标题:A New Motor Imagery EEG Classification Method FB-TRCSP+RF based on CSP and Random Forest
作者:Zhang, Ranran ;Xiao, Xiaoyan ;Liu, Zhi ;Jiang, Wei ;Li, Jianwen ;Cao, Yankun ;Ren, Jianmin ;Jiang, Dongmei ;Cui, Lizhen
作者机构:[Zhang, Ranran ;Liu, Zhi ;Jiang, Wei ;Li, Jianwen ;Cao, Yankun ] School of Information Science and Engineering, Shandong University, Qingdao; 266237, 更多
通讯作者:Liu, Zhi
来源:IEEE Access
出版年:2018
页码:44944-44950
DOI:10.1109/ACCESS.2018.2860633
关键词:classification; Classification algorithms; Covariance matrices; CSP; Electroencephalography; FB−TRCSP+RF; feature; Feature extraction; Forestry; Spatial filters; Training
摘要:There is general agreement in the brain computer interface (BCI) community that the feature extracting method called the common spatial pattern (CSP) combined with nonlinear classifiers can provide better results in some cases. However, CSP is also known to be very sensitive to noise and prone to over fitting, and the performance of this spatial filter is closely related to the operational frequency band of the EEG data. To address this issue, we propose a new method FB−TRCSP+RF based on the CSP and the random forest methods. The FB-TRCSP is combined by the 8th-order Butterworth bandpass-filters and the CSP with Tikhonov regularization, which is a more robust feature extraction method compared to the CSP. Then, the model is applied to an experimental data set collected from 14 subjects and is compared with the non-regularization method FB-CSP+RF. The results show that the method we proposed, using a particular combination feature selection and classification algorithm, yields relatively higher median classification accuracies and stronger abilities in subject-to-subject learning, compared to prevailing approaches. OAPA
收录类别:EI;SCOPUS
资源类型:期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85050746492&doi=10.1109%2fACCESS.2018.2860633&partnerID=40&md5=d5888e484b15e6feebf579d594342ea5
TOP