https://dspace.univ-ouargla.dz/jspui/handle/123456789/1541 Tue, 21 Apr 2026 17:42:50 GMT 2026-04-21T17:42:50Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/21997 Titre: Denoising Medical Ultrasound Images and Error Estimate by Cellular Neural Networks and Translation Invariant Wavelets Auteur(s): Rachida, BOUCHOUAREB; Djamel, BENATIA Résumé: Speckle Noise is a natural characteristic of medical ultrasound images. It is a term used for the granular form that appears in B-Scan and can be considered as a kind of multiplicative noise. Speckle Noise reduces the ability of an observer to distinguish fine details in diagnostic testing. It also limits the effective implementation of image processing such as edge detection, segmentation and volume rendering in 3 D. Therefore; treatment methods of speckle noise were sought to improve the image quality and to increase the capacity of diagnostic medical ultrasound images. Such as median filters, Wiener and linear filters (Persona & Mali, SRAD ...).The first method used in this work is newly invented by Chua & Yang called Cellular Neural Networks (CNN), the second method is 2-D translation invariant forward wavelet transform, both are used in image processing, including noise reduction applications in medical imaging. Description: The Second International Conference on Electrical Engineering and Control Applications Tue, 18 Nov 2014 00:00:00 GMT https://dspace.univ-ouargla.dz/jspui/handle/123456789/21997 2014-11-18T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/20984 Titre: Image Classification Using Texture Features and Support Vector Machine (SVM) Auteur(s): Khaldi, Belal; Aiadi, Oussama; KHERFI, Mohammed Lamine Résumé: Due to their efficiency, texture features are frequently used for describing visual content of images. In this paper, we compare six widely used texture features namely, Weber Local Descriptor (WLD), Local Binary Pattern (LBP), Gist and Gray- Level Co-occurrence Matrix (GLCM), in addition to two recent ones namely, Three-Dimensional Connectivity Index (TDCI) and Dense Micro-block Difference (DMD). Moreover, we have proposed an improvement of TDCI so it can capture local variation of motifs instead of the global. As a classifier, we have considered using Support vector Machine (SVM). After conducting a detailed evaluation on four well-known texture benchmarks which are Broadatz, Vistext, Outext and DTD, we have found out that WLD has, in average, the best performance compared to the other features. Description: Le 2eme Conference Internationale sur intelligence Artificielle et les Technologies Information ICAIIT 2019 Mon, 04 Mar 2019 00:00:00 GMT https://dspace.univ-ouargla.dz/jspui/handle/123456789/20984 2019-03-04T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/20983 Titre: On The Use Of KStar Algorithm For Predicting Object-Oriented Software Maintainability Auteur(s): Zighed, Narimane; Bounour, Nora Résumé: This paper presents an ongoing work on using KStar algorithm to predict Object-Oriented software maintainability. The maintainability is measured as the number of changes made to code throughout the maintenance period by using Object-Oriented software metrics. We build a prediction model based on data collected from two different Object-Oriented systems. However, to figure out the advantages of KStar algorithm we made five experiments with the Weka machine learning workbench and to compare our proposed model with the other algorithms which are (linear Regression, Neural Network, Decision Tree, SVM), the prediction accuracy of all models is evaluated and compared using cross-validation and different types of accuracy measures. As a result, KStar yields better results and it demonstrated to be the best of them to predict more accurately than the other typical techniques. Description: Le 2eme Conference Internationale sur intelligence Artificielle et les Technologies Information ICAIIT 2019 Tue, 05 Mar 2019 00:00:00 GMT https://dspace.univ-ouargla.dz/jspui/handle/123456789/20983 2019-03-05T00:00:00Z https://dspace.univ-ouargla.dz/jspui/handle/123456789/20981 Titre: Datawarehouse-based approach for the analysis of terrorism-related activities in social networks Auteur(s): DJABALLAH, Kamel AHSENE; BOUKHALFA, Kamel; BOUSSAID, Omar Résumé: Social network analysis techniques for activities related to terrorism are mainly based on data mining techniques. These techniques do not take into account the various axes of analysis allowing a study according to several facets. In this article we propose a comparison study of these techniques. We present our approach of analyzing these activities, based on Data warehouse and OLAP analysis. We aim to improve the analysis of these cyber threats. OLAP analysis allows us to explore social networks to detect dangerous content in the direction of targeted cyber threats. Our approach is based on five-tier architecture: (1) data sources; (2) ETL; (3) Data warehouse; (4) Analysis; (5) Presentation. In our experimentations, we used Twitter to detect and analyze the incitement to terrorism and determine the users supported the terrorism. We proposed a datamart with a metric named score, calculated using a data mining technique. Also, we used OLAP analysis techniques, based on the history of positive scores, to determine the users inciting terrorism, their locations and their retweets. Description: Le 2eme Conference Internationale sur intelligence Artificielle et les Technologies Information ICAIIT 2019 Tue, 05 Mar 2019 00:00:00 GMT https://dspace.univ-ouargla.dz/jspui/handle/123456789/20981 2019-03-05T00:00:00Z