisions Based on Soil Moisture and Temperature Sensors
The basic need common to all living beings is water. Less than 1% of the water on earth is fresh water and water use is increasing daily. Agricultural practices alone require huge amounts of water. The drip technique improved the efficiency of water use in irrigation and initiated the introduction and development of fertigation, the integrated distribution of water and fertilizer. The past few decades have seen extensive research being carried out in the area of development and evaluation of different technologies available to estimate/measure soil moisture to aid in various applications and to facilitate the use of drip irrigation for users and farmers. In this technology, plant moisture and temperature are accurately monitored and controlled in real time over roots in the form of droplets, by developing smart monitoring system to save water and avoid water waste using drip irrigation technology. Water is delivered to the roots drop by drop, which saves water as well as prevents plants from being flooded and decaying due to excess water released by irrigation methods such as flood irrigation, border irrigation, furrow irrigation, and control basin irrigation. Drip irrigation with an embedded intelligent monitoring system is one of the most valuable techniques used to save water and farmers’ time and energy. In this paper, we design an embedded monitoring system based in the integrated 65 nm CMOS technology in agricultural practices which would facilitate agriculture and enable farmers to monitor crops. Hence, to demonstrate the feasibility, a prototype was constructed and simulated with modelsim and validated with nclaunch the both tools from Cadence, as well as implementation on the FPGA board, was be performed.
Open AccessFPGA-Embedded Smart Monitoring System for Irrigation Decisions Based on Soil Moisture and Temperature Sensors
The basic need common to all living beings is water. Less than 1% of the water on earth is fresh water and water use is increasing daily. Agricultural practices alone require huge amounts of water. The drip technique improved the efficiency of water use in irrigation and initiated the introduction and development of fertigation, the integrated distribution of water and fertilizer. The past few decades have seen extensive research being carried out in the area of development and evaluation of different technologies available to estimate/measure soil moisture to aid in various applications and to facilitate the use of drip irrigation for users and farmers. In this technology, plant moisture and temperature are accurately monitored and controlled in real time over roots in the form of droplets, by developing smart monitoring system to save water and avoid water waste using drip irrigation technology. Water is delivered to the roots drop by drop, which saves water as well as prevents plants from being flooded and decaying due to excess water released by irrigation methods such as flood irrigation, border irrigation, furrow irrigation, and control basin irrigation. Drip irrigation with an embedded intelligent monitoring system is one of the most valuable techniques used to save water and farmers’ time and energy. In this paper, we design an embedded monitoring system based in the integrated 65 nm CMOS technology in agricultural practices which would facilitate agriculture and enable farmers to monitor crops. Hence, to demonstrate the feasibility, a prototype was constructed and simulated with modelsim and validated with nclaunch the both tools from Cadence, as well as implementation on the FPGA board, was be performed.