Maximum-likelihood estimation of low-rank signals for multiepoch MEG/EEG analysis

被引:20
作者
Baryshnikov, BV
Van Veen, BD
Wakai, RT
机构
[1] Univ Wisconsin, Dept Phys Med, Madison, WI 53706 USA
[2] Univ Wisconsin, Dept Elect & Comp Engn, Madison, WI 53706 USA
基金
美国国家卫生研究院;
关键词
electroencephalography; evoked responses; magnetoencephalography; maximum likelihood parameter estimation; principal component analysis;
D O I
10.1109/TBME.2004.834285
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
A maximum-likelihood-based algorithm is presented for reducing the effects of spatially colored noise in evoked response magneto- and electro-encephalography data. The repeated component of the data, or signal of interest, is modeled as the mean, while the noise is modeled as the Kronecker product of a spatial and a temporal covariance matrix. The temporal covariance matrix is assumed known or estimated prior to the application of the algorithm. The spatial covariance structure is estimated as part of the maximum-likelihood procedure. The mean matrix representing the signal of interest is assumed to be low-rank due to the temporal and spatial structure of the data. The maximum-likelihood estimates of the components of the low-rank signal structure are derived in order to estimate the signal component. The relationship between this approach and principal component analysis (PCA) is explored. In contrast to prestimulus-based whitening followed by PCA, the maximum-likelihood approach does not require signal-free data for noise whitening. Consequently, the maximum-likelihood approach is much more effective with nonstationary noise and produces better quality whitening for a given data record length. The efficacy of this approach is demonstrated using simulated and real MEG data.
引用
收藏
页码:1981 / 1993
页数:13
相关论文
共 19 条
[1]   A mathematical approach to the temporal stationarity of background noise in MEG/EEG measurements [J].
Bijma, F ;
de Munck, JC ;
Huizenga, HM ;
Heethaar, RM .
NEUROIMAGE, 2003, 20 (01) :233-243
[2]   Estimating stationary dipoles from MEG/EEG data contaminated with spatially and temporally correlated background noise [J].
de Munck, JC ;
Huizenga, HM ;
Waldorp, LJ ;
Heethaar, RM .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2002, 50 (07) :1565-1572
[3]   Generalized multivariate analysis of variance [J].
Dogandzic, A ;
Nehorai, A .
IEEE SIGNAL PROCESSING MAGAZINE, 2003, 20 (05) :39-54
[4]  
Golub GH, 2013, Matrix Computations, V4
[5]  
GRAY RM, 1972, IEEE T INFORM THEORY, V18, P725, DOI 10.1109/TIT.1972.1054924
[6]  
Jolliffe I. T., 1986, Principal Component Analysis, DOI [DOI 10.1016/0169-7439(87)80084-9, 10.1007/0-387-22440-8_13, DOI 10.1007/0-387-22440-8_13]
[7]  
Kay S. M., 1993, Fundamentals of Statistical Signal Processing: Estimation Theory
[8]  
KELLY EJ, 1989, 848 LINC LAB
[9]  
KNUUTILA J, 1987, P 6 INT C BIOM, P186
[10]   Recursive MUSIC: A framework for EEG and MEG source localization [J].
Mosher, JC ;
Leahy, RM .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 1998, 45 (11) :1342-1354