Higher Institute of Applied Science and Technology

Damascus, United States

Higher Institute of Applied Science and Technology

Damascus, United States
SEARCH FILTERS
Time filter
Source Type

Sghaier S.,University of Monastir | Souani C.,Higher Institute of Applied science and Technology | Faeidh H.,Higher Institute of Applied science and Technology | Besbes K.,University of Monastir
Studies in Computational Intelligence | Year: 2017

Representing and extracting good quality of facial feature extraction is an essential step in many applications, such as face recognition, pose normalization, expression recognition, human–computer interaction and face tracking. We are interested in the extraction of the pertinent features in 3D face. In this paper, we propose an improved algorithm for 3D face characterization. We propose novel characteristics based on seven salient points of the 3D face. We have used the Euclidean distances and the angles between these points. This step is highly important in 3D face recognition. Our original technique allows fully automated processing, treating incomplete and noisy input data. Besides, it is robust against holes in a meshed image and insensitive to facial expressions. Moreover, it is suitable for different resolutions of images. All the experiments have been performed on the FRAV3D and GAVAB databases. © Springer International Publishing Switzerland 2017.


Necibi O.,Tunis el Manar University | Guesmi C.,Tunis el Manar University | Naoui S.,Tunis el Manar University | Naoui S.,Higher Institute of Applied science and Technology | Gharsallah A.,Tunis el Manar University
International Journal on Communications Antenna and Propagation | Year: 2016

This paper presents a novel method to identify the numerical digits based on the RF signals. When integrated on dielectric substrate and excited with an electromagnetic wave, every number integrated with metallic strips shows an electromagnetic signature. This signature is unique and characterizes the RCS of the radiating number. Consequently, it could be used for identification purposes. Aafrequencyadomainaapproachawas applied to a set of numbers corresponding to the standard numeration. Simulationaresultsaobtainedawith the electromagnetic simulation software CST-MWS® (Computer Simulation Technology-Microwave-studio) are presented and discussed in this paper. The results of this study confirm that the signatures of each number can establish an algorithm for number recognition and identification without errors. © 2016 Praise Worthy Prize S.r.l. - All rights reserved.


Abdelkarim M.,University of Tunis | Naoui S.,University of Tunis | Naoui S.,Higher Institute of Applied Science and Technology | Gharsallah A.,Tunis el Manar University
International Journal on Communications Antenna and Propagation | Year: 2016

In this paper, a dipole antenna with Spiral Split Ring Resonators (SSRR) for RFID reader is proposed, this novel miniaturized metamaterials is characterized by a very small size compared to the classical resonator introduced by J. Pendry, then by the constituting of a negative permeability (µeff) around the resonance frequency. The dipole antenna based on metamaterials is proposed to increase the performance (Directivity, Gain and bandwidth) and reducing the dimensions of RFID reader antennas that operate in the SHF band (2.4-2.485GHz). © 2016 Praise Worthy Prize S.r.l. - All rights reserved.


Hamrita M.E.,Higher Institute of Applied science and Technology | Mabrouk A.B.,University of Monastir
International Journal of Wavelets, Multiresolution and Information Processing | Year: 2011

Scaling laws and generally self-similar structures are now well known facts in financial time series. Furthermore, these signals are characterized by the presence of stochastic behavior allowing their analysis with pure functional methods being incomplete. In the present paper, some existing models are reviewed and modified, based on wavelet theory and self-similarity, to recover multi-scaling cases for approximating financial signals. The resulting models are then tested on some empirical examples and analyzed for error estimates. © 2011 World Scientific Publishing Company.


Ben Salah C.,University of Sfax | Ben Mabrouk A.,Higher Institute of Applied science and Technology | Ouali M.,University of Sfax
International Multi-Conference on Systems, Signals and Devices, SSD'11 - Summary Proceedings | Year: 2011

In this paper wavelet decomposition is combined with autoregressive models to analyze and predict climate time series such as solar radiation and photovoltaic cell temperature. The method is tested on climate parameters for analysis, and solar radiation and cell temperature for prediction. The work effectiveness is evaluated by the prediction of the electric energy produced by a 100 Wp photovoltaic panel. Finally, the performance of predictor is measured by standardized error. © 2011 IEEE.


Assar S.,TELECOM Business School | Assar S.,Paris-Sorbonne University | Assar S.,Higher Institute of Applied Science and Technology | Souveyet C.,TELECOM Business School | And 5 more authors.
Proceedings - International Computer Software and Applications Conference | Year: 2012

Goal modeling is a prominent design paradigm in various domains of information systems engineering. In the field of service oriented computing (SOC) and in the field of semantic web services, emergent research works are basing their engineering approach on the goal concept. Because of the complexity of processes underlying SOC, the usage of the goal concept can vary to a large extent. In this paper, we study approaches to service oriented engineering and propose a framework to analyze and better understand how the goal concept is used in web service discovery. The framework is inspired by the four world vision of information systems engineering (i.e. subject, system, development and usage). Using this framework, we review eight prominent research works in SOE. Through this analysis, we seek to better understand the link between semantic web technologies and the goal concept, and what are the challenging issues in terms of goal usage in service discovery. © 2012 IEEE.


Messai S.,Higher Institute of Applied science and Technology | Ganaoui M.E.,Institut Universitaire de France | Sghaier J.,University of Tunis | Belghith A.,University of Tunis
Thermal Science | Year: 2014

An experimental study to evaluate the convective heat transfer coefficient in a cylindrical packed bed of spherical porous alumina particles is investigated. The task consists in proposing a semi-empirical model to avoid excessive instrumentation and time consumption. The measurement of the bed temperature associated to a simple energy balances led to calculate the gas to particle heat transfer coefficient using a logarithmic mean temperature difference method. These experiments were performed at atmospheric pressure. The operating fluid is humid air. The gas velocity and temperature ranged from 1.7-3 m/s and 120-158 °C, respectively. The data obtained was compared with the correlations reported in the literature. It is shown that the proposed model is in reasonable agreement with the correlation of Ranz and Marshall. Despite, many researches on experimental investigations of heat transfer coefficient in packed beds at low and average temperature are proposed, few studies presented calculation of convective heat transfer coefficient at high temperature (above 120 °C). A possible application of the proposed model is drying and combustion.


Blaiech H.,University of Monastir | Sayadi F.E.,Higher Institute of Applied Science and Technology | Tourki R.,University of Monastir
Proceedings of the 2011 International Conference on Image Processing, Computer Vision, and Pattern Recognition, IPCV 2011 | Year: 2011

This paper presents a hardware implementation of face and eyes detection algorithm. To become we must go through several stages. First we have implemented an algorithm for detecting and tracking eyes written in C using an open source library of image processing and computer vision the "OpenCV". Then a profiling on HW/SW (hardware/software) partition was done. The hardware part solves the part of the algorithm with higher computational costs. The system has been implemented on SpartaniA DSP FPGA board. In order to visualize the results on real images, we have made a co-simulation of this bloc using the Simulink tool of Matlab.


Abroug I.,Higher Institute of Applied science and Technology | Abroug I.,University of Sousse | Essoukri Ben Amara N.,University of Sousse | Essoukri Ben Amara N.,University of Monastir
12th International Multi-Conference on Systems, Signals and Devices, SSD 2015 | Year: 2015

In this paper we present an approach of face recognition by using a planar multi-classifier modelling based on neural networks. Each class of the database has been modelled by a PMCM-NN/NN formed by three secondary models and a main one - of an MLP type. We have retained the same characteristics and database used in [2]. The various experiments have been proven on a FERET face database. The recorded results have shown the contribution of our proposed concepts for the generalization of planar models, initially based on HMMs, to other types of classifiers - neural in this case. The validation of the PMCM in the case of face recognition shows results that are very promising and better than those registered in [2]. © 2015 IEEE.


Saadaoui F.,Higher Institute of Applied science and Technology | Rabbouch H.,National School in Computer Science
Expert Systems with Applications | Year: 2014

The paper proposes a parsimonious nonlinear framework for modeling bivariate stochastic processes. The method is a vector autoregressive-like approach equipped with a wavelet-based feedforward neural network, allowing practitioners dealing with extremely random two-dimensional information to make predictions and plan their future more and more precisely. Artificial Neural Networks (ANN) are recognized as powerful computing devices and universal approximators that proved valuable for a wide range of univariate time series problems. We expand their coverage to handle nonlinear bivariate data. Wavelet techniques are used to strengthen the procedure, since they allow to break up processes information into a finite number of sub-signals, and subsequently extract microscopic patterns in both time and frequency fields. The proposed model can be very valuable especially when modeling nonlinear econophysical systems with high extent of volatility. © 2014 Elsevier Ltd. All rights reserved.

Loading Higher Institute of Applied Science and Technology collaborators
Loading Higher Institute of Applied Science and Technology collaborators