Leukemia Cancer Comparative Classifires Suite | ||||
The International Conference on Electrical Engineering | ||||
Article 55, Volume 9, 9th International Conference on Electrical Engineering ICEENG 2014, May 2014, Page 1-6 PDF (149.97 K) | ||||
Document Type: Original Article | ||||
DOI: 10.21608/iceeng.2014.30470 | ||||
View on SCiNiTO | ||||
Authors | ||||
Ahmed Abd El-Nasser1; Mohamed Shaheen2; Hesham El-Deeb3 | ||||
1Modern Academy in Maadi. | ||||
2Arab Academy for Science, technology, and Maritime Transport. | ||||
3Faculty of Computer Science, M.T.I University. | ||||
Abstract | ||||
A major problem in bioinformatics analysis or medical science is in attaining the correct diagnosis of certain important information. For the ultimate diagnosis, normally, many tests generally involve the clustering or classification Microarray data classification is used primarily to predict unseen data using a model built on categorized existing Microarray data. The applications of microarray technology are able to utilize information and knowledge from human genome project to benefit human health. In the last few years, the remarkable progress achieved in microarray technology domain has helped researchers to develop the optimized treatment of cancer. Human acute leukemia is used as test case to a generic approach to cancer classification, this classification approach is based on gene expression monitoring by DNA microarrays that distinct between acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL). The objective of this research is to investigate and compare the accuracy, time to build model, and errors of classification process using Locally Weighted Learning (LWL) algorithm with nine different classifiers (Bayes Network learning, Conjunctive Rule, NBTree, Voting Frequency Intervals (VFI), Random SubSpace, Naïve Bayes Updateable, DIMM, Kstar, and PART); to previous tested datasets after performing some preprocessing to the datasets to enhance the classification process. The proposed approach and experiments showed that after conducting the preprocessing and the classification using Voting Frequency Intervals, Random Sub Space and Naïve Bayes Updateable algorithms through LWL approach it can be reached in 0.1 s time and accuracy of 94% which is outperform the other previous techniques for the same data when comparing with previous published studies. | ||||
Keywords | ||||
Bioinformatics; classification; Data mining; DNA; Leukemia; LWL | ||||
Statistics Article View: 126 PDF Download: 146 |
||||