期刊名称：International Journal of Computer Science and Network
印刷版ISSN：2277-5420
出版年度：2016
卷号：5
期号：4
页码：609-614
出版社：IJCSN publisher
摘要：Process of selecting relevant features fromavailable dataset is known as features selection. Featureselection is use to remove or reduce redundant and irrelevantfeatures. Various feature selection algorithms such as CFS(correlation feature selection), FCBF (Fast Correlation BasedFilter) and CMIM (Conditional Mutual InformationMaximization) are used to remove redundant and irrelevantfeatures. To determine efficiency and effectiveness is the aimof feature selection algorithm. Time factor is denoted byefficiency and quality factor is denoted by effectiveness ofsubset of features. Problem of feature selection algorithm isaccuracy is not guaranteed, computational complexity islarge, ineffective at removing redundant features. Toovercome these problems Fast Clustering based featureselection algorithm (FAST) is used. Removal of irrelevantfeatures, construction of MST (Minimum Spanning Tree)from relative one and partition of MST and selectingrepresentative features using kruskal’s method are the threesteps used by FAST algorithm
关键词：Feature Clustering; Feature Subset Selection;Minimum Spanning Tree
