EEG feature selection method based on decision tree

doi:10.3233/BME-151397

	EEG feature selection method based on decision tree
	Duan, Lijuan 1,3; Ge, Hui 1,3; Ma, Wei 1,3; Miao, Jun 2
	2015
发表期刊	BIO-MEDICAL MATERIALS AND ENGINEERING
ISSN	0959-2989
卷号	26 页码:S1019-S1025
摘要	This paper aims to solve automated feature selection problem in brain computer interface (BCI). In order to automate feature selection process, we proposed a novel EEG feature selection method based on decision tree (DT). During the electroencephalogram (EEG) signal processing, a feature extraction method based on principle component analysis (PCA) was used, and the selection process based on decision tree was performed by searching the feature space and automatically selecting optimal features. Considering that EEG signals are a series of non-linear signals, a generalized linear classifier named support vector machine (SVM) was chosen. In order to test the validity of the proposed method, we applied the EEG feature selection method based on decision tree to BCI Competition II datasets Ia, and the experiment showed encouraging results.
关键词	Decision tree feature selection optimal features EEG brain-computer interface
DOI	10.3233/BME-151397
收录类别	SCI
语种	英语
资助项目	Natural Science Foundation of China[61003105] ; Natural Science Foundation of China[61175115] ; Natural Science Foundation of China[61370113] ; Natural Science Foundation of China[61272320] ; Beijing Municipal Natural Science Foundation[4152005] ; Beijing Municipal Natural Science Foundation[4152006] ; Importation and Development of High-Caliber Talents Project of Beijing Municipal Institutions (CIT) ; Jing-Hua Talents Project of Beijing University of Technology[2014-JH-L06] ; Ri-Xin Talents Project of Beijing University of Technology[2014-RX-L06] ; Research Fund of Beijing Municipal Commission of Education[PXM2015_014204_500221] ; International Communication Ability Development Plan for Young Teachers of Beijing University of Technology[2014-16] ; Importation and Development of High-Caliber Talents Project of Beijing Municipal Institutions[TCD201304035]
WOS研究方向	Engineering ; Materials Science
WOS类目	Engineering, Biomedical ; Materials Science, Biomaterials
WOS记录号	WOS:000361671800115
出版者	IOS PRESS
引用统计	被引频次：12[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/9345
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Miao, Jun
作者单位	1.Beijing Univ Technol, Coll Comp Sci & Technol, Beijing Key Lab Integrat & Anal Large Scale Strea, Key Lab Trusted Comp, Beijing 100124, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 3.Natl Engn Lab Crit Technol Informat Secur Classif, Beijing 100124, Peoples R China
推荐引用方式 GB/T 7714	Duan, Lijuan,Ge, Hui,Ma, Wei,et al. EEG feature selection method based on decision tree[J]. BIO-MEDICAL MATERIALS AND ENGINEERING,2015,26:S1019-S1025.
APA	Duan, Lijuan,Ge, Hui,Ma, Wei,&Miao, Jun.(2015).EEG feature selection method based on decision tree.BIO-MEDICAL MATERIALS AND ENGINEERING,26,S1019-S1025.
MLA	Duan, Lijuan,et al."EEG feature selection method based on decision tree".BIO-MEDICAL MATERIALS AND ENGINEERING 26(2015):S1019-S1025.