期刊名称：International Journal of Multimedia and Ubiquitous Engineering
印刷版ISSN：1975-0080
出版年度：2015
卷号：10
期号：2
页码：321-332
DOI：10.14257/ijmue.2015.10.2.29
出版社：SERSC
摘要：Soft set theory proposed by Molodtsov is a new mathematical tool for dealing with the uncertain data. Soft set-based dimensionality reduction can be considered as a technique for feature selection. In this paper, we present an alternative technique for feature selection of traditional Malay musical instrument sounds dataset. The technique is based on matrices computation of multi-soft sets for dimensionality reduction. The dataset is taken from our previous work which consists of 1116 instances and 37 attributes of Malay Musical Instrument Sounds Dataset. The result shows that the obtained features of proposed technique are 35 out of 37 features.
关键词：Soft set theory; Feature selection; Traditional Malay musical instruments ; sound dataset
