An efficient multivariate feature ranking method for gene selection in high-dimensional microarray data
作者：
Highlights：
• Classification of microarray data plays a significant role in the diagnosis of cancer.
• Feature selection is necessary for better analysis due to its high-dimensionality.
• An efficient multivariate feature selection method is proposed for microarray data.
• We demonstrate its usefulness of high accuracy and good efficiency using real data.
• The method outperforms other comparable gene selection methods in terms of accuracy.
摘要
•Classification of microarray data plays a significant role in the diagnosis of cancer.•Feature selection is necessary for better analysis due to its high-dimensionality.•An efficient multivariate feature selection method is proposed for microarray data.•We demonstrate its usefulness of high accuracy and good efficiency using real data.•The method outperforms other comparable gene selection methods in terms of accuracy.
论文关键词：Multivariate feature selection,Gene selection,High-dimensional data,Microarray data,Classification,Multiclass,Mixed-type data,Markov blanket,Ranking
论文评审过程：Received 24 March 2020, Revised 25 August 2020, Accepted 2 September 2020, Available online 20 September 2020, Version of Record 10 October 2020.
论文官网地址：https://doi.org/10.1016/j.eswa.2020.113971
