文章基本信息

标题：IMPROVED MOTH FLAME OPTIMIZATION BASED ON HARRIS HAWKS FOR GENESSELECTION
本地全文：下载
作者：RUBA ABU KHURMA ; IBRAHIM ALJARAH ; AHMAD SHARIEH 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2020
卷号：98
期号：23
页码：3794-3807
出版社：Journal of Theoretical and Applied
摘要：Microarray technology is a major shift in the medical and diagnostic fields. Gene expression data are coded by a large number of genes and a limited number of patient�s samples. This causes a challenging problem for the gene selection (GS) methods to specify the most relevant and reliable genes for cancer diagnosis. Recently, meta-heuristic (MH) algorithms have made an evident contribution in handling the gene expression data. A great expansion has been achieved in developing robust and efficient cancer diagnostic systems. In this chapter, a hybrid MH-MH wrapper, called IMFOHHO is proposed for the GS problem. The proposed approach is based on hybridizing the Moth Flame Optimization (MFO) algorithms and Harris Hawks Optimization (HHO) to improve the exploration and the exploitation phases. The main purpose is to integrate the excellent features of both algorithms in one model and overcome their limitations when experienced in the gene search space. Combining two swarm systems in one model can achieve strong exploration for the gene space and ensure the diversity of solutions. The performance of the proposed method has been evaluated using ten gene expression data sets. The comparative study demonstrates that the IMFOHHO model enhances the classification performance without increasing the computational complexity.
关键词：Genes selection (GS);Microarray;Harris Hawks Optimization (HHO);Moth Flame Optimization (MFO);Classification.