Feature Selection Algorithm for High-dimensional Biomedical Data using Information Gain and Improved Chemical Reaction Optimization

(E-pub Ahead of Print)

Author(s): Ge Zhang, Pan Yu, Jianlin Wang*, Chaokun Yan*

Journal Name: Current Bioinformatics

Become EABM
Become Reviewer


Background: There have been rapid developments in various bioinformatics technologies, which have led to the accumulation of a large amount of biomedical data However, these datasets usually involve thousands of features and include many irrelevant or redundant information, which leads to confuse during diagnosis. Feature selection is a solution that consists in finding the optimal subset, which is known to be an NP problem because of the large search space.

Objective: For the issue, this paper proposes a hybrid feature selection method based on an improved chemical reaction optimization algorithm (ICRO) and information gain (IG) approach, called IGICRO.

Method: IG is adopted to obtain some important feature subsets. The neighborhood search mechanism is combined with ICRO to increase the diversity of the population and improve the capacity of local search.

Results: Experimental results on eight publicly available data sets demonstrate that our proposed approach outperforms original CRO and other state-of-the-art approaches.

Keywords: Feature selection, Chemical reaction optimization algorithm (CRO), Information gain, Neighborhood search mechanism, Biomedical data, Optimal subset

Rights & PermissionsPrintExport Cite as

Article Details

(E-pub Ahead of Print)
DOI: 10.2174/1574893615666200204154358
Price: $95