Get started
Work

A Comparative Analysis of Feature Selection Algorithms for Cancer Classification Using Gene Expression Microarray Data

Year: 2023
Type: article
Abstract: DNA Microarray technology allows simultaneous analysis of gene expression levels, making it useful in cancer classification.However, analyzing Microarray data is challenging due to the large number of genes and their sparsity.Feature selection has emerged as an effective method to overcome these challenges.This research aims to study the impact of three well-known feature selection algorithms (ReliefF, Chi Square, and ANOVA) in enhancing the accuracy of gene expression profile classification.A three-stage approach was employed: data preprocessing, feature selection, and feature classification.The focus is on selecting relevant features to accurately represent the problem under study.Four classifiers, i.e., SVM, GNB, LDA, and KNN, were evaluated using the aforementioned feature selection algorithms.The proposed methodology was tested on 10 publicly available gene expression datasets.Using all genes, the SVM classifier showed the best accuracy and F1 scores, followed by the LDA classifier.When applying the ReliefF feature selection algorithm, the SVM classifier performed best with a 5% dataset ratio.Moreover, the ANOVA feature selection algorithm yielded optimal results with the SVM classifier at dataset ratios of 3%, 4%, and 5%.Lastly, the Chi-square feature selection consistently produced the best results with both SVM and GNB classifiers for all dataset ratios.The study underscores the significance of feature selection for improving gene expression profile classification accuracy.The findings of this research offer promising insights into the analysis of microarray data, which can be instrumental in enhancing the accuracy of cancer classification.
DOI: 10.18280/ria.370316
Language: English
Open Access status: hybrid
OpenAlex ID: W4385386554
FWCI:
Cites: 55
Cited by:
Related to: 10