Mourad Mzili

Mourad Mzili

Auto-generated profile, based on publicly available information

Mourad Mzili

Department of Mathematics, Faculty of Sciences Chouaib Doukkali University El Jadida Morocco

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 July 2025 in Mesopotamian Journal of Artificial Intelligence in Healthcare
Verified
Journal Article
Open access
PDF file
ZBZakaria Benlalia
Zakaria Benlalia
Ghada Al-KatebGhada Al-Kateb
Ghada Al-Kateb
MMMourad Mzili
Mourad Mzili
KDKonstantina Diamanti
Konstantina Diamanti
Human-Centric Artificial Intelligence (HCAI) is rapidly emerging as a transformative paradigm, shifting the focus of AI development from mere algorithmic optimization to ethical alignment, user trust, and societal integration most notably within the critical domain of healthcare. This review offers a comprehensive examination of the principles, architecture, challenges, and future directions underpinning HCAI, with an emphasis on its applications in health-related contexts. We begin by exploring the conceptual foundations of human-centricity, including core values such as transparency, fairness, autonomy, and privacy, all of which are essential in sensitive environments like clinical decision-making and patient data management. The paper then surveys key enabling technologies such as Explainable AI (XAI), Human-in-the-Loop learning, affective computing, and multi-agent collaboration demonstrating how these approaches operationalize human alignment in real-world systems, especially in personalized healthcare delivery and diagnostic support. Societal implications are critically evaluated, encompassing trust, data sovereignty, algorithmic bias, regulatory compliance, and cross-cultural adaptability, which are particularly pronounced in global health systems. We highlight the limitations of existing benchmarks and propose a multi-metric, user-centered evaluation framework capable of assessing both technical robustness and alignment with human values in healthcare and beyond. Finally, we identify open research challenges and outline a strategic agenda that integrates cognitive science, ethical theory, and participatory design. This review aims to serve as both a foundational reference and a forward-looking roadmap for researchers, developers, and policymakers striving to build AI systems that are not only intelligent, but also responsible, inclusive, and aligned with human dignity, particularly in life-critical domains like healthcare

10 April 2025 in Babylonian Journal of Internet of Things
Verified
Journal Article
Open access
PDF file
TMToufik Mzili
Toufik Mzili
MMMourad Mzili
Mourad Mzili
SBSaif Islam Bouderba
Saif Islam Bouderba
AAAhmed Abatal
Ahmed Abatal
WAWidi Aribowo
Widi Aribowo
AAAdarsh Kumar Arya
Adarsh Kumar Arya
This research investigates the existing taxonomies of interoperability within the Internet of Things (IoT), focusing on the critical gaps and challenges that impede seamless integration across various IoT systems, particularly in the healthcare sector. It addresses the key issue of disparate standards and protocols that complicate interoperability, utilizing a comprehensive analysis of qualitative and quantitative data, including case studies, technical specifications, and user experiences. The research identifies significant barriers such as data silos, inconsistent protocol adoption, and the lack of standardized frameworks, highlighting a need for cohesive solutions that foster interoperability. The findings reveal that enhancing interoperability can lead to improved patient outcomes, greater operational efficiency, and reduced costs, thereby underscoring the importance of standardized communication between devices and systems in healthcare. The implications of this study extend beyond technical advancements, suggesting that addressing interoperability challenges could catalyze a paradigm shift towards more integrated, patient-centered healthcare delivery models. By proposing actionable solutions, this research not only contributes to the academic discourse on IoT interoperability but also offers practical insights for stakeholders aiming to optimize the use of IoT technology in health-related applications.

1 February 2025 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
AAAhmed Abatal
Ahmed Abatal
MMMourad Mzili
Mourad Mzili
ZBZakaria Benlalia
Zakaria Benlalia
HKHajar Khallouki
Hajar Khallouki
TMToufik Mzili
Toufik Mzili
Laith AbualigahLaith Abualigah
Laith Abualigah
In this study, we address critical operational inefficiencies in emergency departments (EDs) by developing a hybrid predictive model that integrates long short-term memory (LSTM) networks with decision trees (DT). This model significantly enhances the prediction of patient volumes, a key factor in reducing wait times, optimizing resource allocation, and improving overall service quality in hospitals. By accurately forecasting the number of incoming patients, our model facilitates the efficient distribution of both human and material resources, tailored specifically to anticipated demand. Furthermore, this predictive accuracy ensures that EDs can maintain high service standards even during peak times, ultimately leading to better patient outcomes and more effective use of healthcare facilities. This paper demonstrates how advanced data analytics can be leveraged to solve some of the most pressing challenges faced by emergency medical services today.

9 May 2025 in Mesopotamian Journal of Artificial Intelligence in Healthcare
Verified
Journal Article
Open access
PDF file
TMToufik Mzili
Toufik Mzili
MMMourad Mzili
Mourad Mzili
SBSaif Islam Bouderba
Saif Islam Bouderba
AAAhmed Abatal
Ahmed Abatal
WAWidi Aribowo
Widi Aribowo
ZOZahra Oughannou
Zahra Oughannou
This study developed an XGBoost-based risk assessment model to enhance early tumor detection among Egyptian patients, addressing the challenges of late diagnosis and limited healthcare resources. Utilizing a retrospective dataset of 178 patients, the model incorporated demographic, clinical, and biochemical variables, including AFP levels, viral hepatitis status (HBV/HCV), and liver function markers. The model demonstrated strong predictive performance, achieving an accuracy of 0.833, precision of 0.846, and an AUC of 0.86, though recall remained moderate (0.688), indicating room for improvement in identifying high-risk cases. Feature importance analysis highlighted AFP levels and hepatitis status as the most influential predictors, aligning with Egypt’s high prevalence of liver cancer. The findings underscore the potential of AI-driven tools for early cancer screening in resource-limited settings, offering a scalable and cost-effective solution. However, future work should focus on expanding datasets, optimizing recall, and validating the model across diverse populations to ensure clinical applicability. This research contributes to the growing integration of AI in oncology, providing a framework for tailored risk stratification in high-burden regions

9 April 2026 in Engineering Reports
Verified
Journal Article
Open access
PDF file
MMMourad Mzili
Mourad Mzili
MTMouna Torki
Mouna Torki
TMToufik Mzili
Toufik Mzili
MAMohammed Benzakour Amine
Mohammed Benzakour Amine
NEBOJSA BACANINNEBOJSA BACANIN
NEBOJSA BACANIN
MSMomina Shaheen
Momina Shaheen
The permutation flow shop scheduling problem (PFSSP) is a classical NP‐hard problem that aims to determine an optimal job sequence across machines to minimize makespan. Existing swarm intelligence and evolutionary algorithms often suffer from premature convergence, parameter sensitivity, and limited adaptability in dynamic environments. This study proposes a Hybrid Recruit Simulated Annealing and Rat Swarm Optimization (HRSA‐RSO) algorithm that integrates the exploration capability of Rat Swarm Optimization with the probabilistic local refinement of Simulated Annealing. The hybrid design incorporates adaptive parameter control, a swap insertion neighborhood structure, and a modified Nawaz Enscore Ham (NEH) initialization strategy. An adaptive temperature mechanism guided by Hamming‐based diversity enhances robustness while reducing the need for manual tuning. Experiments on 15 Taillard benchmark instances show that HRSA‐RSO achieves an average Percentage Relative Deviation (PRD) of 0.46%–2.25%, outperforming 10 state‐of‐the‐art metaheuristics while using 20%–30% less computational time. Statistical analyses (ANOVA, Wilcoxon, and Friedman tests, p < 0.05) confirm the superiority and consistency of the proposed approach. Owing to its low computational overhead and strong scalability, HRSA‐RSO represents an effective and practical solution for large‐scale PFSSP and real‐world manufacturing environments.

1 November 2025 in SHIFRA
Verified
Journal Article
Open access
PDF file
ZBZakaria Benlalia
Zakaria Benlalia
TMToufik Mzili
Toufik Mzili
MHMustapha Hankar
Mustapha Hankar
AAAhmed Abatal
Ahmed Abatal
MMMourad Mzili
Mourad Mzili
MSMomina Shaheen
Momina Shaheen
This study aimed to address the increasing sophistication of cybersecurity threats by analyzing a substantial dataset to evaluate the efficacy of detection methodologies. Utilizing a dataset comprising 14,133 records and 16 variables, we investigated the prevalence of various cyber threats and assessed the performance of machine learning models in their detection. Our methodological approach centered on the application of attention-based neural networks, which facilitated a comprehensive analysis of complex threat scenarios. Results showed that unauthorized access and data breaches were the most prevalent threats, representing a significant portion of the dataset. Additionally, malware and phishing attacks emerged as notable threats, highlighting the necessity for enhanced detection strategies. The implementation of attention-based neural networks significantly improved threat detection capabilities, with these models effectively classifying diverse threat patterns. This methodological advancement underscores the potential of machine learning in augmenting cybersecurity measures. Our findings suggest a pressing need for targeted detection methods tailored to specific threat categories, thereby optimizing threat detection and response strategies. The identification of system vulnerabilities emphasizes the importance of proactive mitigation strategies to bolster cybersecurity resilience. These results indicate that integrating advanced machine learning models into cybersecurity frameworks can substantially enhance detection accuracy and efficiency. In conclusion, this research provides critical insights into the landscape of cybersecurity threats and the effectiveness of detection methodologies. By leveraging a large dataset, we have elucidated key patterns in threat prevalence and detection efficacy. Our findings reinforce the imperative for ongoing innovation in cybersecurity practices, with attention-based neural networks offering a promising avenue for future exploration.