Cancer Classification using Support Vector Machines and Relevance Vector Machine based on Analysis of Variance Features | Science Publications

Journal of Computer Science

A. M. Natarajan¹  A. Bharathi¹ 

关键词: Gene expressions;    cancer classification;    neural networks;    Continuous Wavelet Transform (CWT);    Support Vector Machine (SVM);    Relevance Vector Machine (RVM);    Principal Component Analysis (PCA);    Generalized Singular Value Decomposition (GSVD);    Singular Value Decomposition (SVD);   

DOI  :  10.3844/jcssp.2011.1393.1399

学科分类：计算机科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: The objective of this study is, to find the smallest set of genes that canensure highly accurate classification of cancer from micro array data by using supervised machinelearning algorithms. The significance of finding the minimum subset is three fold: The computationalburden and noise arising from irrelevant genes are much reduced; the cost for cancer testing is reducedsignificantly as it simplifies the gene expression tests to include only a very small number of genesrather than thousands of genes; it calls for more investigation into the probable biological relationshipbetween these small numbers of genes and cancer development and treatment. Approach: Theproposed method involves two steps. In the first step, some important genes were chosen with the helpof Analysis of Variance (ANOVA) ranking scheme. In the second step, the classification capabilitywas tested for all simple combinations of those important genes using a better classifier. Results: Theproposed method initially uses Support Vector Machine (SVM) classifier. Relevance Vector Machine(RVM) classifier was used for increasing the classification accuracy over SVM classifier. Conclusion:The experimental result shows that the proposed method performs the cancer classification with betteraccuracy when compared to the conventional methods.

【 授权许可】

Unknown