Color Image Enhancement Using Steady State Genetic Algorithm Reyadh Naoum, Ala'a Al-Sabbah College of Information Technology Middle East University, Jordan. Abstract: The purpose of this paper is to enhance the colored images using the  enhancement developed steady state genetic algorithm, SSGA, with modified fitness  function to get more accurate result and less noise. In this paper the Hue Saturation  Intensity (HSV) color model will  be used, after enhance the S, H and V components  the transformation will be made to RGB color model. We have developed three  models for enhancing the colorful and chromaity of the image with different types of  input - output and different type of parameter. The models are compared based on  their ability to train with lowest error values. To use these models the  input RGB  color image is converted to an intensity image using Space Variant Luminance Map  SVLM. Keywords : Image processing; color enhancement; steady state genetic algorithm; the  hue saturation intensity; space variant luminance map. Arabic Content Classification System Using statistical Bayes classifier With Words Detection and Correction Abdullah Mamoun Hattab, Abdulameer Khalaf Hussein Department of Computer science Middle East University, Jordan. Abstract: Automatic Arabic content classification is an important text mining task  especially with the rapid growth of the number of online Arabic documents. This  system is an enhancement of the implemented machine learning classification  algorithm by applying detection and correction algorithm of Non-Words in Arabic text.  This detection and correction algorithm is built on morphological knowledge in form  of consistent root pattern relationships, and some morpho-syntactical knowledge  based on affixation and morph-graphic rules to specify the word recognition and non-  word correction process. Many researchers had been focused on Arabic content  classification from only morphological view such as word’s root and stemming  techniques (prefixes and suffixes) which showed variant results. In this work, consider classification from a very different way which is the syntactical approach. This paper  presents the results of experiments on document classification achieved on ten  different Arabic domains (Economy, History, Family studies, Islamic, Sport, Health,  Law, Stories, astronomy and Food articles) using statistical methodology. The  performance of this classification system showed encouraging results compared with  other existing systems. Keywords : text mining; classification; Arabic text classification; Arabic language  processing. Cournot and Bertrand Game Models for A Simple Spectrum Sharing Framework in Cognitive Radio Networks Hadi Malekpour, Reza Berangi Computer Engineering Iran University of Science and Technology, Iran. Abstract: Cognitive radio technology has been proposed to achieve a more efficient  spectrum usage by using spectrum opportunities in time, frequency and space which is  not fully used by a licensed system (primary system), but without disturbing the  primary system. In this paper, we address the problem of spectrum sharing among one primary user and two secondary users. We model this problem as a game and use  Cournot and Bertrand game models for spectrum allocation to secondary users. In  each game model we first present the formulation of static cases when the secondary  users can observe the adopted strategies and the payoff of each other. However, this  assumption may not be realistic in some cognitive radio systems. Therefore, we  formulate dynamic approaches in which the secondary users just communicate with  the primary user. The stability conditions of the dynamic behavior for these spectrum  sharing schemes is investigated. Keywords : spectrum sharing; cognitive radio; game theory. Text-Independent Speaker Identification Using Hidden Markov Model Sayed Jaafer Abdallah, Izzeldin Mohamed Osman, Mohamed Elhafiz Mustafa College of Computer Science and Information Technology, Sudan University of Science and Technology, Sudan. Abstract: This paper presents a text-independent speaker identification system based  on Mel-Frequency Cepstrum Coefficient (MFCC) feature vectors and Hidden Markov  Model (HMM) classifier. The implementation of the HMM is divided into two steps:  feature extraction and recognition. In the feature extraction step, the paper reviews  MFCCs by which the spectral features of speech signal can be estimated and shows  how these features can be computed. In the recognition step, the theory and  implementation of HMM are reviewed and followed by an explanation of how HMM can  be trained to generate the model parameters using Forward-Backward algorithm and  tested using forward algorithm. The HMM is evaluated using data of 40 speakers  extracted from Switchboard corpus. Experimental results show an identification rate  of about 84%. Keywords : Speaker identification; MFCC; HMM; Feature extraction; Forward-  Backward; and Switchboard.