Browsing by Author "El-Deeb, Hesham"

Now showing 1 - 4 of 4

A Comparative Study of Game Tree Searching Methods
(SCIENCE & INFORMATION SAI ORGANIZATION LTD, 2014-05) El-Deeb, Hesham; Gadallah, Mahmoud; Aziem, Mostafa Abdel; Elnaggar, Ahmed A
In this paper, a comprehensive survey on gaming tree searching methods that can use to find the best move in two players zero-sum computer games was introduced. The purpose of this paper is to discuss, compares and analyzes various sequential and parallel algorithms of gaming tree, including some enhancement for them. Furthermore, a number of open research areas and suggestions of future work in this field are mentioned.
Enhanced HGS Algorithm (EHGSA) for Cost Reduction Regression Testing
(IEEE, 2015) El-Din, Mohamed Alaa; Taha, Ismail Abd El-Hamid; El-Deeb, Hesham
reducing techniques for test suites aims to cost decreasing of system testing via smart removal of the repeated test cases from the original suite and still generating reduced tests set that keeping the original percentage of the software coverage as the original one. This paper proposes an enhanced algorithm (EHGSA), based on the concept of HGS algorithm and the Greedy algorithm, generating minimized test suite having lower run time cost. The proposed algorithm is reduced the cost of conducting a test suite if it is compared with relative techniques. The comparison is conducted among the HGS, Greedy and the EHGSA for cases containing nested IF statements and other comparison for cases having non-nested IF statements. The proposed algorithm exhibits robust behavior in both comparisons
Enhanced Leukemia Cancer Classifier Algorithm
(IEEE, 2014) Abd El-Nasser, Ahmed; Shaheen, Mohamed; El-Deeb, Hesham
The development of data mining applications such as classification and clustering has shown the need for machine learning algorithms to be applied to large scale data. Cancer classification has improved over the past 20 years; there has been no general approach for identifying new cancer classes or for assigning tumors to known classes (class prediction). Most proposed cancer classification methods are from the statistical and machine learning area, ranging from the old nearest neighbor analysis, to the new support vector machines. There is no single classifier that is superior over the rest. A generic approach to cancer classification based on gene expression monitoring by DNA microarrays is described and applied to human acute leukemia as a test case. A class discovery procedure automatically discovered the distinction between acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL) with previous knowledge of these classes. There are two main objectives of this research, the first is to introduce the design and implementation of SMIG (Select Most Informative Genes) Algorithm, and the second objective is to design and Implement Enhanced Classification algorithm (ECA) system to enhance Leukemia cancer classification using SMIG module and ranking procedure. The proposed approach and experiments showed that after conducting the preprocessing and the classification using the proposed ECA system it can be reached in 0.1 s time the accuracy of 98% which is better when compared to previous techniques in previously published studies.
Enhanced Parallel NegaMax Tree Search Algorithm on GPU
(IEEE, 2014) Elnaggar, Ahmed A.; Gadallah, Mahmoud; Aziem, Mostafa Abdel; El-Deeb, Hesham
Parallel performance for GPUs today surpasses the traditional multi-core CPUs. Currently, many researchers started to test several AI algorithms on GPUs instead of CPUs, especially after the release of libraries such as CUDA and OpenCL that allows the implementation of general algorithms on the GPU. One of the most famous game tree search algorithms is Negamax, which tries to find the optimal next move for zero sum games. In this research, an implementation of an enhanced parallel NegaMax algorithm is presented, that runs on GPU using CUDA library. The enhanced algorithms use techniques such as no divergence, dynamic parallelism and shared GPU table. The approach was tested in checkers and chess games. It was compared with previous studies, including threads on CPU for up to 6x speedup for an 8 core processor and threads on GPU using iterative dependence and fixed grid and block size for up to 40x speedup at 14 depth. Furthermore, the approach was tested with different depths on the CPU and the GPU. The result shows speed up for parallel GPU up to 80x at 14 depth for checkers game and 90x at 14 depth for chess game, which doubled the previous research results.