文献类型：期刊文献

英文题名：Learning Common Time-Frequency-Spatial Patterns for Motor Imagery Classification

作者：Miao, Yangyang[1];Jin, Jing[1];Daly, Ian[2];Zuo, Cili[1];Wang, Xingyu[1];Cichocki, Andrzej[3,4];Jung, Tzyy-Ping[5]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Univ Essex, Sch Comp Sci & Elect Engn, Brain Comp Interfacing & Neural Engn Lab, Colchester CO4 3SQ, Essex, England;[3]Skolkovo Inst Sci & Technol, Moscow 121205, Russia;[4]Nicolaus Copernicus Univ UMK, PL-87100 Torun, Poland;[5]Univ Calif San Diego, Inst Neural Computat, Swartz Ctr Computat Neurosci, La Jolla, CA 92093 USA

年份：2021

卷号：29

起止页码：699

外文期刊名：IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING

收录：;EI(收录号：20211510209712);WOS:【SCI-EXPANDED(收录号:WOS:000640713000002)】；

基金：This work was supported in part by the National Key Research and Development Program under Grant 2017YFB13003002; in part by the National Natural Science Foundation of China, under Grant 61573142, Grant 61773164, and Grant 91420302; in part by the programme of Introducing Talents of Discipline to Universities (the 111 Project) under Grant B17017; in part by the Ministry of Education and Science of the Russian Federation under Grant 14.756.31.0001; in part by the Polish National Science Center under Grant UMO-2016/20/W/NZ4/00354; and in part by the "ShuGuang" Project supported by the Shanghai Municipal Education Commission and Shanghai Education Development Foundation under Grant 19SG25.

语种：英文

外文关键词：Electroencephalography; Feature extraction; Spatial filters; Support vector machines; Time-frequency analysis; Task analysis; Training; Common spatial patterns (CSP); motor imagery (MI); electroencephalogram (EEG); brain-computer interface (BCI)

摘要：The common spatial patterns (CSP) algorithm is the most popular spatial filtering method applied to extract electroencephalogram (EEG) features for motor imagery (MI) based brain-computer interface (BCI) systems. The effectiveness of the CSP algorithm depends on optimal selection of the frequency band and time window from the EEG. Many algorithms have been designed to optimize frequency band selection for CSP, while few algorithms seek to optimize the time window. This study proposes a novel framework, termed common time-frequency-spatial patterns (CTFSP), to extract sparse CSP features from multi-band filtered EEG data in multiple time windows. Specifically, the whole MI period is first segmented into multiple subseries using a sliding time window approach. Then, sparse CSP features are extracted from multiple frequency bands in each time window. Finally, multiple support vector machine (SVM) classifiers with the Radial Basis Function (RBF) kernel are trained to identify the MI tasks and the voting result of these classifiers determines the final output of the BCI. This study applies the proposed CTFSP algorithm to three public EEG datasets (BCI competition III dataset IVa, BCI competition III dataset IIIa, and BCI competition IV dataset 1) to validate its effectiveness, compared against several other state-of-the-art methods. The experimental results demonstrate that the proposed algorithm is a promising candidate for improving the performance of MI-BCI systems.