Said Jai-Andaloussi
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
Said Jai-Andaloussi has a total of 47 co-authors. Here are the top co-authors by number of shared publications:
Abderrahim Sekkaki
Hassan II University of Casablanca
15 shared publications- Ouail Ouchetto
University Hassan II of Casablanca
10 shared publications - Abdelali Elmoufidi
National School of Commerce and Management, Hassan 2 University
6 shared publications Khalid El Fahssi
Department of Mathematics & Computer Science Casablanca Hassan II University Faculty of Science Aïn Chock B.P 5366 Maarif 20100, Casablanca Morocco
6 shared publicationsNabil Madrane
6 shared publicationsGuy Cazuguel
Inserm, UMR 1101
5 shared publications
Latest Publications
- 1 May 2026
- Published by Springer Nature
- p. 394-405
Towards Robust and Transparent AI: Addressing Adversarial Threats, Biases, and Governance Challenges
- 1 May 2026
- Published by Springer Nature
- p. 394-405
Towards Robust and Transparent AI: Addressing Adversarial Threats, Biases, and Governance Challenges
- 1 October 2025
- Published by Springer Nature
- p. 187-201
An Ensemble Model for 30-Minute Blood Glucose Prediction in Type 1 Diabetes: Balancing Accuracy and Simplicity
- 1 October 2025
- Published by Springer Nature
- p. 187-201
An Ensemble Model for 30-Minute Blood Glucose Prediction in Type 1 Diabetes: Balancing Accuracy and Simplicity
- Open Access
- 25 June 2025
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 19 (12) , 19-37
AI Chatbots in Higher Education: Opportunities and Challenges for Personalized and Mobile Learning
The landscape of higher education is increasingly shaped by the integration of innovative tools such as chatbots, which offer promising solutions to enhance e-learning experiences. As conversational agents, chatbots are being adopted to address challenges in e-learning environments, including low student engagement and lack of personalized support. This literature review explores the current state of e-learning chatbots in higher education, with a particular focus on mobile learning environment. It aims to investigate how these tools contribute to personalize learning, the opportunities they present, and the key limitations and challenges they face. We conducted a comprehensive review of 815 publications from 2018 to 2024 across three major digital databases: Scopus, IEEE Xplore, and Science direct. From these, 39 studies were selected for in-depth analysis. Findings reveal that chatbots enhance personalized learning by adapting content and feedback based on various learner-specific features. In addition, chatbots are particularly effective when integrated into mobile applications and powered by AI technologies. Results show further that e-learning chatbots in higher education support a wide range of educational tasks from language learning to personalized guidance. Despite these advancements, significant challenges need to be addressed, including the technical limitations of both rule-based and AI-based chatbots. These challenges highlight the need for continued research aimed at improving chatbot capabilities. This review aims to inspire and support the effective integration of chatbots in higher education by offering concrete insights for instructors, developers, and researchers.
- 25 June 2025
- Published by International Association of Online Engineering (IAOE) in International Journal of Interactive Mobile Technologies (iJIM)
- Vol. 19 (12) , 19-37
Open AccessAI Chatbots in Higher Education: Opportunities and Challenges for Personalized and Mobile Learning
The landscape of higher education is increasingly shaped by the integration of innovative tools such as chatbots, which offer promising solutions to enhance e-learning experiences. As conversational agents, chatbots are being adopted to address challenges in e-learning environments, including low student engagement and lack of personalized support. This literature review explores the current state of e-learning chatbots in higher education, with a particular focus on mobile learning environment. It aims to investigate how these tools contribute to personalize learning, the opportunities they present, and the key limitations and challenges they face. We conducted a comprehensive review of 815 publications from 2018 to 2024 across three major digital databases: Scopus, IEEE Xplore, and Science direct. From these, 39 studies were selected for in-depth analysis. Findings reveal that chatbots enhance personalized learning by adapting content and feedback based on various learner-specific features. In addition, chatbots are particularly effective when integrated into mobile applications and powered by AI technologies. Results show further that e-learning chatbots in higher education support a wide range of educational tasks from language learning to personalized guidance. Despite these advancements, significant challenges need to be addressed, including the technical limitations of both rule-based and AI-based chatbots. These challenges highlight the need for continued research aimed at improving chatbot capabilities. This review aims to inspire and support the effective integration of chatbots in higher education by offering concrete insights for instructors, developers, and researchers.
- Open Access
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Assessing the Robustness of Deep Learning-Based Gait Recognition Systems Against Adversarial Attacks
This study presents a comprehensive analysis of the robustness of deep learning-based gait recognition systems in the face of adversarial attacks. As gait recognition technologies become increasingly vital in security-critical domains, they are challenged by the emerging threats of adversarial interventions. In response, our research proposes a novel approach, integrating the strengths of Proximal Policy Optimization (PPO) and Generative Adversarial Networks (GANs), to engineer and analyze complex adversarial attacks. The focus of our strategy is the generation and deployment of adversarial patches, designed to disrupt gait recognition algorithms while remaining imperceptible to human observers. Utilizing reinforcement learning principles, our method strategically positions these patches, compelling the target Convolutional Neural Network (CNN) models into erroneous gait pattern classification. The effectiveness of our methodology is demonstrated through comprehensive evaluations using the CASIA Gait Database: Dataset B, a prominent dataset in gait recognition research. The results underscore a noticeable decline in the accuracy of gait recognition systems post-attack, affirming the effectiveness of our adversarial tactics.
- 18 April 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-8
Open AccessAssessing the Robustness of Deep Learning-Based Gait Recognition Systems Against Adversarial Attacks
This study presents a comprehensive analysis of the robustness of deep learning-based gait recognition systems in the face of adversarial attacks. As gait recognition technologies become increasingly vital in security-critical domains, they are challenged by the emerging threats of adversarial interventions. In response, our research proposes a novel approach, integrating the strengths of Proximal Policy Optimization (PPO) and Generative Adversarial Networks (GANs), to engineer and analyze complex adversarial attacks. The focus of our strategy is the generation and deployment of adversarial patches, designed to disrupt gait recognition algorithms while remaining imperceptible to human observers. Utilizing reinforcement learning principles, our method strategically positions these patches, compelling the target Convolutional Neural Network (CNN) models into erroneous gait pattern classification. The effectiveness of our methodology is demonstrated through comprehensive evaluations using the CASIA Gait Database: Dataset B, a prominent dataset in gait recognition research. The results underscore a noticeable decline in the accuracy of gait recognition systems post-attack, affirming the effectiveness of our adversarial tactics.
- Open Access
- 5 July 2023
- Published by Elsevier in Scientific African
- Vol. 21
Advancing human action recognition: A hybrid approach using attention-based LSTM and 3D CNN
- 5 July 2023
- Published by Elsevier in Scientific African
- Vol. 21
Open AccessAdvancing human action recognition: A hybrid approach using attention-based LSTM and 3D CNN
- Open Access
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Leveraging Blockchain for Enhanced Security in IOB Data Management
The Internet of Behaviors (IOB) extends the Internet of Things (IoT) by focusing on individual behaviors through the analysis of data collected from connected devices. However, ensuring the security of IOB data is a major concern due to the increasing number of cyber attacks. To tackle this challenge, we propose an IOB architecture that leverages blockchain technology to enhance data security. In this article, we define IOB, highlight the differences between IOB and IoT, discuss the challenges of IOB, present our proposed IOB architecture with a blockchain-based security framework, and showcase real-life applications and use cases that require a high level of data security to demonstrate the effectiveness of our approach by combining IOB and blockchain.
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessLeveraging Blockchain for Enhanced Security in IOB Data Management
The Internet of Behaviors (IOB) extends the Internet of Things (IoT) by focusing on individual behaviors through the analysis of data collected from connected devices. However, ensuring the security of IOB data is a major concern due to the increasing number of cyber attacks. To tackle this challenge, we propose an IOB architecture that leverages blockchain technology to enhance data security. In this article, we define IOB, highlight the differences between IOB and IoT, discuss the challenges of IOB, present our proposed IOB architecture with a blockchain-based security framework, and showcase real-life applications and use cases that require a high level of data security to demonstrate the effectiveness of our approach by combining IOB and blockchain.
- Open Access
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Exploring Collaborative Filtering Algorithms in MOOCs Recommender Systems: A Comprehensive Overview
Nowadays, Massive Open Online Courses (MOOCs) have revolutionized traditional education, making it more accessible to millions of learners. These courses allow students to enroll and learn from a variety of subjects offered by prestigious universities worldwide. However, the vast amount of information available in MOOCs can make it challenging for students to choose courses that meet their needs and interests, leading to high dropout and low completion rates. To address this issue, Recommender Systems (RS) can be used to personalize the learning process in order to improve the learners' engagement and the completion rates. This overview examines papers published between 2018 and 2022 in the Scopus database and available in the IEEEXplore, ACM Digital Library, and Science Direct repositories to present the state-of-the-art of MOOCs recommender systems based on collaborative filtering algorithms. Through a qualitative analysis, we examine the use of collaborative filtering algorithms in MOOCs recommender systems and highlight the challenges of this technique, including cold start and sparsity problems, as well as the recent techniques used in combination with this algorithm to alleviate these challenges.
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessExploring Collaborative Filtering Algorithms in MOOCs Recommender Systems: A Comprehensive Overview
Nowadays, Massive Open Online Courses (MOOCs) have revolutionized traditional education, making it more accessible to millions of learners. These courses allow students to enroll and learn from a variety of subjects offered by prestigious universities worldwide. However, the vast amount of information available in MOOCs can make it challenging for students to choose courses that meet their needs and interests, leading to high dropout and low completion rates. To address this issue, Recommender Systems (RS) can be used to personalize the learning process in order to improve the learners' engagement and the completion rates. This overview examines papers published between 2018 and 2022 in the Scopus database and available in the IEEEXplore, ACM Digital Library, and Science Direct repositories to present the state-of-the-art of MOOCs recommender systems based on collaborative filtering algorithms. Through a qualitative analysis, we examine the use of collaborative filtering algorithms in MOOCs recommender systems and highlight the challenges of this technique, including cold start and sparsity problems, as well as the recent techniques used in combination with this algorithm to alleviate these challenges.
- Open Access
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
An Advanced IoT-Based Architecture for Healthcare Systems: A Focus on Blockchain-based Edge Computing for Diabetes Management
The healthcare industry has undergone a significant transformation with the emergence of Internet of Things (IoT) technology. Various computing paradigms, including cloud computing, fog computing, and edge computing, have emerged to address challenges in processing, storing, and analyzing data in modern systems. This paper proposes an advanced architecture for healthcare systems based on our research team's previous work. Our research focuses on developing a smart healthcare system to assist diabetes patients in managing their illness. Our novel architecture builds on the previous one, which included blockchain with IoT, by incorporating a blockchain-based edge layer to address scalability and security challenges that were previously encountered.
- 24 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessAn Advanced IoT-Based Architecture for Healthcare Systems: A Focus on Blockchain-based Edge Computing for Diabetes Management
The healthcare industry has undergone a significant transformation with the emergence of Internet of Things (IoT) technology. Various computing paradigms, including cloud computing, fog computing, and edge computing, have emerged to address challenges in processing, storing, and analyzing data in modern systems. This paper proposes an advanced architecture for healthcare systems based on our research team's previous work. Our research focuses on developing a smart healthcare system to assist diabetes patients in managing their illness. Our novel architecture builds on the previous one, which included blockchain with IoT, by incorporating a blockchain-based edge layer to address scalability and security challenges that were previously encountered.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 56-59
Homogenization of Lossy Artificial Structures with Mirror Cells
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 56-59
Homogenization of Lossy Artificial Structures with Mirror Cells