Mohamed Amin Benatia
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mohamed Amin Benatia has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
Anne Louis
CESI Engineering School,CESI LINEACT,Rouen,France
3 shared publications- M'HAmmed Sahnoun
CESI LINEACT, Rouen, France
3 shared publications Abdelkhalak El-Hami
LOFIMS/INSA-Rouen
1 shared publication- Ahmed Nait Chabane
CESI LINEACT, Saint Nazaire, France
1 shared publication Amal Ayadi
CESI Engineering School,CESI LINEACT,Rouen,France
1 shared publication- Ammar Chouchane
University Center of Barika, Barika, Algeria
1 shared publication
Latest Publications
- 2 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Optimisation multi-objectives d’une infrastructure réseau dédiée aux bâtiments intelligents
Au cours de cette thèse, nous avons étudié le problème de déploiement des Réseaux de Capteurs Sans-Fil (RCSF) pour des applications indoor tel que le bâtiment intelligent. Le but de notre travail était de développer un outil de déploiement capable d'assister les concepteurs de RCSF lors de la phase de déploiement de ces derniers. Nous avons commencé cette thèse par la modélisation de tous les paramètres qui interviennent lors du déploiement des RCSF, à savoir : coût, connectivité, couverture et durée de vie. Par la suite, nous avons implémenté cinq algorithmes d'optimisation, dont trois multi-objectifs afin de résoudre le problème de déploiement. Deux cas d'études réelles (grande et petite instance) ont été identifiés afin de tester ces algorithmes. Les résultats obtenus ont montré que ces algorithmes sont efficaces quand il s'agit d'un petit bâtiment (petit espace). Par contre, dès que la surface du bâtiment augmente les performances des algorithmes étudiés se dégradent. Pour répondre à cela, nous avons développé et implémenté un algorithme d'optimisation multi-objectifs hybride. Cet algorithme se base sur des notions de clustering et d'analyse de données afin de limiter le nombre d'évaluations directes qu'entreprennent ces méthodes pendant chaque itération. Afin d'assurer cette limitation d'évaluation les fonctions de fitness sont approximées grâce aux réseaux de neurones et l'algorithme de classification K-means. Les résultats obtenus ont montré une très bonne performance sur les deux instances de tailles différentes. Ces résultats ont été comparés à ceux obtenus avec les méthodes classiques utilisées et sont compétitives et prometteuses.
- 2 April 2026
- Published by Agence Bibliographique de l'Enseignement Supérieur
Optimisation multi-objectives d’une infrastructure réseau dédiée aux bâtiments intelligents
Au cours de cette thèse, nous avons étudié le problème de déploiement des Réseaux de Capteurs Sans-Fil (RCSF) pour des applications indoor tel que le bâtiment intelligent. Le but de notre travail était de développer un outil de déploiement capable d'assister les concepteurs de RCSF lors de la phase de déploiement de ces derniers. Nous avons commencé cette thèse par la modélisation de tous les paramètres qui interviennent lors du déploiement des RCSF, à savoir : coût, connectivité, couverture et durée de vie. Par la suite, nous avons implémenté cinq algorithmes d'optimisation, dont trois multi-objectifs afin de résoudre le problème de déploiement. Deux cas d'études réelles (grande et petite instance) ont été identifiés afin de tester ces algorithmes. Les résultats obtenus ont montré que ces algorithmes sont efficaces quand il s'agit d'un petit bâtiment (petit espace). Par contre, dès que la surface du bâtiment augmente les performances des algorithmes étudiés se dégradent. Pour répondre à cela, nous avons développé et implémenté un algorithme d'optimisation multi-objectifs hybride. Cet algorithme se base sur des notions de clustering et d'analyse de données afin de limiter le nombre d'évaluations directes qu'entreprennent ces méthodes pendant chaque itération. Afin d'assurer cette limitation d'évaluation les fonctions de fitness sont approximées grâce aux réseaux de neurones et l'algorithme de classification K-means. Les résultats obtenus ont montré une très bonne performance sur les deux instances de tailles différentes. Ces résultats ont été comparés à ceux obtenus avec les méthodes classiques utilisées et sont compétitives et prometteuses.
- 8 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 55 (4) , 480-489
Infrastructure-Free Indoor Localization for Cultural Heritage Sites
Indoor positioning systems are crucial for preserving and promoting cultural heritage sites by providing visitors with accurate location information and real-time exhibit details. These systems also offer valuable insights into visitor behavior for museums and cultural institutions to optimize their offerings and enhance the overall visitor experience. Their importance lies in driving engagement, fostering deeper connections with visitors, and providing data for future decision-making. This study proposes a magnetic field-based pedestrian localization algorithm as a solution to the challenge of providing accurate location information for visitors in indoor environments during virtual tours. The proposed approach uses magnetic field sequences to identify unique landmarks and a deep neural network (VGG-16) to analyze magnetic signal features and determine the visitor's location based on the nearest landmark. The study's results indicate that this magnetic field-based approach can be reliable for providing location information in indoor environments.
- 8 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Human-Machine Systems
- Vol. 55 (4) , 480-489
Infrastructure-Free Indoor Localization for Cultural Heritage Sites
Indoor positioning systems are crucial for preserving and promoting cultural heritage sites by providing visitors with accurate location information and real-time exhibit details. These systems also offer valuable insights into visitor behavior for museums and cultural institutions to optimize their offerings and enhance the overall visitor experience. Their importance lies in driving engagement, fostering deeper connections with visitors, and providing data for future decision-making. This study proposes a magnetic field-based pedestrian localization algorithm as a solution to the challenge of providing accurate location information for visitors in indoor environments during virtual tours. The proposed approach uses magnetic field sequences to identify unique landmarks and a deep neural network (VGG-16) to analyze magnetic signal features and determine the visitor's location based on the nearest landmark. The study's results indicate that this magnetic field-based approach can be reliable for providing location information in indoor environments.
- 26 December 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (3) , 1-17
Fault diagnosis using deep neural networks for industrial alarm sequence clustering
- 26 December 2024
- Published by Springer Nature in Applied Intelligence
- Vol. 55 (3) , 1-17
Fault diagnosis using deep neural networks for industrial alarm sequence clustering
- 8 December 2024
- Published by Elsevier in Energy Economics
- Vol. 141
Energy savings and coverage optimization in edge WiFi sensor deployment for buildings: A multi-objective evolutionary approach
- 8 December 2024
- Published by Elsevier in Energy Economics
- Vol. 141
Energy savings and coverage optimization in edge WiFi sensor deployment for buildings: A multi-objective evolutionary approach
- Open Access
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
RUL Prediction with Encoding and Spatial-Temporal Deep Neural Networks
The objective of this paper is to design and develop an approach to estimate the Remaining Useful Life (RUL) of an industrial equipment evolving in a Cyber-Physical System (CPS). To do so, this work aims to predict failures and malfunctions of an industrial equipment, as well as evaluating all the main underlying causes. The system will also identify the actions to be taken in order to maintain the system at a certain level of performance and guarantee that it will operate in the most efficient way, which implies a study of all aspects: reliability, availability and maintenance. Existing works are often limited to the estimation phase of the RUL, with only a few case studies (such as ball bearings and Proof Of Concept(PoC)) available and a significant lack of data. The innovation of this research work will be to design and develop diagnostic and prognostic approaches based on Deep Learning (DL)(e.g. Boltzmann Machine, Recurrent Networks and Echo State Network (ESN)) for the maintenance and health management of industrial equipment evolving in a CPS.
- 28 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Open AccessRUL Prediction with Encoding and Spatial-Temporal Deep Neural Networks
The objective of this paper is to design and develop an approach to estimate the Remaining Useful Life (RUL) of an industrial equipment evolving in a Cyber-Physical System (CPS). To do so, this work aims to predict failures and malfunctions of an industrial equipment, as well as evaluating all the main underlying causes. The system will also identify the actions to be taken in order to maintain the system at a certain level of performance and guarantee that it will operate in the most efficient way, which implies a study of all aspects: reliability, availability and maintenance. Existing works are often limited to the estimation phase of the RUL, with only a few case studies (such as ball bearings and Proof Of Concept(PoC)) available and a significant lack of data. The innovation of this research work will be to design and develop diagnostic and prognostic approaches based on Deep Learning (DL)(e.g. Boltzmann Machine, Recurrent Networks and Echo State Network (ESN)) for the maintenance and health management of industrial equipment evolving in a CPS.
- 1 July 2020
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 13 (7) , 3683-3692
Detecting counterfeit products by means of frequent pattern mining
- 1 July 2020
- Published by Springer Nature in Journal of Ambient Intelligence and Humanized Computing
- Vol. 13 (7) , 3683-3692
Detecting counterfeit products by means of frequent pattern mining
- 3 February 2017
- Published by Springer Nature in Wireless Personal Communications
- Vol. 94 (4) , 2739-2768
Multi-Objective WSN Deployment Using Genetic Algorithms Under Cost, Coverage, and Connectivity Constraints
- 3 February 2017
- Published by Springer Nature in Wireless Personal Communications
- Vol. 94 (4) , 2739-2768
Multi-Objective WSN Deployment Using Genetic Algorithms Under Cost, Coverage, and Connectivity Constraints
- 1 November 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 39, 1-5
3D and 2D face recognition based on image segmentation
In this paper we propose a framework for 3D Face Recognition System (3DFRS) using segmentation by grouping of regions of facial images before and after fusion of two modalities (color and depth images). Firstly, the detection of face region is based on the localization of nose tip and integral projection curves. Then, the features resulting from Principle Component Analyses (PCA) followed by Enhanced Fisher Model (EFM) are extracted. Finally, the classification process is performed with two methods, distance measurement L3 and Support Vector Machine (SVM). Experiments are performed on the CASIA3D face database which contains 123 persons under varying illumination and expression. We have tried to examine all the variants associated with our algorithms in order to optimize the maximum our recognition system. The promising results of the experimental evaluation show that our proposed approach achieves a high recognition performance.
- 1 November 2014
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 39, 1-5
3D and 2D face recognition based on image segmentation
In this paper we propose a framework for 3D Face Recognition System (3DFRS) using segmentation by grouping of regions of facial images before and after fusion of two modalities (color and depth images). Firstly, the detection of face region is based on the localization of nose tip and integral projection curves. Then, the features resulting from Principle Component Analyses (PCA) followed by Enhanced Fisher Model (EFM) are extracted. Finally, the classification process is performed with two methods, distance measurement L3 and Support Vector Machine (SVM). Experiments are performed on the CASIA3D face database which contains 123 persons under varying illumination and expression. We have tried to examine all the variants associated with our algorithms in order to optimize the maximum our recognition system. The promising results of the experimental evaluation show that our proposed approach achieves a high recognition performance.