Mohamed CHOUAI

Dr. Mohamed CHOUAI

orcid

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 April 2022 in IEEE Latin America Transactions
Verified
Journal Article
Closed access
BCBilal Djamal Eddine Cherif
Bilal Djamal Eddine Cherif
MCMohamed CHOUAI
Mohamed CHOUAI
SSSara Seninete
Sara Seninete
BABendiabdellah Azeddine
Bendiabdellah Azeddine
The principal objective of this paper is to detect and automatically monitor switch open-circuit faults in a two-level three-phase voltage source inverter fed induction motor from the processing of its current signals. The proposed diagnostic method uses both signal processing techniques and machine learning techniques in order to detect and localize the switch under an open-circuit fault. First, the Hilbert-Huang transform using the empirical ensemble mode decomposition is employed for each phase current signal, which leads to extracting the intrinsic mode functions. In order to optimally choose the function indicating the open-circuit fault harmonic, two factors, namely, the root mean square and the correlation coefficient are calculated out for each function. In this regard, two criteria are proposed that lead to choose the optimal function giving better information about the defected phase. The spectral envelope of the optimal function permits extra0cting the fault harmonic of the switch. Second, different machine learning techniques are applied to locate and classify the switch open-circuit faults with the hyper-parameters optimization for a better design of the different models. Finally, a comparative study of the different machine learning techniques is carried out for determining the best classifier for the open-circuit faults. The experimental results effectively demonstrate a very high classification rate of 98.98%.

15 August 2020 in Micromachines
Verified
Journal Article
Open access
PDF file
SLSIDI SALAH LAKHDAR
SIDI SALAH LAKHDAR
MCMohamed CHOUAI
Mohamed CHOUAI
YDYann Danlée
Yann Danlée
IHIsabelle Huynen
Isabelle Huynen
NONassira Ouslimani
Nassira Ouslimani
Electronic devices that transmit, distribute, or utilize electrical energy create electromagnetic interference (EMI) that can lead to malfunctioning and degradation of electronic devices. EMI shielding materials block the unwanted electromagnetic waves from reaching the target material. EMI issues can be solved by using a new family of building blocks constituted of polymer and nanofillers. The electromagnetic absorption index of this material is calculated by measuring the “S-parameters”. In this article, we investigated the use of artificial intelligence (AI) in the EMI shielding field by developing a new system based on a multilayer perceptron neural network designed to predict the electromagnetic absorption of polycarbonate-carbon nanotubes composites films. The proposed system included 15 different multilayer perception (MLP) networks; each network was specialized to predict the absorption value of a specific category sample. The selection of appropriate networks was done automatically, using an independent block. Optimization of the hyper-parameters using hold-out validation was required to ensure the best results. To evaluate the performance of our system, we calculated the similarity error, precision accuracy, and calculation time. The results obtained over our database showed clearly that the system provided a very good result with an average accuracy of 99.7997%, with an overall average calculation time of 0.01295 s. The composite based on polycarbonate−5 wt.% carbon nanotube was found to be the ultimate absorber over microwave range according to Rozanov formalism.

30 August 2021 in Sensors
Verified
Journal Article
Open access
PDF file
MCMohamed CHOUAI
Mohamed CHOUAI
Petr DolezelPetr Dolezel
Petr Dolezel
DSDominik Stursa
Dominik Stursa
ZNZdenek Nemec
Zdenek Nemec
In the field of computer vision, object detection consists of automatically finding objects in images by giving their positions. The most common fields of application are safety systems (pedestrian detection, identification of behavior) and control systems. Another important application is head/person detection, which is the primary material for road safety, rescue, surveillance, etc. In this study, we developed a new approach based on two parallel Deeplapv3+ to improve the performance of the person detection system. For the implementation of our semantic segmentation model, a working methodology with two types of ground truths extracted from the bounding boxes given by the original ground truths was established. The approach has been implemented in our two private datasets as well as in a public dataset. To show the performance of the proposed system, a comparative analysis was carried out on two deep learning semantic segmentation state-of-art models: SegNet and U-Net. By achieving 99.14% of global accuracy, the result demonstrated that the developed strategy could be an efficient way to build a deep neural network model for semantic segmentation. This strategy can be used, not only for the detection of the human head but also be applied in several semantic segmentation applications.

1 June 2020 in Journal of Transportation Security
Verified
Journal Article
Closed access
PDF file
MCMohamed CHOUAI
Mohamed CHOUAI
MMMostefa Merah
Mostefa Merah
MMMalika Mimi
Malika Mimi
MMMerah Mustefa
Merah Mustefa

30 March 2021 in Materials
Verified
Journal Article
Open access
PDF file
SLSIDI SALAH LAKHDAR
SIDI SALAH LAKHDAR
NONassira Ouslimani
Nassira Ouslimani
MCMohamed CHOUAI
Mohamed CHOUAI
YDYann Danlée
Yann Danlée
IHIsabelle Huynen
Isabelle Huynen
AHaksas hammouche
aksas hammouche
Polycarbonate—carbon nanotube (PC-CNT) conductive composites containing CNT concentration covering 0.25–4.5 wt.% were prepared by melt blending extrusion. The alternating current (AC) conductivity of the composites has been investigated. The percolation threshold of the PC-CNT composites was theoretically determined using the classical theory of percolation followed by numerical analysis, quantifying the conductivity of PC-CNT at the critical volume CNT concentration. Different theoretical models like Bueche, McCullough and Mamunya have been applied to predict the AC conductivity of the composites using a hyperparameter optimization method. Through multiple series of the hyperparameter optimization process, it was found that McCullough and Mamunya theoretical models for electrical conductivity fit remarkably with our experimental results; the degree of chain branching and the aspect ratio are estimated to be 0.91 and 167 according to these models. The development of a new model based on a modified Sohi model is in good agreement with our data, with a coefficient of determination R2=0.922 for an optimized design model. The conductivity is correlated to the electromagnetic absorption (EM) index showing a fine fit with Steffen–Boltzmann (SB) model, indicating the ultimate CNTs volume concentration for microwave absorption at the studied frequency range.

1 October 2019 in Journal of Intelligent Manufacturing
Verified
Journal Article
Closed access
PDF file
MCMohamed CHOUAI
Mohamed CHOUAI
MMMostefa Merah
Mostefa Merah
JSJosé-Luis Sancho-Gómez
José-Luis Sancho-Gómez
MMMalika Mimi
Malika Mimi