Ahmed Al Nuaim
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ahmed Al Nuaim has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Nour Elislem Karabadji
National Higher School of Technology and Engineering, Laboratoire De Technologies Des Systèmes Énergétiques (LTSE) E3360100
3 shared publications - Wajdi Dhifli
University of Lille, Lille, France
3 shared publications Abdullah Al Nuaim
Department of Management Information System, College of Business Administration, King Faisal University, 31982, Al Ahsa, Saudi Arabia
2 shared publications- Ali Assi
Rochester Institute of Technology, Dubai, United Arab Emirates
2 shared publications Asim Zafar
2 shared publications- Mohamed Elati
Univ. Lille, CNRS, Inserm, CHU Lille, UMR9020-U1277 – CANTHER – Cancer Heterogeneity Plasticity and Resistance to Therapies, Lille, France
2 shared publications
Latest Publications
- 30 October 2026
- Published by Springer Nature in Journal of Electronic Materials
- p. 1-19
Multiscale Homogenization of CNT-Doped PDMS/PZT Piezoelectric Composites with Primitive TPMS Architecture
- 30 October 2026
- Published by Springer Nature in Journal of Electronic Materials
- p. 1-19
Multiscale Homogenization of CNT-Doped PDMS/PZT Piezoelectric Composites with Primitive TPMS Architecture
- Open Access
- 23 October 2026
- Published by F1000 Research Ltd in F1000Research
- Vol. 15, 1768
Baseline Predictive Analysis of Saudi Digital Payment Activity Using Official Payment and Public-Sector Data
Saudi Arabia’s expansion of digital payment activity creates an opportunity for empirical analysis based on official payment systems and public-sector data. Existing Saudi studies have documented fintech development, digital-payment adoption, open government data, and COVID-related payment shifts, but less work has applied baseline predictive analytics directly to official Saudi payment and contextual datasets. This paper develops a modest applied benchmark using a region-month structure, with the main target variable being the monthly point-of-sale (POS) transaction value by region. The study compares payment-only models, based on lagged POS value, ATM cash-related controls, payment variables, moving averages, growth rates, and seasonal indicators, with payment-plus-contextual-public-data models that additionally incorporate CPI or inflation, population, business establishments, tourism activity, regional indicators, and calendar effects. Standard predictive metrics, including RMSE, MAE, MAPE, and R 2 , are used to evaluate temporal-holdout performance. The strongest results are achieved by LightGBM with contextual public-sector variables, while payment-only models also establish a strong empirical baseline. SHAP values are used only to support the interpretation of fitted tree-based models. The contribution is therefore intentionally limited but useful: it shows that official Saudi payment and public-sector data can support a clean, reproducible baseline predictive analysis without making causal, real-time, or high-claim explainable-AI assertions.
- 23 October 2026
- Published by F1000 Research Ltd in F1000Research
- Vol. 15, 1768
Open AccessBaseline Predictive Analysis of Saudi Digital Payment Activity Using Official Payment and Public-Sector Data
Saudi Arabia’s expansion of digital payment activity creates an opportunity for empirical analysis based on official payment systems and public-sector data. Existing Saudi studies have documented fintech development, digital-payment adoption, open government data, and COVID-related payment shifts, but less work has applied baseline predictive analytics directly to official Saudi payment and contextual datasets. This paper develops a modest applied benchmark using a region-month structure, with the main target variable being the monthly point-of-sale (POS) transaction value by region. The study compares payment-only models, based on lagged POS value, ATM cash-related controls, payment variables, moving averages, growth rates, and seasonal indicators, with payment-plus-contextual-public-data models that additionally incorporate CPI or inflation, population, business establishments, tourism activity, regional indicators, and calendar effects. Standard predictive metrics, including RMSE, MAE, MAPE, and R 2 , are used to evaluate temporal-holdout performance. The strongest results are achieved by LightGBM with contextual public-sector variables, while payment-only models also establish a strong empirical baseline. SHAP values are used only to support the interpretation of fitted tree-based models. The contribution is therefore intentionally limited but useful: it shows that official Saudi payment and public-sector data can support a clean, reproducible baseline predictive analysis without making causal, real-time, or high-claim explainable-AI assertions.
- Open Access
- 1 October 2026
- Published by SAGE Publications in Science Progress
- Vol. 109 (4)
A comprehensive finite element-based investigation on the linear and geometrically nonlinear bending response of CNT-agglomerated composite plates using an inverse hyperbolic shear theory
Carbon nanotube (CNT)-reinforced composites offer significant promise for lightweight multifunctional structures; however, their structural efficiency is often compromised by manufacturing-induced CNT agglomeration. Such clustering causes non-uniform load transfer, stiffness loss, and discrepancies between idealized predictions and practical performance. In this work, a mechanics-based finite element framework is developed to quantify the influence of CNT agglomeration on the linear and geometrically nonlinear bending response of composite plates. The effective material properties are evaluated through a two-parameter micromechanical model capable of representing different clustering states of CNTs. Geometric nonlinearity is incorporated using Green–Lagrange strain relations, and the resulting nonlinear equilibrium equations are solved through an incremental Newton–Raphson procedure. The proposed model is validated against benchmark solutions available in the literature. Extensive parametric studies are then carried out for square and rectangular plates under uniformly distributed and sinusoidal loading conditions, considering different CNT volume fractions, agglomeration states, aspect ratios, thickness ratios, and boundary constraints. Results reveal that CNT agglomeration significantly reduces the effective stiffness and increases transverse deflections in both linear and nonlinear regimes. Improved CNT dispersion and higher CNT content markedly enhance bending resistance, while clamped supports provide superior stiffness compared with simply supported boundaries. The study highlights the critical importance of realistic CNT dispersion modeling in the design of advanced composite plate structures.
- 1 October 2026
- Published by SAGE Publications in Science Progress
- Vol. 109 (4)
Open AccessA comprehensive finite element-based investigation on the linear and geometrically nonlinear bending response of CNT-agglomerated composite plates using an inverse hyperbolic shear theory
Carbon nanotube (CNT)-reinforced composites offer significant promise for lightweight multifunctional structures; however, their structural efficiency is often compromised by manufacturing-induced CNT agglomeration. Such clustering causes non-uniform load transfer, stiffness loss, and discrepancies between idealized predictions and practical performance. In this work, a mechanics-based finite element framework is developed to quantify the influence of CNT agglomeration on the linear and geometrically nonlinear bending response of composite plates. The effective material properties are evaluated through a two-parameter micromechanical model capable of representing different clustering states of CNTs. Geometric nonlinearity is incorporated using Green–Lagrange strain relations, and the resulting nonlinear equilibrium equations are solved through an incremental Newton–Raphson procedure. The proposed model is validated against benchmark solutions available in the literature. Extensive parametric studies are then carried out for square and rectangular plates under uniformly distributed and sinusoidal loading conditions, considering different CNT volume fractions, agglomeration states, aspect ratios, thickness ratios, and boundary constraints. Results reveal that CNT agglomeration significantly reduces the effective stiffness and increases transverse deflections in both linear and nonlinear regimes. Improved CNT dispersion and higher CNT content markedly enhance bending resistance, while clamped supports provide superior stiffness compared with simply supported boundaries. The study highlights the critical importance of realistic CNT dispersion modeling in the design of advanced composite plate structures.
- Open Access
- 8 August 2026
- Published by Elsevier in Information Fusion
- Vol. 138
Fractional class-specific weighted random forest optimization
- 8 August 2026
- Published by Elsevier in Information Fusion
- Vol. 138
Open AccessFractional class-specific weighted random forest optimization
- Open Access
- 10 June 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Quantized Low-Rank Adaptation in Large Language Models for Clinical Text Simplification
- 10 June 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Open AccessQuantized Low-Rank Adaptation in Large Language Models for Clinical Text Simplification
- Open Access
- 24 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
A hierarchical neuromorphic multi agent framework for energy aware and secure 6G resource optimization using Neuro6G agent
The convergence of Sixth-Generation (6G) wireless networks and neuromorphic computing presents significant opportunities for intelligent, energy-efficient resource management in distributed architectures. This paper introduces Neuro6G-Agent, a hierarchical neuromorphic agentic intelligence framework that integrates Energy-Aware Spiking Neural Networks (EA-SNNs) with multi-agent reinforcement learning to enable energy-conscious cognitive collaboration across cloud-edge-end 6G deployments. The framework addresses three principal challenges in distributed 6G resource management: energy sustainability, end-to-end latency under ultra-dense connectivity, and security resilience against adversarial threats. A three-tier architecture is employed, comprising cloud orchestrators, edge coordinators, and end devices, each operating dedicated neuromorphic agents with autonomous decision-making and trust-aware collaborative learning capabilities. The framework incorporates adaptive threshold EA-SNNs for event-driven processing, a distributed trust computation mechanism for secure multi-agent cooperation, and a hierarchical resource optimization algorithm responsive to dynamic workload conditions. Experimental evaluation across three public benchmark datasets—DeepMIMO (6G channel modeling), DVS128 Gesture (neuromorphic sensing), and CICIDS-2017 (network intrusion detection) demonstrates a 34.7% reduction in energy consumption, a 28.3% decrease in end-to-end latency, and a 95.6% security threat detection accuracy compared to state-of-the-art baseline methods, validated across ten independent experimental runs (p < 0.01). These results confirm the viability of neuromorphic intelligence for addressing complex optimization challenges in next-generation wireless architectures.
- 24 May 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessA hierarchical neuromorphic multi agent framework for energy aware and secure 6G resource optimization using Neuro6G agent
The convergence of Sixth-Generation (6G) wireless networks and neuromorphic computing presents significant opportunities for intelligent, energy-efficient resource management in distributed architectures. This paper introduces Neuro6G-Agent, a hierarchical neuromorphic agentic intelligence framework that integrates Energy-Aware Spiking Neural Networks (EA-SNNs) with multi-agent reinforcement learning to enable energy-conscious cognitive collaboration across cloud-edge-end 6G deployments. The framework addresses three principal challenges in distributed 6G resource management: energy sustainability, end-to-end latency under ultra-dense connectivity, and security resilience against adversarial threats. A three-tier architecture is employed, comprising cloud orchestrators, edge coordinators, and end devices, each operating dedicated neuromorphic agents with autonomous decision-making and trust-aware collaborative learning capabilities. The framework incorporates adaptive threshold EA-SNNs for event-driven processing, a distributed trust computation mechanism for secure multi-agent cooperation, and a hierarchical resource optimization algorithm responsive to dynamic workload conditions. Experimental evaluation across three public benchmark datasets—DeepMIMO (6G channel modeling), DVS128 Gesture (neuromorphic sensing), and CICIDS-2017 (network intrusion detection) demonstrates a 34.7% reduction in energy consumption, a 28.3% decrease in end-to-end latency, and a 95.6% security threat detection accuracy compared to state-of-the-art baseline methods, validated across ten independent experimental runs (p < 0.01). These results confirm the viability of neuromorphic intelligence for addressing complex optimization challenges in next-generation wireless architectures.
- Open Access
- 18 April 2026
- Published by Elsevier in SSRN Electronic Journal
Level-Wise Feature Weighting for Decision Tree Induction via Swarm Intelligence
Constructing optimal decision trees is an NP-complete problem. To address this challenge, we propose PSO-LWFWDT, a framework that reformulates tree induction as a continuous optimization problem. The proposed approach introduces a continuous level-wise feature-weighting mechanism optimized through Particle Swarm Optimization (PSO). Gini gain is dynamically modulated by these weights, while a hard-thresholding mechanism suppresses weak attributes, thereby enabling implicit depth-specific feature selection. The learning process is guided by a multi-objective fitness function that maximizes the weighted F1-score while penalizing tree depth, encouraging the induction of parsimonious trees without the need for post-pruning. An extensive evaluation on 30 benchmark datasets shows that PSO-LWFWDT achieves competitive or superior predictive performance compared with CART, Oblique Tree, and NCART, while maintaining controlled model complexity.
- 18 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessLevel-Wise Feature Weighting for Decision Tree Induction via Swarm Intelligence
Constructing optimal decision trees is an NP-complete problem. To address this challenge, we propose PSO-LWFWDT, a framework that reformulates tree induction as a continuous optimization problem. The proposed approach introduces a continuous level-wise feature-weighting mechanism optimized through Particle Swarm Optimization (PSO). Gini gain is dynamically modulated by these weights, while a hard-thresholding mechanism suppresses weak attributes, thereby enabling implicit depth-specific feature selection. The learning process is guided by a multi-objective fitness function that maximizes the weighted F1-score while penalizing tree depth, encouraging the induction of parsimonious trees without the need for post-pruning. An extensive evaluation on 30 benchmark datasets shows that PSO-LWFWDT achieves competitive or superior predictive performance compared with CART, Oblique Tree, and NCART, while maintaining controlled model complexity.
- Top Cited PapersOpen Access
- 7 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Artificial intelligence driven multi agent framework for adaptive cyber attack simulation and automated incident response in cyber range environments
Cyber range environments are key platforms for cybersecurity training, research and testing. This can enable the emulation of realistic cyberattacks and incident response scenarios. Most of the traditional approaches to simulation are based on predefined or rule-based models. These approaches do not allow for adaptation and fail to account for the complexity of evolving threats. An artificial Intelligence-Driven Multi-Agent System (MAS) has been proposed in this paper. The framework autonomously simulates sophisticated cyberattacks and coordinates automated incident response within a cyber range. CICIDS2017 and UNSW-NB15 datasets are combined and integrated into a cyber range simulator CyDER 2.0. Reinforcement learning and anomaly detection methods are used to enable attack and defence agents for adaptive behaviours. The MAS architecture implements realistic attack vectors and response strategies. A set of experiments demonstrate that the AI-driven MAS achieves much higher simulation realism and responsiveness than the traditional static systems. This method also has higher detection accuracy with minimal mitigation times. The model undergoes rigorous validation and acceptance testing to assess robustness and generalizability.
- 7 April 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Top Cited PapersOpen AccessArtificial intelligence driven multi agent framework for adaptive cyber attack simulation and automated incident response in cyber range environments
Cyber range environments are key platforms for cybersecurity training, research and testing. This can enable the emulation of realistic cyberattacks and incident response scenarios. Most of the traditional approaches to simulation are based on predefined or rule-based models. These approaches do not allow for adaptation and fail to account for the complexity of evolving threats. An artificial Intelligence-Driven Multi-Agent System (MAS) has been proposed in this paper. The framework autonomously simulates sophisticated cyberattacks and coordinates automated incident response within a cyber range. CICIDS2017 and UNSW-NB15 datasets are combined and integrated into a cyber range simulator CyDER 2.0. Reinforcement learning and anomaly detection methods are used to enable attack and defence agents for adaptive behaviours. The MAS architecture implements realistic attack vectors and response strategies. A set of experiments demonstrate that the AI-driven MAS achieves much higher simulation realism and responsiveness than the traditional static systems. This method also has higher detection accuracy with minimal mitigation times. The model undergoes rigorous validation and acceptance testing to assess robustness and generalizability.
- Top Cited PapersOpen Access
- 29 January 2026
- Published by MDPI AG in Information
- Vol. 17 (2) , 126
AI-Enabled System-of-Systems Decision Support: BIM-Integrated AI-LCA for Resilient and Sustainable Fiber-Reinforced Façade Design
Sustainable and resilient communities increasingly rely on interdependent, data-driven building systems where material choices, energy performance, and lifecycle impacts must be optimized jointly. This study presents a digital-twin-ready, system-of-systems (SoS) decision-support framework that integrates BIM-enabled building energy simulation with an AI-enhanced lifecycle assessment (AI-LCA) pipeline to optimize fiber-reinforced concrete (FRC) façade systems for smart buildings. Conventional LCA is often inventory-driven and static, limiting its usefulness for SoS decision making under operational variability. To address this gap, we develop machine learning surrogate models (Random Forests, Gradient Boosting, and Artificial Neural Networks) to perform a dual prediction of façade mechanical performance and lifecycle indicators (CO2 emissions, embodied energy, and water use), enabling a rapid exploration of design alternatives. We fuse experimental FRC measurements, open environmental inventories, and BIM-linked energy simulations into a unified dataset that captures coupled material–building behavior. The models achieve high predictive performance (up to 99.2% accuracy), and feature attribution identifies the fiber type, volume fraction, and curing regime as key drivers of lifecycle outcomes. Scenario analyses show that optimized configurations reduce embodied carbon while improving energy-efficiency trajectories when propagated through BIM workflows, supporting carbon-aware and resilient façade selection. Overall, the framework enables scalable SoS optimization by providing fast, coupled predictions for façade design decisions in smart built environments.
- 29 January 2026
- Published by MDPI AG in Information
- Vol. 17 (2) , 126
Top Cited PapersOpen AccessAI-Enabled System-of-Systems Decision Support: BIM-Integrated AI-LCA for Resilient and Sustainable Fiber-Reinforced Façade Design
Sustainable and resilient communities increasingly rely on interdependent, data-driven building systems where material choices, energy performance, and lifecycle impacts must be optimized jointly. This study presents a digital-twin-ready, system-of-systems (SoS) decision-support framework that integrates BIM-enabled building energy simulation with an AI-enhanced lifecycle assessment (AI-LCA) pipeline to optimize fiber-reinforced concrete (FRC) façade systems for smart buildings. Conventional LCA is often inventory-driven and static, limiting its usefulness for SoS decision making under operational variability. To address this gap, we develop machine learning surrogate models (Random Forests, Gradient Boosting, and Artificial Neural Networks) to perform a dual prediction of façade mechanical performance and lifecycle indicators (CO2 emissions, embodied energy, and water use), enabling a rapid exploration of design alternatives. We fuse experimental FRC measurements, open environmental inventories, and BIM-linked energy simulations into a unified dataset that captures coupled material–building behavior. The models achieve high predictive performance (up to 99.2% accuracy), and feature attribution identifies the fiber type, volume fraction, and curing regime as key drivers of lifecycle outcomes. Scenario analyses show that optimized configurations reduce embodied carbon while improving energy-efficiency trajectories when propagated through BIM workflows, supporting carbon-aware and resilient façade selection. Overall, the framework enables scalable SoS optimization by providing fast, coupled predictions for façade design decisions in smart built environments.
- Open Access
- 18 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 309
Towards better random forests with tree weighting, accuracy and diversity-preserving pruning
- 18 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 309
Open AccessTowards better random forests with tree weighting, accuracy and diversity-preserving pruning