文章基本信息

标题：Gene Selection and Classification Using Linear Support Vector Machine Based On Microarray Data
本地全文：下载
作者：Dr. T.Karthikeyan ; Dr. B.Ragavan ; S.Sruthi 等
期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：7
DOI：10.15680/ijircce.2015. 0307052
出版社：S&S Publications
摘要：Microarraydata play an important role in the development of efficient cancer diagnoses andclassification System using Gene Expression Data. However, micro array expression data are usually redundant andnoisy, and only a subset of them present distinct profiles for different classes of samples. Thus, selecting highdiscriminative genes from gene expression data has become increasingly interesting in the field of bioinformatics. Inthis paper, a multi-objective biogeography based optimization method is proposed to select the small subset ofinformative relevant to the classification. A typical microarray gene expression dataset is usually both extremely sparseand imbalanced. To select multiple highly informative gene subsets for cancer classification and diagnosis,a hybrid algorithm has been proposed of statistical learning, Principle component analysis, PSO clustering, andgranular computing separately eliminates irrelevant, redundant, or noisy genes in different granules at different stagesand selects highly informative genes with potentially different biological functions in balance. To show theeffectiveness of the proposed approach, we compare the performance of this technique with the signal-to-noise ratio(SNR) and Fmeasure. Using gene microarray datasets dataset from the adult stem cell (including both binary and multiclassclassification problems), we demonstrate experimentally that our proposed scheme can achieve significantempirical success and is biologically relevant for cancer diagnosis and drug discovery in terms of performance factorslike precision , recall and Fmeasure.
关键词：Cancer Classification; Microarray data; Fuzzy Preference; Particle Swarm Optimization; Principle;Component Analysis Support Vector Machine