Complex independent component analysis of frequency-domain electroencephalographic data

被引:152
作者
Anemüller, J
Sejnowski, TJ
Makeig, S
机构
[1] Univ Calif San Diego, Inst Neural Computat, Swartz Ctr Computat Neurosci, La Jolla, CA 92093 USA
[2] Salk Inst Biol Studies, Computat Neurobiol Lab, La Jolla, CA 92037 USA
关键词
complex independent component analysis; frequency-domain; convolutive mixing; biomedical signal analysis; electroencephalogram; event-related potential; visual selective attention;
D O I
10.1016/j.neunet.2003.08.003
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Independent component analysis (ICA) has proven useful for modeling brain and electroencephalographic (EEG) data. Here, we present a new, generalized method to better capture the dynamics of brain signals than previous ICA algorithms. We regard EEG sources as eliciting spatio-temporal activity patterns, corresponding to, e.g. trajectories of activation propagating across cortex. This leads to a model of convolutive signal superposition, in contrast with the commonly used instantaneous mixing model. In the frequency-domain, convolutive mixing is equivalent to multiplicative mixing of complex signal sources within distinct spectral bands. We decompose the recorded spectral-domain signals into independent components by a complex infomax ICA algorithm. First results from a visual attention EEG experiment exhibit: (1) sources of spatio-temporal dynamics in the data, (2) links to subject behavior, (3) sources with a limited spectral extent, and (4) a higher degree of independence compared to sources derived by standard ICA. (C) 2003 Elsevier Ltd. All rights reserved.
引用
收藏
页码:1311 / 1323
页数:13
相关论文
共 26 条
  • [1] Amari S, 1996, ADV NEUR IN, V8, P757
  • [2] Adaptive separation of acoustic sources for anechoic conditions:: A constrained frequency domain approach
    Anemüller, J
    Kollmeier, B
    [J]. SPEECH COMMUNICATION, 2003, 39 (1-2) : 79 - 95
  • [3] ANEMULLER J, 2001, THESIS U OLDENBURG
  • [4] [Anonymous], P INT WORKSH IND COM
  • [5] [Anonymous], INDEPENDENT COMPONEN
  • [6] Dynamics of ongoing activity: Explanation of the large variability in evoked cortical responses
    Arieli, A
    Sterkin, A
    Grinvald, A
    Aertsen, A
    [J]. SCIENCE, 1996, 273 (5283) : 1868 - 1871
  • [7] AN INFORMATION MAXIMIZATION APPROACH TO BLIND SEPARATION AND BLIND DECONVOLUTION
    BELL, AJ
    SEJNOWSKI, TJ
    [J]. NEURAL COMPUTATION, 1995, 7 (06) : 1129 - 1159
  • [8] Electroencephalogram in humans
    Berger, H
    [J]. ARCHIV FUR PSYCHIATRIE UND NERVENKRANKHEITEN, 1929, 87 : 527 - 570
  • [9] Bloomfield P, 2000, FOURIER ANAL TIME SE
  • [10] STIMULUS NOVELTY, TASK RELEVANCE AND VISUAL EVOKED-POTENTIAL IN MAN
    COURCHESNE, E
    HILLYARD, SA
    GALAMBOS, R
    [J]. ELECTROENCEPHALOGRAPHY AND CLINICAL NEUROPHYSIOLOGY, 1975, 39 (02): : 131 - 143