Mokhtar Essaid
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Mokhtar Essaid has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Lhassane Idoumghar
IRIMAS, Université de Haute-Alsace, Mulhouse, France
9 shared publications - Muhammad Junaid Ali
Université de Haute-Alsace, IRIMAS UR 7499
5 shared publications - Laurent Moalic
Université de Haute-Alsace, IRIMAS UR 7499
4 shared publications - Daniel Fodorean
Electrical Machines and Drives Department, Technical University of Cluj-Napoca, 400114 Cluj-Napoca, Romania
2 shared publications Julien Lepagnot
University of Haute-Alsace
2 shared publications- Julien Lepagnot
Université de Haute-Alsace, IRIMAS UR 7499, Mulhouse, France
2 shared publications
Latest Publications
- 16 October 2024
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 118, 102441
A review of AutoML optimization techniques for medical image applications
- 16 October 2024
- Published by Elsevier in Computerized Medical Imaging and Graphics
- Vol. 118, 102441
A review of AutoML optimization techniques for medical image applications
- 27 June 2024
- Published by Springer Nature
- p. 131-146
Evolutionary Neural Architecture Search for 2D and 3D Medical Image Classification
- 27 June 2024
- Published by Springer Nature
- p. 131-146
Evolutionary Neural Architecture Search for 2D and 3D Medical Image Classification
- 29 April 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (S1) , 355-372
Conv-ViT fusion for improved handwritten Arabic character classification
- 29 April 2024
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (S1) , 355-372
Conv-ViT fusion for improved handwritten Arabic character classification
- 21 March 2024
- Published by Springer Nature
- p. 163-179
Robust Neural Architecture Search Using Differential Evolution for Medical Images
- 21 March 2024
- Published by Springer Nature
- p. 163-179
Robust Neural Architecture Search Using Differential Evolution for Medical Images
- 24 January 2024
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 188
Surrogate-assisted metaheuristics for the facility location problem with distributed demands on network edges
- 24 January 2024
- Published by Elsevier in Computers & Industrial Engineering
- Vol. 188
Surrogate-assisted metaheuristics for the facility location problem with distributed demands on network edges
- Open Access
- 15 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 263-266
Designing Convolutional Neural Networks using Surrogate assisted Genetic Algorithm for Medical Image Classification
Recently, Deep Learning (DL) algorithms have shown state-of-the-art performance in numerous tasks. The design of DL algorithms is time-consuming process that requires expert-level knowledge. To overcome this problem, Neural Architecture Search (NAS) is proposed, which automatically searches for the best neural network architecture for a given task. Indeed, evolutionary NAS has emerged as a widely studied research area, in which evolutionary algorithms are used to design neural networks. In this study, we proposed a novel encoding scheme to represent Convolutional Neural Network (CNN) architectures using continuous representation, which provides a larger search space and potentially finds better solutions compared to discrete representations. Moreover, it allows better exploitation of genetic operators, leading to a quick convergence of individuals. Furthermore, in order to reduce the computational time of the evaluation phase during the search process, surrogate models are used to provide an alternative objective function. To evaluate the effectiveness of the proposal, experiments are performed on CIFAR-10 and multiple datasets from the MedMNIST benchmark. The experimental results demonstrated the effectiveness of the proposed approach compared to several existing state-of-the-art algorithms.
- 15 July 2023
- Published by Association for Computing Machinery (ACM)
- p. 263-266
Open AccessDesigning Convolutional Neural Networks using Surrogate assisted Genetic Algorithm for Medical Image Classification
Recently, Deep Learning (DL) algorithms have shown state-of-the-art performance in numerous tasks. The design of DL algorithms is time-consuming process that requires expert-level knowledge. To overcome this problem, Neural Architecture Search (NAS) is proposed, which automatically searches for the best neural network architecture for a given task. Indeed, evolutionary NAS has emerged as a widely studied research area, in which evolutionary algorithms are used to design neural networks. In this study, we proposed a novel encoding scheme to represent Convolutional Neural Network (CNN) architectures using continuous representation, which provides a larger search space and potentially finds better solutions compared to discrete representations. Moreover, it allows better exploitation of genetic operators, leading to a quick convergence of individuals. Furthermore, in order to reduce the computational time of the evaluation phase during the search process, surrogate models are used to provide an alternative objective function. To evaluate the effectiveness of the proposal, experiments are performed on CIFAR-10 and multiple datasets from the MedMNIST benchmark. The experimental results demonstrated the effectiveness of the proposed approach compared to several existing state-of-the-art algorithms.
- Open Access
- 13 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 142114-142128
Novel Differential Evolutionary Optimization Approach for an Integrated Motor-Magnetic Gear Used for Propulsion Systems
This paper addresses the proposition of an electrical multiport propulsion system. This traction system contains an electric motor to which a magnetic gear is attached; it is called an integrated motor-magnetic gear (IMMG) propulsion unit. This IMMG has two shafts and two levels of torque and speed. Thus, it is suited for the propulsion of an electric tractor, which has different diameters for the front and rear wheels. The IMMG design is optimized based on the differential evolution (DE) algorithm. For such an algorithm, offline tuning of its parameters may fail given the different characteristics of optimization problems. Therefore, a parameter adaptation that considers feedback from the search process can be an alternative. In this work, we propose a novel online strategy to control the DE algorithm’s parameters. This strategy is based on a simple adaptation mechanism to generate a promising mutation parameter value for each individual in the population. The design process was evaluated through experiments, and a good correlation was found between the designed performances and tested results.
- 13 October 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 9, 142114-142128
Open AccessNovel Differential Evolutionary Optimization Approach for an Integrated Motor-Magnetic Gear Used for Propulsion Systems
This paper addresses the proposition of an electrical multiport propulsion system. This traction system contains an electric motor to which a magnetic gear is attached; it is called an integrated motor-magnetic gear (IMMG) propulsion unit. This IMMG has two shafts and two levels of torque and speed. Thus, it is suited for the propulsion of an electric tractor, which has different diameters for the front and rear wheels. The IMMG design is optimized based on the differential evolution (DE) algorithm. For such an algorithm, offline tuning of its parameters may fail given the different characteristics of optimization problems. Therefore, a parameter adaptation that considers feedback from the search process can be an alternative. In this work, we propose a novel online strategy to control the DE algorithm’s parameters. This strategy is based on a simple adaptation mechanism to generate a promising mutation parameter value for each individual in the population. The design process was evaluated through experiments, and a good correlation was found between the designed performances and tested results.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 713-720
An Eigenvector-Enhanced Parallel Adaptive Differential Evolution for Electric Motor Design
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 713-720
An Eigenvector-Enhanced Parallel Adaptive Differential Evolution for Electric Motor Design
- 12 June 2018
- Published by Springer Nature
- p. 501-517
A Hybrid Optimization Algorithm for Electric Motor Design
- 12 June 2018
- Published by Springer Nature
- p. 501-517
A Hybrid Optimization Algorithm for Electric Motor Design