Browsing by Author "Khebli, A."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Mechanical Performances of Honeycomb Structures Reinforced by a Magnetorheological Elastomer Material: Experimental and Numerical Approaches
    (2024) Djedid, Toufik; Nour, A.; Aguib, S.; Chikh, N.; Settet, A.T.; Khebli, A.; Kobzili, L.; Boudjana, Abderzak; Tourab, M.
    In this article, the performance of mechanical resistance against failure of mechanical structures under bending load was studied by the use of a hybrid sandwich composite (Magnetorheo- logical Elastomer (MRE) - Honeycomb). Accordingly, a series of four-point bending mechanical tests were carried out. In addition, a comparison of the force-deflection responses, the values of the maxi- mum forces supported by each sample before damage were determined. Through the additional effect of the MRE core, the hybrid sandwich composite samples presented the best performances in terms of energy absorption-dissipation, and thanks to the effect of the honeycomb part, the Hybrid sandwich composite samples presented the best performance in terms of mechanical strength. To validate the performance of these developed hybrid structures, the numerical results are compared with the corre- sponding experimental results.
  • No Thumbnail Available
    Item
    A new technique based on 3D convolutional neural networks and filtering optical flow maps for action classification in infrared video
    (Control Engineering and Applied Informatics Journal, 2019) Khebli, A.; Meglouli, H.; Bentabet, L.; Airouche, M.
    Human action in video sequences provides three-dimensional spatio-temporal signals that characterize both visual appearance and motion dynamics. The aim of this work is to recognize human action in infrared video by focusing mainly on dynamic information. We developed a new technique based on deep 3D convolutional neural networks (3D CNNs) that take optical flow maps as input. Our approach consists mainly of three parts: 1) computation of optical flow maps; 2) filtering of these maps, using an entropy measurement in order to increase the classification rate and reduce the run time by eliminating sequences that do not contain human action; and 3) classification using 3D CNN. The experimental results obtained by our approach on the InfAR dataset show considerable improvement in comparison with results obtained by existing models.