Mohamad Abou Ali
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohamad Abou Ali has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Fadi Dornaika
University of the Basque Country UPV/EHU, San Sebastian, Spain
18 shared publications - Ignacio Arganda-Carreras
Dept. of Computer Science and Artificial Intelligence, University of the Basque Country (UPV/EHU), San Sebastian, Spain
10 shared publications - Hussein Ali
University of the Basque Country EHU, San Sebastian, Spain
4 shared publications - Jinan Charafeddine
De Vinci Higher Education, De Vinci Research Center, Paris, France
4 shared publications - Abdallah Kassem
Notre Dame University
3 shared publications - Ali Cherry
Lebanese International University
2 shared publications
Latest Publications
- 6 October 2026
- Published by Springer Nature
- p. 181-204
AI-Driven Peripheral Blood Smear Analysis Using YOLOv11 for Infectious Disease and Pandemic Management
- 6 October 2026
- Published by Springer Nature
- p. 181-204
AI-Driven Peripheral Blood Smear Analysis Using YOLOv11 for Infectious Disease and Pandemic Management
- Open Access
- 30 July 2026
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (12)
Automated machine learning in the era of large language models: a systematic review of green, trustworthy, and human-centered automation (2020–2026)
Automated Machine Learning (AutoML) has rapidly transformed the landscape of artificial intelligence by democratizing access to sophisticated machine learning models and streamlining complex development workflows. This systematic review, conducted in accordance with the PRISMA 2020 guidelines, comprehensively analyzes the evolution of AutoML from 2020 to early 2026 (final search conducted in early February 2026), with a particular focus on the integration of Large Language Models (LLMs) and the emerging paradigm of Green AutoML. Based on a systematic search of IEEE Xplore, ACM Digital Library, ScienceDirect, arXiv, and Google Scholar, 103 studies meeting all eligibility criteria were included in the qualitative synthesis. We synthesize key architectural shifts, evaluate the impact of LLMs on the AutoML pipeline, and assess the progress toward sustainable and energy-efficient AI solutions. The review also identifies critical research gaps—especially concerning trustworthiness, interpretability, and human-in-the-loop integration—and proposes a strategic roadmap for future research. Our findings highlight a significant transition from traditional Hyperparameter Optimization (HPO) and Neural Architecture Search (NAS) toward LLM-driven generative AutoML systems, alongside a growing imperative for environmentally conscious AI development. This work provides a structured overview for researchers and practitioners, offering a novel taxonomy of LLM-integrated AutoML systems, a comprehensive evaluation of energy-efficiency metrics, and a roadmap for Human-in-the-Loop (HITL) AutoML. Collectively, these contributions support the development of more robust, ethical, and sustainable automated machine learning solutions.
- 30 July 2026
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (12)
Open AccessAutomated machine learning in the era of large language models: a systematic review of green, trustworthy, and human-centered automation (2020–2026)
Automated Machine Learning (AutoML) has rapidly transformed the landscape of artificial intelligence by democratizing access to sophisticated machine learning models and streamlining complex development workflows. This systematic review, conducted in accordance with the PRISMA 2020 guidelines, comprehensively analyzes the evolution of AutoML from 2020 to early 2026 (final search conducted in early February 2026), with a particular focus on the integration of Large Language Models (LLMs) and the emerging paradigm of Green AutoML. Based on a systematic search of IEEE Xplore, ACM Digital Library, ScienceDirect, arXiv, and Google Scholar, 103 studies meeting all eligibility criteria were included in the qualitative synthesis. We synthesize key architectural shifts, evaluate the impact of LLMs on the AutoML pipeline, and assess the progress toward sustainable and energy-efficient AI solutions. The review also identifies critical research gaps—especially concerning trustworthiness, interpretability, and human-in-the-loop integration—and proposes a strategic roadmap for future research. Our findings highlight a significant transition from traditional Hyperparameter Optimization (HPO) and Neural Architecture Search (NAS) toward LLM-driven generative AutoML systems, alongside a growing imperative for environmentally conscious AI development. This work provides a structured overview for researchers and practitioners, offering a novel taxonomy of LLM-integrated AutoML systems, a comprehensive evaluation of energy-efficiency metrics, and a roadmap for Human-in-the-Loop (HITL) AutoML. Collectively, these contributions support the development of more robust, ethical, and sustainable automated machine learning solutions.
- Open Access
- 20 July 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 181
Edge artificial intelligence: Past advances, current paradigms, and emerging horizons
- 20 July 2026
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 181
Open AccessEdge artificial intelligence: Past advances, current paradigms, and emerging horizons
- Open Access
- 12 July 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (7) , 235
From Static Pages to Symbiotic Intelligence: The CET-WAIP Framework for Understanding AI–Web Coevolution
The convergence of the World Wide Web and artificial intelligence (AI) has fundamentally reconfigured digital ecosystems. Yet conventional generational models—Web 1.0 through 4.0—remain inadequate for capturing the recursive, mutually constitutive dynamics that characterize this coevolution. The historical trajectory of the Web reveals a progressive expansion of human agency: Web 1.0 afforded read access; Web 2.0 enabled user-generated content; Web 3.0 introduced digital ownership. Artificial intelligence has followed a parallel arc. Early generative systems, such as ChatGPT, demonstrated read capabilities—conditional upon human authorization. Subsequent code-generation agents, including Codex and Claude Code, extended this to write capabilities—also contingent upon human approval, initiation, and financial compensation. Web 4.0, however, constitutes a qualitative rupture: AI agents now read, write, own, earn, and transact autonomously, without requiring human oversight. Such automatons operate on their own behalf or on the behalf of a creator who may be human, another agent, or entirely absent. In the Web 4.0 paradigm, the end user is no longer human—it is AI itself. This review addresses the analytical inadequacy of existing models by introducing the CET-WAIP framework (CoEvolutionary Tiers of Web and AI Paradigms), a novel classificatory framework that models AI–Web coevolution across seven intelligence tiers spanning infrastructural complexity, cognitive capabilities, and governance dimensions. Grounded in an integrative literature review with PRISMA-informed reporting, the framework aligns key AI paradigms—from rule-based systems to agentic AI—with corresponding transformations in Web architecture, revealing how intelligence scaling reshapes user agency, data structures, and ethical oversight. To demonstrate its analytical utility, we conduct a multi-tiered analysis of ChatGPT and compare it with open-source agentic systems (AutoGPT, LangChain, Sora), showing how architectural dissonance between cognitive capabilities and infrastructure is systematically diagnosable. The findings highlight the limitations of linear Web evolution frameworks and underscore the need for intelligence-centric approaches that integrate technological, cognitive, and governance dimensions. We conclude by outlining a research agenda for hybrid intelligence, adaptive governance, and equitable human–AI collaboration in ecosystems where both human and non-human agents participate as first-class actors.
- 12 July 2026
- Published by MDPI AG in Big Data and Cognitive Computing
- Vol. 10 (7) , 235
Open AccessFrom Static Pages to Symbiotic Intelligence: The CET-WAIP Framework for Understanding AI–Web Coevolution
The convergence of the World Wide Web and artificial intelligence (AI) has fundamentally reconfigured digital ecosystems. Yet conventional generational models—Web 1.0 through 4.0—remain inadequate for capturing the recursive, mutually constitutive dynamics that characterize this coevolution. The historical trajectory of the Web reveals a progressive expansion of human agency: Web 1.0 afforded read access; Web 2.0 enabled user-generated content; Web 3.0 introduced digital ownership. Artificial intelligence has followed a parallel arc. Early generative systems, such as ChatGPT, demonstrated read capabilities—conditional upon human authorization. Subsequent code-generation agents, including Codex and Claude Code, extended this to write capabilities—also contingent upon human approval, initiation, and financial compensation. Web 4.0, however, constitutes a qualitative rupture: AI agents now read, write, own, earn, and transact autonomously, without requiring human oversight. Such automatons operate on their own behalf or on the behalf of a creator who may be human, another agent, or entirely absent. In the Web 4.0 paradigm, the end user is no longer human—it is AI itself. This review addresses the analytical inadequacy of existing models by introducing the CET-WAIP framework (CoEvolutionary Tiers of Web and AI Paradigms), a novel classificatory framework that models AI–Web coevolution across seven intelligence tiers spanning infrastructural complexity, cognitive capabilities, and governance dimensions. Grounded in an integrative literature review with PRISMA-informed reporting, the framework aligns key AI paradigms—from rule-based systems to agentic AI—with corresponding transformations in Web architecture, revealing how intelligence scaling reshapes user agency, data structures, and ethical oversight. To demonstrate its analytical utility, we conduct a multi-tiered analysis of ChatGPT and compare it with open-source agentic systems (AutoGPT, LangChain, Sora), showing how architectural dissonance between cognitive capabilities and infrastructure is systematically diagnosable. The findings highlight the limitations of linear Web evolution frameworks and underscore the need for intelligence-centric approaches that integrate technological, cognitive, and governance dimensions. We conclude by outlining a research agenda for hybrid intelligence, adaptive governance, and equitable human–AI collaboration in ecosystems where both human and non-human agents participate as first-class actors.
- Top Cited PapersOpen Access
- 14 November 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (1) , 11
Agentic AI: a comprehensive survey of architectures, applications, and future directions
Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models—a practice known as conceptual retrofitting . This survey cuts through this confusion by introducing a novel dual-paradigm framework that categorizes agentic systems into two distinct lineages: the symbolic/classical (relying on algorithmic planning and persistent state) and the neural/generative (leveraging stochastic generation and prompt-driven orchestration). Through a systematic PRISMA-based review of 90 studies (2018–2025), we provide a comprehensive analysis structured around this framework across three dimensions: (1) the theoretical foundations and architectural principles defining each paradigm; (2) domain-specific implementations in healthcare, finance, and robotics, demonstrating how application constraints dictate paradigm selection; and (3) paradigm-specific ethical and governance challenges, revealing divergent risks and mitigation strategies. Our analysis reveals that the choice of paradigm is strategic: symbolic systems dominate safety-critical domains (e.g., healthcare), while neural systems prevail in adaptive, data-rich environments (e.g., finance). Furthermore, we identify critical research gaps, including a significant deficit in governance models for symbolic systems and a pressing need for hybrid neuro-symbolic architectures. The findings culminate in a strategic roadmap arguing that the future of Agentic AI lies not in the dominance of one paradigm, but in their intentional integration to create systems that are both adaptable and reliable . This work provides the essential conceptual toolkit to guide future research, development, and policy toward robust and trustworthy hybrid intelligent systems.
- 14 November 2025
- Published by Springer Nature in Artificial Intelligence Review
- Vol. 59 (1) , 11
Top Cited PapersOpen AccessAgentic AI: a comprehensive survey of architectures, applications, and future directions
Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models—a practice known as conceptual retrofitting . This survey cuts through this confusion by introducing a novel dual-paradigm framework that categorizes agentic systems into two distinct lineages: the symbolic/classical (relying on algorithmic planning and persistent state) and the neural/generative (leveraging stochastic generation and prompt-driven orchestration). Through a systematic PRISMA-based review of 90 studies (2018–2025), we provide a comprehensive analysis structured around this framework across three dimensions: (1) the theoretical foundations and architectural principles defining each paradigm; (2) domain-specific implementations in healthcare, finance, and robotics, demonstrating how application constraints dictate paradigm selection; and (3) paradigm-specific ethical and governance challenges, revealing divergent risks and mitigation strategies. Our analysis reveals that the choice of paradigm is strategic: symbolic systems dominate safety-critical domains (e.g., healthcare), while neural systems prevail in adaptive, data-rich environments (e.g., finance). Furthermore, we identify critical research gaps, including a significant deficit in governance models for symbolic systems and a pressing need for hybrid neuro-symbolic architectures. The findings culminate in a strategic roadmap arguing that the future of Agentic AI lies not in the dominance of one paradigm, but in their intentional integration to create systems that are both adaptable and reliable . This work provides the essential conceptual toolkit to guide future research, development, and policy toward robust and trustworthy hybrid intelligent systems.
- Open Access
Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions
Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice known as conceptual retrofitting. This survey cuts through this confusion by introducing a novel dual-paradigm framework that categorizes agentic systems into two distinct lineages: the Symbolic/Classical (relying on algorithmic planning and persistent state) and the Neural/Generative (leveraging stochastic generation and prompt-driven orchestration). Through a systematic PRISMA-based review of 90 studies (2018--2025), we provide a comprehensive analysis structured around this framework across three dimensions: (1) the theoretical foundations and architectural principles defining each paradigm; (2) domain-specific implementations in healthcare, finance, and robotics, demonstrating how application constraints dictate paradigm selection; and (3) paradigm-specific ethical and governance challenges, revealing divergent risks and mitigation strategies. Our analysis reveals that the choice of paradigm is strategic: symbolic systems dominate safety-critical domains (e.g., healthcare), while neural systems prevail in adaptive, data-rich environments (e.g., finance). Furthermore, we identify critical research gaps, including a significant deficit in governance models for symbolic systems and a pressing need for hybrid neuro-symbolic architectures. The findings culminate in a strategic roadmap arguing that the future of Agentic AI lies not in the dominance of one paradigm, but in their intentional integration to create systems that are both adaptable and reliable. This work provides the essential conceptual toolkit to guide future research, development, and policy toward robust and trustworthy hybrid intelligent systems.
Open AccessAgentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions
Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice known as conceptual retrofitting. This survey cuts through this confusion by introducing a novel dual-paradigm framework that categorizes agentic systems into two distinct lineages: the Symbolic/Classical (relying on algorithmic planning and persistent state) and the Neural/Generative (leveraging stochastic generation and prompt-driven orchestration). Through a systematic PRISMA-based review of 90 studies (2018--2025), we provide a comprehensive analysis structured around this framework across three dimensions: (1) the theoretical foundations and architectural principles defining each paradigm; (2) domain-specific implementations in healthcare, finance, and robotics, demonstrating how application constraints dictate paradigm selection; and (3) paradigm-specific ethical and governance challenges, revealing divergent risks and mitigation strategies. Our analysis reveals that the choice of paradigm is strategic: symbolic systems dominate safety-critical domains (e.g., healthcare), while neural systems prevail in adaptive, data-rich environments (e.g., finance). Furthermore, we identify critical research gaps, including a significant deficit in governance models for symbolic systems and a pressing need for hybrid neuro-symbolic architectures. The findings culminate in a strategic roadmap arguing that the future of Agentic AI lies not in the dominance of one paradigm, but in their intentional integration to create systems that are both adaptable and reliable. This work provides the essential conceptual toolkit to guide future research, development, and policy toward robust and trustworthy hybrid intelligent systems.
- Open Access
Edge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons
Edge Artificial Intelligence (Edge AI) embeds intelligence directly into devices at the network edge, enabling real-time processing with improved privacy and reduced latency by processing data close to its source. This review systematically examines the evolution, current landscape, and future directions of Edge AI through a multi-dimensional taxonomy including deployment location, processing capabilities such as TinyML and federated learning, application domains, and hardware types. Following PRISMA guidelines, the analysis traces the field from early content delivery networks and fog computing to modern on-device intelligence. Core enabling technologies such as specialized hardware accelerators, optimized software, and communication protocols are explored. Challenges including resource limitations, security, model management, power consumption, and connectivity are critically assessed. Emerging opportunities in neuromorphic hardware, continual learning algorithms, edge-cloud collaboration, and trustworthiness integration are highlighted, providing a comprehensive framework for researchers and practitioners.
Open AccessEdge Artificial Intelligence: A Systematic Review of Evolution, Taxonomic Frameworks, and Future Horizons
Edge Artificial Intelligence (Edge AI) embeds intelligence directly into devices at the network edge, enabling real-time processing with improved privacy and reduced latency by processing data close to its source. This review systematically examines the evolution, current landscape, and future directions of Edge AI through a multi-dimensional taxonomy including deployment location, processing capabilities such as TinyML and federated learning, application domains, and hardware types. Following PRISMA guidelines, the analysis traces the field from early content delivery networks and fog computing to modern on-device intelligence. Core enabling technologies such as specialized hardware accelerators, optimized software, and communication protocols are explored. Challenges including resource limitations, security, model management, power consumption, and connectivity are critically assessed. Emerging opportunities in neuromorphic hardware, continual learning algorithms, edge-cloud collaboration, and trustworthiness integration are highlighted, providing a comprehensive framework for researchers and practitioners.
- Open Access
Comprehensive Benchmarking of YOLOv11 Architectures for Scalable and Granular Peripheral Blood Cell Detection
Manual peripheral blood smear (PBS) analysis is labor intensive and subjective. While deep learning offers a promising alternative, a systematic evaluation of state of the art models such as YOLOv11 for fine grained PBS detection is still lacking. In this work, we make two key contributions. First, we curate a large scale annotated dataset for blood cell detection and classification, comprising 16,891 images across 12 peripheral blood cell (PBC) classes, along with the red blood cell class, all carefully re annotated for object detection tasks. In total, the dataset contains 298,850 annotated cells. Second, we leverage this dataset to conduct a comprehensive evaluation of five YOLOv11 variants (ranging from Nano to XLarge). These models are rigorously benchmarked under two data splitting strategies (70:20:10 and 80:10:10) and systematically assessed using multiple performance criteria, including mean Average Precision (mAP), precision, recall, F1 score, and computational efficiency. Our experiments show that the YOLOv11 Medium variant achieves the best trade off, reaching a mAP@0.5 of 0.934 under the 8:1:1 split. Larger models (Large and XLarge) provide only marginal accuracy gains at substantially higher computational cost. Moreover, the 8:1:1 split consistently outperforms the 7:2:1 split across all models. These findings highlight YOLOv11, particularly the Medium variant, as a highly effective framework for automated, fine grained PBS detection. Beyond benchmarking, our publicly released dataset (github.com/Mohamad-AbouAli/OI-PBC-Dataset) offers a valuable resource to advance research on blood cell detection and classification in hematology.
Open AccessComprehensive Benchmarking of YOLOv11 Architectures for Scalable and Granular Peripheral Blood Cell Detection
Manual peripheral blood smear (PBS) analysis is labor intensive and subjective. While deep learning offers a promising alternative, a systematic evaluation of state of the art models such as YOLOv11 for fine grained PBS detection is still lacking. In this work, we make two key contributions. First, we curate a large scale annotated dataset for blood cell detection and classification, comprising 16,891 images across 12 peripheral blood cell (PBC) classes, along with the red blood cell class, all carefully re annotated for object detection tasks. In total, the dataset contains 298,850 annotated cells. Second, we leverage this dataset to conduct a comprehensive evaluation of five YOLOv11 variants (ranging from Nano to XLarge). These models are rigorously benchmarked under two data splitting strategies (70:20:10 and 80:10:10) and systematically assessed using multiple performance criteria, including mean Average Precision (mAP), precision, recall, F1 score, and computational efficiency. Our experiments show that the YOLOv11 Medium variant achieves the best trade off, reaching a mAP@0.5 of 0.934 under the 8:1:1 split. Larger models (Large and XLarge) provide only marginal accuracy gains at substantially higher computational cost. Moreover, the 8:1:1 split consistently outperforms the 7:2:1 split across all models. These findings highlight YOLOv11, particularly the Medium variant, as a highly effective framework for automated, fine grained PBS detection. Beyond benchmarking, our publicly released dataset (github.com/Mohamad-AbouAli/OI-PBC-Dataset) offers a valuable resource to advance research on blood cell detection and classification in hematology.
- 3 January 2025
- Published by Springer Nature in Applied Magnetic Resonance
- Vol. 56 (3) , 359-394
Enhancing Generalization and Mitigating Overfitting in Deep Learning for Brain Cancer Diagnosis from MRI
- 3 January 2025
- Published by Springer Nature in Applied Magnetic Resonance
- Vol. 56 (3) , 359-394
Enhancing Generalization and Mitigating Overfitting in Deep Learning for Brain Cancer Diagnosis from MRI
- Open Access
Real-Time PPG-Based Biometric Identification: Advancing Security with 2D Gram Matrices and Deep Learning Models
The integration of liveness detection into biometric systems is crucial for countering spoofing attacks and enhancing security. This study investigates the efficacy of photoplethysmography (PPG) signals, which offer distinct advantages over traditional biometric techniques. PPG signals are non-invasive, inherently contain liveness information that is highly resistant to spoofing, and are cost-efficient, making them a superior alternative for biometric authentication. A comprehensive protocol was established to collect PPG signals from 40 subjects using a custom-built acquisition system. These signals were then transformed into two-dimensional representations through the Gram matrix conversion technique. To analyze and authenticate users, we employed an EfficientNetV2 B0 model integrated with a Long Short-Term Memory (LSTM) network, achieving a remarkable 99% accuracy on the test set. Additionally, the model demonstrated outstanding precision, recall, and F1 scores. The refined model was further validated in real-time identification scenarios, underscoring its effectiveness and robustness for next-generation biometric recognition systems.
Open AccessReal-Time PPG-Based Biometric Identification: Advancing Security with 2D Gram Matrices and Deep Learning Models
The integration of liveness detection into biometric systems is crucial for countering spoofing attacks and enhancing security. This study investigates the efficacy of photoplethysmography (PPG) signals, which offer distinct advantages over traditional biometric techniques. PPG signals are non-invasive, inherently contain liveness information that is highly resistant to spoofing, and are cost-efficient, making them a superior alternative for biometric authentication. A comprehensive protocol was established to collect PPG signals from 40 subjects using a custom-built acquisition system. These signals were then transformed into two-dimensional representations through the Gram matrix conversion technique. To analyze and authenticate users, we employed an EfficientNetV2 B0 model integrated with a Long Short-Term Memory (LSTM) network, achieving a remarkable 99% accuracy on the test set. Additionally, the model demonstrated outstanding precision, recall, and F1 scores. The refined model was further validated in real-time identification scenarios, underscoring its effectiveness and robustness for next-generation biometric recognition systems.