Samir Bennani
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Samir Bennani has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Asmaâ Retbi
Mohammed V University
8 shared publications - Mohammed Khalidi Idrissi
Mohammadia School of Engineers (EMI), Mohammed V University In Rabat Morocco
6 shared publications - Chaimae Ouhaddou
Mohammadia School of Engineers (EMI) Mohammed V University in Rabat
2 shared publications - Houda Sekkal
Mohammed V University Rabat
2 shared publications - Qamar El Maazouzi
Rime Team-Networking, Modeling and e-Learning Team-Masi Laboratory-Engineering 3S Research Center, Mohammadia School of Engineers, Mohammed V University in Rabat, Rabat 10100, Morocco
2 shared publications - Zaynabe Ragala
Mohammed V University
2 shared publications
Latest Publications
- 1 May 2026
- Published by Springer Nature
- p. 25-36
AI-Generated Visualizations in Physics Education: A Framework for Enhancing Teaching Methodologies
- 1 May 2026
- Published by Springer Nature
- p. 25-36
AI-Generated Visualizations in Physics Education: A Framework for Enhancing Teaching Methodologies
- Open Access
- 1 January 2025
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 16 (11)
Enhancing Career Counseling for Baccalaureate Students in Morocco through Retrieval-Augmented Generation Technology: A RAG-Based Chatbot
JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.
- 1 January 2025
- Published by Engineering and Technology Publishing in Journal of Advances in Information Technology
- Vol. 16 (11)
Open AccessEnhancing Career Counseling for Baccalaureate Students in Morocco through Retrieval-Augmented Generation Technology: A RAG-Based Chatbot
JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.
- 24 December 2024
- Published by Springer Nature
- p. 106-118
Optimizing Recommendation Systems in E-Learning: Synergistic Integration of Lang Chain, GPT Models, and Retrieval Augmented Generation (RAG)
- 24 December 2024
- Published by Springer Nature
- p. 106-118
Optimizing Recommendation Systems in E-Learning: Synergistic Integration of Lang Chain, GPT Models, and Retrieval Augmented Generation (RAG)
- 29 March 2024
- Published by Springer Nature
- p. 151-159
Enriching Ontology with Named Entity Recognition (NER) Integration
- 29 March 2024
- Published by Springer Nature
- p. 151-159
Enriching Ontology with Named Entity Recognition (NER) Integration
- Open Access
- 2 December 2022
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-4/W, 135-141
RAILWAY TRACK FAULTS DETECTION BASED ON IMAGE PROCESSING USING MOBILENET
The use of rail transport is increasing. Damaged rails interrupt traffic to carry out repairs. In fact, when a conductor or railway operator reports a damaged rail that interrupted the traffic in the affected area. A team of specialized agents dispatch to the site and carries out the repairs. Hence, the importance of automation of railway track faults detection to ensure track safety and reduce maintenance costs. In this work, we propose a method using image processing technologies and deep learning networks. We have studied the correlation effects of MobileNetV2 and optimization algorithms on accuracy and other performance metrics to generate a model that can achieve good performance in classifying railway track faults. The results show that the Rmsprop can improve the effectiveness of feature extraction and classification of MobileNetV2.
- 2 December 2022
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-4/W, 135-141
Open AccessRAILWAY TRACK FAULTS DETECTION BASED ON IMAGE PROCESSING USING MOBILENET
The use of rail transport is increasing. Damaged rails interrupt traffic to carry out repairs. In fact, when a conductor or railway operator reports a damaged rail that interrupted the traffic in the affected area. A team of specialized agents dispatch to the site and carries out the repairs. Hence, the importance of automation of railway track faults detection to ensure track safety and reduce maintenance costs. In this work, we propose a method using image processing technologies and deep learning networks. We have studied the correlation effects of MobileNetV2 and optimization algorithms on accuracy and other performance metrics to generate a model that can achieve good performance in classifying railway track faults. The results show that the Rmsprop can improve the effectiveness of feature extraction and classification of MobileNetV2.
- Open Access
- 2 December 2022
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-4/W, 53-60
AUTOMATISATION HYPERPARAMETERS TUNING PROCESS FOR TIMES SERIES FORECASTING: APPLICATION TO PASSENGER’S FLOW PREDICTION ON A RAILWAY NETWORK
Many industries and companies in various fields are interested in time series analysis to predict the future. However, in time series modeling, precision is lacking as time progress. In this paper, an architecture is proposed, allowing on the one hand keep the prediction accurate over time using the Walk Forward Optimization (WFO); On the other hand, automate the choice of parameters of the statistical models (ARIMA) introducing “AutoArima”; The RNN models, especially LSTM architectures (LSTM, Bi-LSTM, Stacked LSTM) using the function Optuna. Moreover, to avoid overfitting the LSTM models, an automatic function is implemented in the presented architecture. To demonstrate the validity of this research, a comparison of three models applied to a railway company to predict the flow of passengers is made. In particular, the naive model constitutes a reference base, the ARIMA model which had demonstrated its performances in several research, and finally, following the last progress in the neural networks the LSTM architecture is introduced in the paper. According to the results, the implemented architecture has great potential and more accurate predictions by using WFO. Through the comparisons of the models made, Each model has proven its performance according to the case of study. More concretely the mean absolute error obtained by LSTM for the railway stations is 0,13 compared to 0,15 obtained by ARIMA and 0,16 for the naive model, showing a small superiority for LSTM over ARIMA. On the other side, ARIMA excels on the Train lines.
- 2 December 2022
- Published by Copernicus GmbH in The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
- Vol. XLVIII-4/W, 53-60
Open AccessAUTOMATISATION HYPERPARAMETERS TUNING PROCESS FOR TIMES SERIES FORECASTING: APPLICATION TO PASSENGER’S FLOW PREDICTION ON A RAILWAY NETWORK
Many industries and companies in various fields are interested in time series analysis to predict the future. However, in time series modeling, precision is lacking as time progress. In this paper, an architecture is proposed, allowing on the one hand keep the prediction accurate over time using the Walk Forward Optimization (WFO); On the other hand, automate the choice of parameters of the statistical models (ARIMA) introducing “AutoArima”; The RNN models, especially LSTM architectures (LSTM, Bi-LSTM, Stacked LSTM) using the function Optuna. Moreover, to avoid overfitting the LSTM models, an automatic function is implemented in the presented architecture. To demonstrate the validity of this research, a comparison of three models applied to a railway company to predict the flow of passengers is made. In particular, the naive model constitutes a reference base, the ARIMA model which had demonstrated its performances in several research, and finally, following the last progress in the neural networks the LSTM architecture is introduced in the paper. According to the results, the implemented architecture has great potential and more accurate predictions by using WFO. Through the comparisons of the models made, Each model has proven its performance according to the case of study. More concretely the mean absolute error obtained by LSTM for the railway stations is 0,13 compared to 0,15 obtained by ARIMA and 0,16 for the naive model, showing a small superiority for LSTM over ARIMA. On the other side, ARIMA excels on the Train lines.
- 18 November 2022
- Published by Springer Nature
- p. 39-49
Overview of Gradient Descent Algorithms: Application to Railway Regularity
- 18 November 2022
- Published by Springer Nature
- p. 39-49
Overview of Gradient Descent Algorithms: Application to Railway Regularity
- 13 September 2022
- Published by Springer Nature
- p. 491-521
Towards a Recommender System Based on Community Detection and Performed Activities in the Context of Social Learning
- 13 September 2022
- Published by Springer Nature
- p. 491-521
Towards a Recommender System Based on Community Detection and Performed Activities in the Context of Social Learning
- Open Access
- 8 September 2022
- Published by International Association of Online Engineering (IAOE) in International Journal of Emerging Technologies in Learning (iJET)
- Vol. 17 (17) , 62-77
Cognitive Learning Style Detection in e-Learning Environments using Artificial Neural Network
COVID-19 pandemic has impacted all aspects of our lives including learning. With the particular growth of e-learning, teaching approaches are being implemented at a distance on online platforms due to this pandemic. In this context, to make student involved throughout the online course, it is recommended to create an efficient platform similar to the traditional learning mode. In this study, we aims to improve learning style detection process by exploring additional such as cognitive traits. In fact, we have proposed novel approach based on Artificial neural network that classify students according to their level of cognitive learning styles in real-time. The proposed automated approach will certainly provide tutors with exhaustive information that helps them in achieving an improved and innovative online learning method. The results obtained are quite interesting and demonstrate the relevance of our solution.
- 8 September 2022
- Published by International Association of Online Engineering (IAOE) in International Journal of Emerging Technologies in Learning (iJET)
- Vol. 17 (17) , 62-77
Open AccessCognitive Learning Style Detection in e-Learning Environments using Artificial Neural Network
COVID-19 pandemic has impacted all aspects of our lives including learning. With the particular growth of e-learning, teaching approaches are being implemented at a distance on online platforms due to this pandemic. In this context, to make student involved throughout the online course, it is recommended to create an efficient platform similar to the traditional learning mode. In this study, we aims to improve learning style detection process by exploring additional such as cognitive traits. In fact, we have proposed novel approach based on Artificial neural network that classify students according to their level of cognitive learning styles in real-time. The proposed automated approach will certainly provide tutors with exhaustive information that helps them in achieving an improved and innovative online learning method. The results obtained are quite interesting and demonstrate the relevance of our solution.