Title: Research on bioinformatics data classification method based on support vector machine

Authors: Hui Yan; Yunxin Long; Chao Lv; Ping Yu; Duo Long

Addresses: Suqian University, Jiangsu, 223800, China ' College of Traditional Codeledinese Medicine, Changchun University of Chinese Medicine, Changchun, 130117, China ' Jilin Province S&T Innovation Center for Physical Simulation and Security of Water Resources and Electric Power Engineering, Changchun Institute of Technology, Changchun, 130012, China ' Jilin Province S&T Innovation Center for Physical Simulation and Security of Water Resources and Electric Power Engineering, Changchun Institute of Technology, Changchun, 130012, China ' Suqian University, Jiangsu, 223800, China

Abstract: Due to the problems of low classification accuracy and long classification time in traditional biological information data classification methods, a biological information data classification method based on support vector machine is proposed. Bio-information data was acquired through gene expression and the characteristics analysed. Based on the data analysis results, outlier detection and data scaling for the acquired bio-information data are carried out. Based on the processing results, mutual information is used to measure the correlation and redundancy, then, the bio-information data features are selected through the feature selection algorithm of minimum redundancy and maximum correlation, and finally, the selected bio-information data features are taken as data samples. Through support vector machine, the classification decision function is established under the conditions of linear and non-separable data samples to obtain the classification results of biological information data. The experimental results show that the proposed method has higher classification accuracy and shorter classification time.

Keywords: support vector machine; bioinformation; data classification; minimum redundancy and maximum correlation; feature selection.

DOI: 10.1504/IJDMB.2025.142975

International Journal of Data Mining and Bioinformatics, 2025 Vol.29 No.1/2, pp.21 - 35

Received: 23 Apr 2023
Accepted: 26 Oct 2023
Published online: 02 Dec 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article