文章基本信息

标题：Filter-Wrapper Combination and Embedded Feature Selection for Gene Expression Data
本地全文：下载
作者：Shilan S. Hameed ; Olutomilayo Olayemi Petinrin ; Abdirahman Osman Hashi 等
期刊名称：International Journal of Advances in Soft Computing and Its Applications
印刷版ISSN：2074-8523
出版年度：2018
卷号：10
期号：1
页码：90
出版社：International Center for Scientific Research and Studies
摘要：Biomedical and bioinformatics datasets are generally large interms of their number of features - and include redundant andirrelevant features, which affect the effectiveness and efficiency ofclassification of these datasets. Several different features selectionmethods have been utilised in various fields, includingbioinformatics, to reduce the number of features. This study utilisedFilter-Wrapper combination and embedded (LASSO) featureselection methods on both high and low dimensional datasets beforeclassification was performed. The results illustrate that thecombination of filter and wrapper feature selection to create a hybridform of feature selection provides better performance than usingfilter only. In addition, LASSO performed better on highdimensional data.
关键词：Bioinformatics; Gene Expression Data; Feature Selection; Filter;Methods; Wrapper Methods.