A Method Based on Filter Bank Common Spatial Pattern for Multiclass Motor Imagery BCI

被引：1

作者：

Xia, Ziqing ^{[1
,2
]}

Xia, Likun ^{[1
,2
,3
,4
]}

Ma, Ming ^{[5
]}

机构：

[1] Capital Normal Univ, Coll Informat Engn, Beijing, Peoples R China

[2] Lab Neural Comp & Intelligent Percept NCIP, New York, NY 10027 USA

[3] Int Sci & Technol Cooperat Base Elect Syst Reliab, Beijing, Peoples R China

[4] Beijing Adv Innovat Ctr Imaging Technol, Beijing, Peoples R China

[5] Stanford Univ, Sch Med, Stanford, CA 94305 USA

来源：

INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING (IDEAL 2019), PT II | 2019年 / 11872卷

关键词：

Brain-computer interface; Motor imagery; Machine learning; EEG; CLASSIFICATION; MACHINE;

D O I：

10.1007/978-3-030-33617-2_16

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The Common Spatial Pattern (CSP) algorithm is capable of solving the binary classification problem for the motor image task brain-computer interface (BCI). This paper proposes a novel method based on the Filter Bank Common Spatial Pattern (FBCSP) termed the Multiscale and Overlapping FBCSP (MO-FBCSP). We extend the CSP algorithm for multiclass by using the one-versus-one (OvO) strategy. Multiple periods are selected and combined with the overlapping spectrum of the filter bank which contains useful information. This method is evaluated on the benchmark BCI Competition IV dataset 2a with 9 subjects. An average accuracy of 80% was achieved with the random forest (RF) classifier, and the corresponding kappa value was 0.734. Quantitative results have shown that the proposed scheme outperforms the classical FBCSP algorithm by over 12%.

引用

页码：141 / 149

页数：9

共 22 条

[1] Multilevel Weighted Feature Fusion Using Convolutional Neural Networks for EEG Motor Imagery Classification [J].

Amin, Syed Umar ;

Alsulaiman, Mansour ;

Muhammad, Ghulam ;

Bencherif, Mohamed A. ;

Hossain, M. Shamim .

IEEE ACCESS, 2019, 7 :18940-18950

[2] Filter bank common spatial pattern algorithm on BCI competition IV Datasets 2a and 2b [J].

Ang, Kai Keng ;

Chin, Zheng Yang ;

Wang, Chuanchu ;

Guan, Cuntai ;

Zhang, Haihong .

FRONTIERS IN NEUROSCIENCE, 2012, 6

[3] Multiclass Brain-Computer Interface Classification by Riemannian Geometry [J].

Barachant, Alexandre ;

Bonnet, Stephane ;

Congedo, Marco ;

Jutten, Christian .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2012, 59 (04) :920-928

[4]

Brunner C., BCI Competition 2008Graz Data Set A

[5] Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms [J].

Dornhege, G ;

Blankertz, B ;

Curio, G ;

Müller, KR .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2004, 51 (06) :993-1002

[6] Combined optimization of spatial and temporal filters for improving brain-computer interfacing [J].

Dornhege, Guido ;

Blankertz, Benjamin ;

Krauledat, Matthias ;

Losch, Florian ;

Curio, Gabriel ;

Mueller, Klaus-Robert .

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2006, 53 (11) :2274-2281

[7] A multi-class EEG-based BCI classification using multivariate empirical mode decomposition based filtering and Riemannian geometry [J].

Gaur, Pramod ;

Pachori, Ram Bilas ;

Wang, Hui ;

Prasad, Girijesh .

EXPERT SYSTEMS WITH APPLICATIONS, 2018, 95 :201-211

[8] Common Bayesian Network for Classification of EEG-Based Multiclass Motor Imagery BCI [J].

He, Lianghua ;

Hu, Die ;

Wan, Meng ;

Wen, Ying ;

von Deneen, Karen M. ;

Zhou, MengChu .

IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS, 2016, 46 (06) :843-854

[9]

Hersche M, 2018, EUR SIGNAL PR CONF, P1690, DOI 10.23919/EUSIPCO.2018.8553378

[10] A Classification Algorithm for Electroencephalography Signals by Self-Induced Emotional Stimuli [J].

Iacoviello, Daniela ;

Petracca, Andrea ;

Spezialetti, Matteo ;

Placidi, Giuseppe .

IEEE TRANSACTIONS ON CYBERNETICS, 2016, 46 (12) :3171-3180

← 1 2 3 →