Accepted Papers
- Robust Colour Image Watermarking Scheme Based On Feature Points And Image Normalization In DCT Domain
Ibrahim Alsonosi Nasir,Sebha University, LibyaABSTRACT
Geometric attacks can desynchronize the location of the watermark and hence cause incorrect watermark detection. This paper presents a robust colour image watermarking scheme based on visually significant feature points and image normalization technique. The feature points are used as synchronization marks between watermark embedding and detection. The watermark is embedded into the non overlapped normalized circular regions in the luminance component or the blue component of a color image. The embedding of the watermark is carried out by modifying the DCT coefficients values in selected blocks. The original unmarked image is not required for watermark extraction Experimental results show that the proposed scheme successfully makes the watermark perceptually invisible as well as robust to common signal processing and geometric attacks. - Evaluation Of An Information Fusion Models Based Data Mining Technique To Improve The Segmentation Of Medical Images
Lamiche Chaabane1,Moussaoui Abdelouahab2,1University of M’sila,2University of Setif, AlgeriaABSTRACT
The aim of this work is to evaluate the segmentation of medical images of human brain using three data fusion models based data mining method and possibility theory concepts. Our proposed approach consists of three principals points : (1) a data coming from T1-weighted, T2-weighted and PD-weighted images is extracted and modeled separately using an adequate data mining algorithm, (2) the three fuzzy maps provided in the first step are combined with a combination rule which can managing the uncertainty and ambiguity in the different images. (3) the final segmented image is obtained in decision step. - La construction d’un lexique de polarité pour l’identification de l’opinion dans le texte arabe.
ABIDI karima1,Guiassa Yamina Tlili2,1École supérieur d’informatique,2Université Badji Mokhtar ,AlgerieABSTRACT
La recherche présenté dans cet article s’inscrit dans le domaine de la fouille d’opinion, un domaine qui consiste à localiser les passages porteurs d’opinion dans une collection textuelle afin pour les classer qu’ils soit objectifs ou subjectifs, le calcule de la polarité nécessite un ensemble de ressources et de lexiques qui sont malheureusement rare pour la langue arabe et sont plus souvent construit a partir d’un petit nombre de mot, notre objectif et de développer un modèle de construction d’un lexique d’opinion (de valence) pour la langue arabe. - Study And Review Of Fuzzy Inference Systems For Decision Making And Control
Swati Chaudhari and Manoj Patil,SSBT’s COET Bambhori,IndiaABSTRACT
The fuzzy inference system with weighted average is computationally efficient and useful for dynamic nonlinear system control while the system that defuzzifies the fuzzy output into crisp is best suited for decision making and control. However in these systems complexity with high order polynomials and a substantial computational burden rises when used separately. Multilayer approach with weighted average and defuzzification set in layers can reduce the cost of defuzzification and lack of output expressivity that causes risk when used as a controller. The adaptive fuzzy system with this approach makes the system exploitable for areas requiring easy interpretation and human reasoning. In this review paper there is the study of fuzzy inference systems and a multilayer system is proposed with defuzzification and weighted average. - Fuzzy Similarity For Document Retrieval
Marwa Massaabi and Wahiba Ben Abdessalem Karaa,University of Tunis,TunisiaABSTRACT
Information retrieval is a very important research field. However, retrieving needed information has become a delicate task due to the huge amount of data available on the web. Duplicated documents are a major cause that made of it an irritating burden. In this paper, we propose a new fuzzy similarity measure which detects automatically the similarity between documents and eliminates duplications. This approach combines fuzzy logic and distance measurements to achieve its goal. It has shown remaquable results. - Application Of Neural Networks Technique In Renewable Energy Systems
Lamine Thiaw ,Gustave Sow and Salif Sagana Fall,Ecole Superieure Polytechnique de Dakar,SenegalABSTRACT
Artificial Intelligence (AI) techniques are increasingly used in various area due to their capability of handling complex systems specificities. Among the techniques of AI, Artificial Neural Networks (ANN) technique plays an important role. This technique is used in this work to perform important tasks encountered in Photovoltaic systems and in Wind Energy Systems: a) Maximum Power Point Tracking (MPPT) of Photovoltaic Generators; b) and wind energy ressource assessment. It is shown how a neural network technique can be used to design an MPPT controller for photovoltaic generators, enabling to improve their eciency, and how it is possible to assess the available and recov- erable wind energy potential of a site, by means of nding an adequate distribution law of the wind speeds based on a neural model. The proposed methods are illustrated by simulation results which exhibit the advantages of using ANN techniques in Renewable Energy Systems.
