BBBelaid Bouikhalene

Belaid Bouikhalene

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Belaid Bouikhalene has a total of 123 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Hyers-Ulam Stability for A Class of Third-Order Linear Differential Equations

    by Karim Farhat, Omar Ajebbar, Idriss Ellahiani, Belaid Bouikhalene

    This paper examines the Hyers-Ulam stability of a class of third-order linear differential equations of the form y(3)(x) + (δ − 2)y′′(x) − (2δ − 1)y′(x) + δy(x) = 0, x ∈ I, where δ is a real parameter and I = [a,b] is a real interval. Several illustrative examples are provided to support the theoretical results and analyze the influence of the parameter δ on the structure of solutions and on the stability constant.

  • Open Access

    Intelligent assessment of harmonic distortion compliance in reverse osmosis systems

    by Cherki Lahlou, Belaid Bouikhalene, Jamaa Bengourram, Hassan Latrache

    This study explores the critical challenge of harmonic distortion compliance in reverse osmosis (RO) desalination systems, with a focus on aligning with international standards, specifically IEC 61000, IEEE 519, and EN 50160. High-power equipment, particularly high-pressure pumps (HPP), introduces significant harmonic distortions, threatening power quality and operational reliability. To address this issue, we integrated advanced machine learning (ML) algorithms, namely decision tree (DT), random forest (RF), support vector machine (SVM), and multi-layer perceptron (MLP) to assess harmonic compliance and predict total harmonic distortion (THD) under four operational scenarios. All data used for training and testing were obtained from real-time measurements taken at a large-scale desalination plant using a power quality analyzer (QUALISTAR CA 8336), which guarantees the practical relevance of the analysis. The models were trained on harmonic order and amplitude data and evaluated using accuracy, precision, recall, and F1-score metrics. Among the models, MLP demonstrated superior performance, achieving an accuracy of 99.11% and an F1-score of 98.9%, making it a robust tool for harmonic compliance assessment. SVM and RF also showed commendable results, while DT proved effective for basic analysis. This research underscores the potential of AI-driven approaches in mitigating harmonic-related challenges, optimizing power quality, and enhancing operational efficiency in RO plants. These findings offer a pathway toward more reliable and energy-efficient industrial operations.


  • Adaptive Approach for Skills Assessment on MOODLE: Use of Big Data and Artificial Intelligence

    by Elhoucine Ouassam, Hamzaoui Radoine, Younes-Aziz Bachiri, Bouikhalene Belaid

  • Open Access

    Harnessing generative AI to boost active retrieval and retention in MOOCs with spaced repetition

    by Younes-Aziz Bachiri, Hicham Mouncif, Belaid Bouikhalene

    This study explores the use of artificial intelligence to improve active retrieval and retention in Massive Open Online Courses (MOOCs). We developed an AI-driven system that generates learning cards to facilitate active recall and utilize spaced repetition. The system was tested with a group of students and instructors, and the results showed significant improvements in memory retention and overall satisfaction. Expert reviews and participant feedback highlighted the system’s effectiveness in producing accurate and relevant learning cards. Despite promising outcomes, challenges with personalization and language complexity were identified, which will be addressed in future work. This research underscores the potential of AI-driven tools to enhance online learning, offering scalable and personalized solutions that can improve educational outcomes and engagement in MOOCs.


  • Open Access

    Exploring the Impact of Mobile Devices in E-Learning: A case Study Evaluating its Effectiveness

    by Khalid Ghoulam, Belaid Bouikhalene

    Aim. The integration of mobile devices into educational environments has revolutionized the landscape of e-learning, presenting new opportunities and challenges. This research paper aims to examine the pivotal role of mobile devices in the e-learning environment and assess the effectiveness of mobile learning applications in enhancing the educational experience. Methodology. The study employs a mixed-methods approach, combining quantitative data through surveys and usage analytics with qualitative insights derived from interviews and focus group discussions. Results. By analyzing the perspectives of both educators and learners, the research investigates how mobile devices contribute to the flexibility and accessibility of e-learning content. Additionally, the paper evaluates the effectiveness of various mobile learning applications in promoting engagement, knowledge retention, and overall learning outcomes. It scrutinizes the features that contribute to the success of these applications, such as user interface design, interactivity, and adaptability to diverse learning styles. Furthermore, the research delves into the challenges associated with mobile learning, including issues related to device compatibility, connectivity, and user motivation. Strategies to overcome these challenges and optimize the benefits of mobile learning are explored. The findings of this study are expected to provide valuable insights for educators, curriculum designers, and developers of mobile learning applications. Conclusion. The research contributes to the ongoing discourse on the effective integration of mobile devices in e-learning environments and offers recommendations for optimizing the design and implementation of mobile learning strategies.


  • Open Access

    Invariant Tchebichef And Krawtchouk Moments For Shape Recognition: A Performance Evaluation Study

    by Abdelati Bourzik, Belaid Bouikhalene, Jaouad El-Mekkaoui, Amal Hjouji

    In the last few decades, orthogonal invariant moments have become a considerable technique used in feature extraction. Thanks to their invariability against geometric transformations such as translation, scale changing, and rotation. This property makes them very useful in shape recognition and image classification tasks. In this paper, an application case and performance evaluation of the invariant moments derived from the known orthogonal Tchebichef and Krawtcouk polynomials are presented. The invariants are computed by creating a relationship between these moments and invariant geometric ones. These invariants are used to form an efficient vector of features. However, for performance evaluation, we adopt two classification models as input. The invariant descriptor vector is considered an input feature vector for classification models. The first model is a k-nearest neighbor, and the second is a neural network model. These models are used for handwritten digit classification in free-noise and different environmental noise types. In addition, the classification with the invariant method is also compared with the convolutional neural network image classifier. The results show the power and efficiency of invariant orthogonal moments in shape and pattern recognition.


  • Open Access

    Toward Artificial Intelligence-Enhanced Hybrid Learning: Leveraging Video Content for Personalized Education

    by Hamzaoui, Bachiri, Ouassam, Mouncif, Bouikhalene

    The COVID-19 pandemic has necessitated a rapid shift to online and hybrid learning models, presenting unique challenges and opportunities in the educational sector. This study, conducted at Sultan Moulay Slimane University (USMS) in Morocco, explores the integration of Artificial Intelligence (AI) to enhance distance learning through the automatic generation of assessment questions from video content. By leveraging advanced natural language processing (NLP) and deep learning techniques, the research aims to address the limitations of passive video watching and promote active learning and self-regulated learning skills. The methodology encompasses the use of speech recognition to transcribe video content, summarization techniques to distill core concepts, and a Text2Text generation model for creating relevant assessment questions. The study's findings demonstrate that the AI-driven question generation system can match the quality, diversity, and relevance of human-authored questions, thereby reducing instructor workload and fostering personalization and engagement in hybrid learning contexts. This research contributes to the body of knowledge on applying AI in education, offering insights and frameworks for adopting AI-driven methodologies to improve online pedagogies, assessments, and learning experiences in the post-pandemic era.


  • Open Access

    Improving the efficiency and security of passport control processes at airports by using the R-CNN object detection model

    by Elhoucine Ouassam, Yassine Dabachine, Nabil Hmina, Belaid Bouikhalene

    يمكن أن يؤدي استخدام التعلم الآلي في الوقت الفعلي لتحسين إجراءات مراقبة جوازات السفر في المطار إلى تحسين كفاءة العملية وأمانها بشكل كبير. لأتمتة هذه الإجراءات وتحسينها ، يمكن تنفيذ خوارزميات الذكاء الاصطناعي مثل التعرف على الأحرف والتعرف على الوجه والخوارزميات التنبؤية والمعالجة التلقائية للبيانات. تتمثل الطريقة المقترحة في استخدام نموذج R-CNN للكشف عن الأشياء لاكتشاف أجسام جواز السفر في الصور في الوقت الفعلي التي تم جمعها بواسطة كاميرات مراقبة الجوازات. تصف هذه المقالة العملية خطوة بخطوة للنهج المقترح ، والتي تشمل المعالجة المسبقة والتدريب واختبار نموذج R-CNN ودمجه في نظام مراقبة جوازات السفر وتقييم دقته وموثوقيته وسرعة الإدارة الفعالة لـتدفقات الركاب في المطارات الدولية. وقد أظهر تطبيق هذه الطريقة أداءً فائقًا مقارنة بالطرق السابقة من حيث تقليل الأخطاء والتأخيرات والتكاليف المرتبطة بها.