: Deoxyribonucleic acid (DNA) micro-arrays present a powerful means of observing thousands of gene terms levels at the same time. They consist of high dimensional datasets, which challenge conventional clustering methods. The data’s high dimensionality calls for Self Organizing Maps (SOMs) to cluster DNA micro-array data. The DNA micro-array dataset are stored in huge biological databases for several purposes . The proposed methods are based on the idea of selecting a gene subset to distinguish all classes, it will be more effective to solve a multi-class problem, and we will propose a genetic programming (GP) based approach to analyze multi-class micro-array datasets. This biological dataset will be derived from multiple biological databases. The procedure responsible for extracting datasets called DNA-Aggregator. We will design a biological aggregator, which aggregates various datasets via DNA micro-array community-developed ontology based upon the concept of semantic Web for integrating and exchanging biological data. Our aggregator is composed of modules that retrieve the data from various biological databases. It will also enable queries by other applications to recognize the genes. The genes will be categorized in groups based on a classification method, which collects similar expression patterns. Using a clustering method such as k-mean is required either to discover the groups of similar objects from the biological database to characterize the underlying data distribution. arabic 9 English 55
Mariam Abojela Msaad, Zakaria Suliman Zubi(1-2011)

This paper describes a comparative study of the performance of VoIP over wireless networks using OPNET tool. The simulation study is completed by running VoIP application in different network scenarios with IEEE 802.16 (UGS, ertPS) and IEEE 802.11 (b, g) with best effort service and interactive service The result clearly illustrated that the WiMax type ertPS has the best performance among all tested cases
Azeddien M. Sllame, Hana Soso, Mona Aown, Lamya Abdelmajeed(9-2016)

The manual detection and classification finding correct location and identifying type of tumor becomes a rigorous and hectic task for the radiologists. Medical diagnosis via image processing and machine learning is considered one of the most important issues of artificial intelligence systems. Deep learning has been used successfully in supervised classification tasks in order to learn complex patterns. The main contributions of this paper are as create a more generalized method for brain tumor classification using deep learning a variety of neural networks were constructed based on the preprocessing of image data., analyze the application of tumorless brain images on brain tumor classification and empirically evaluate neural networks on the given datasets with per image accuracy and per patient accuracy. And also presents an efficient image segmentation using machine learning algorithm with some optimization techniques to detect brain tumors. arabic 19 English 128
Mohamed Abdeldaiem Abdelhadi Mahboub(3-2019)