A multi-objective heuristic algorithm for gene expression microarray data classification

作者：

Highlights：

• A multi-objective model for microarray based on analytic hierarchy process is built.

• A heuristic algorithm improved from UMDA called MOEDA is to solve the model.

• Both classification accuracy and number of genes are the objectives.

• The classification accuracy is treated absolutely important than the number of genes.

• It always gets high accuracy with small number of genes on microarray data.

摘要

•A multi-objective model for microarray based on analytic hierarchy process is built.•A heuristic algorithm improved from UMDA called MOEDA is to solve the model.•Both classification accuracy and number of genes are the objectives.•The classification accuracy is treated absolutely important than the number of genes.•It always gets high accuracy with small number of genes on microarray data.

论文关键词：Microarray,Gene selection,Small number of selected genes,Multi-objective,Heuristic algorithm

论文评审过程：Received 26 May 2015, Revised 29 February 2016, Accepted 16 April 2016, Available online 19 April 2016, Version of Record 26 April 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.04.020