Local discriminative spatial patterns for movement-related potentials-based EEG classification

被引:12
作者
Wang, Haixian [1 ]
Xu, Jiang [2 ]
机构
[1] Southeast Univ, Res Ctr Learning Sci, Nanjing 210096, Jiangsu, Peoples R China
[2] Southeast Univ, Sch Mech Engn, Nanjing 211189, Jiangsu, Peoples R China
基金
中国国家自然科学基金;
关键词
Brain-computer interface (BCI); Discriminative spatial patterns (DSP); Electroencephalogram (EEG) classification; Local information; SINGLE-TRIAL EEG; BRAIN-COMPUTER INTERFACES; FACE RECOGNITION; DIMENSIONALITY REDUCTION; COMMUNICATION; FILTERS; BCI;
D O I
10.1016/j.bspc.2010.12.004
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
A novel discriminant method, termed local discriminative spatial patterns (LDSP), is proposed for movement-related potentials (MRPs)-based single-trial electroencephalogram (EEG) classification. Different from conventional discriminative spatial patterns (DSP), LDSP explicitly considers local structure of EEG trials in the construction of scatter matrices in the Fisher-like criterion. The underlying manifold structure of two-dimensional spatio-temporal EEG signals contains more discriminative information. LDSP is an extension to DSP in the sense that DSP can be formulated as a special case of LDSP. By constructing an adjacency matrix, LDSP is calculated as a generalized eigenvalue problem, and so is computationally straightforward. Experiments on MRPs-based single-trial EEG classification show the effectiveness of the proposed LDSP method. (C) 2010 Elsevier Ltd. All rights reserved.
引用
收藏
页码:427 / 431
页数:5
相关论文
共 19 条
  • [1] Blankertz B, 2002, ADV NEUR IN, V14, P157
  • [2] The Berlin brain-computer interface:: EEG-based communication without subject training
    Blankertz, Benjamin
    Dornhege, Guido
    Krauledat, Matthias
    Mueller, Klaus-Robert
    Kunzmann, Volker
    Losch, Florian
    Curio, Gabriel
    [J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2006, 14 (02) : 147 - 152
  • [3] Boosting bit rates in noninvasive EEG single-trial classifications by feature combination and multiclass paradigms
    Dornhege, G
    Blankertz, B
    Curio, G
    Müller, KR
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2004, 51 (06) : 993 - 1002
  • [4] He XF, 2004, ADV NEUR IN, V16, P153
  • [5] Face recognition using Laplacianfaces
    He, XF
    Yan, SC
    Hu, YX
    Niyogi, P
    Zhang, HJ
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (03) : 328 - 340
  • [6] Face recognition based on 2D Fisherface approach
    Jing, XY
    Wong, HS
    Zhang, D
    [J]. PATTERN RECOGNITION, 2006, 39 (04) : 707 - 710
  • [7] Spatio-spectral filters for improving the classification of single trial EEG
    Lemm, S
    Blankertz, B
    Curio, G
    Müller, KR
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2005, 52 (09) : 1541 - 1548
  • [8] Combining spatial filters for the classification of, single-trial EEG in a finger movement task
    Liao, Xiang
    Yao, Dezhong
    Wu, Dan
    Li, Chaoyi
    [J]. IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2007, 54 (05) : 821 - 831
  • [9] Linear and nonlinear methods for brain-computer interfaces
    Müller, KR
    Anderson, CW
    Birch, GE
    [J]. IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, 2003, 11 (02) : 165 - 169
  • [10] Event-related EEG/MEG synchronization and desynchronization: basic principles
    Pfurtscheller, G
    da Silva, FHL
    [J]. CLINICAL NEUROPHYSIOLOGY, 1999, 110 (11) : 1842 - 1857