TY  - EJOU
AU  - Poongodi, K. 
AU  - Sabari, A. 

TI  - Identification of Bio-Markers for Cancer Classification Using Ensemble Approach and Genetic Algorithm
T2  - Intelligent Automation \& Soft Computing

PY  - 2022
VL  - 33
IS  - 2
SN  - 2326-005X

AB  - The microarray gene expression data has a large number of genes with different expression levels. Analyzing and classifying datasets with entire gene space is quite difficult because there are only a few genes that are informative. The identification of bio-marker genes is significant because it improves the diagnosis of cancer disease and personalized medicine is suggested accordingly. Initially, the parallelized minimum redundancy and maximum relevance ensemble (mRMRe) is employed to select top m informative genes. The selected genes are then fed into the Genetic Algorithm (GA) that selects the optimal set of genes heuristically, which uses Mahalanobis Distance (MD) as the distance measure. This proposed method (mRMRe-GA) is applied to four microarray datasets using Support Vector Machine (SVM) as a classifier. The Leave One out Cross Validation (LOOCV) method is used to analyze the performance of the classifier. Comparative study of the proposed mRMRe-GA method is carried out with other methods. The proposed mRMRe-GA method significantly improves the classification accuracy with less number of selected genes.
KW  - mRMR; mRMRe; microarray; gene expression data; GA; feature selection; SVM; cancer classification; mRMRe-GA

DO  - 10.32604/iasc.2022.023038