Mohamed Hamlich

Mohamed Hamlich

Auto-generated profile, based on publicly available information

Mohamed Hamlich

University of Hassan II

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
1 October 2019 in Journal of Environmental Chemical Engineering
Verified
Journal Article
Closed access
FEF. Echabbi
F. Echabbi
MHM. Hamlich
M. Hamlich
SHS. Harkati
S. Harkati
AJA. Jouali
A. Jouali
STS. Tahiri
S. Tahiri
MSM. Safi
M. Safi

1 January 2019 in AIMS Energy
Verified
Journal Article
Open access
PDF file
AKAbdelkarim El Khantach
Abdelkarim El Khantach
MHMohamed Hamlich
Mohamed Hamlich
NBNour Eddine Belbounaguia
Nour Eddine Belbounaguia
The accuracy of electricity consumption forecasts is of paramount importance in energy planning, it provides strong support for the effective energy demand management. In this work, we proposed a load forecast through the decomposition of the historical time series in relation to the historical evolution of each hour of the day. The output of these decomposition were served as input to different algorithms of machine learning. We tested our model by five machines learning methods, the achieved results are examined with three of the most commonly used evaluation measures in forecasting. The obtained results were very satisfactory.

1 January 2022 in SoftwareX
Verified
Journal Article
Open access
MGMoncef Garouani
Moncef Garouani
AAAdeel Ahmad
Adeel Ahmad
MBMourad Bouneffa
Mourad Bouneffa
MHMohamed Hamlich
Mohamed Hamlich

1 April 2019
Verified
Conference Paper
Closed access
YMYoussef Msala
Youssef Msala
MHMohamed Hamlich
Mohamed Hamlich
AMAhmed Mouchtachi
Ahmed Mouchtachi
In the field of multi-robots, various research works have addressed the problem of coordination and task division between robots. Coordination in a multi-robot system is necessary when they collaborate to perform a given task or simultaneously share the same resources. The coordination aims to ensure that each robot in the multi-robot system (MRS) performs its tasks safely. As well as a good method of distribution and assignment of tasks must be effective, reliable and well-defined. In this work, we will present a conceptual architecture, that ensures coordination between the entire team of heterogeneous robots and then a new strategy based on artificial intelligence algorithms to assign tasks for a heterogeneous MRS in the optimal way.

1 June 2023 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
PDF file
MCMeryem Chaabi
Meryem Chaabi
MHMohamed Hamlich
Mohamed Hamlich
MGMoncef Garouani
Moncef Garouani
To meet customer expectations and remain competitive, industrials try constantly to improve their quality control systems. There is hence increasing demand for adopting automatic defect detection solutions. However, the biggest issue in addressing such systems is the imbalanced aspect of industrial datasets. Often, defect-free samples far exceed the defected ones, due to continuous improvement approaches adopted by manufacturing companies. In this sense, we propose an automatic defect detection system based on one-class classification (OCC) since it involves only normal samples during training. It consists of three sub-models, first, a convolutional autoencoder serves as latent features extractor, the extracted features vectors are subsequently fed into the dimensionality reduction process by performing principal component analysis (PCA), then the reduced-dimensional data are used to train the one-class classifier support vector data description (SVDD). During the test phase, both normal and defected images are used. The first two stages of the trained model generate a low-dimensional features vector, whereas the SVDD classifies the new input, whether it is defect-free or defected. This approach is evaluated on the carpet images from the industrial inspection dataset MVTec anomaly detection (MVTec AD). During training, only normal images were used. The results showed that the proposed method outperforms the state-of-the-art methods.