General Strategy for Hierarchical Decomposition of Multivariate Time Series: Implications for Temporal Lobe Seizures

AbstractWe describe a novel method for the analysis of multivariate time series that exploits the dynamic relationships among the multiple signals. The approach resolves the multivariate time series into hierarchically dependent underlying sources, each driven by noise input and influencing subordinate sources in the hierarchy. Implementation of this hierarchical decomposition (HD) combines principal components analysis (PCA), autoregressive modeling, and a novel search strategy among orthogonal rotations. For model systems conforming to this hierarchical structure, HD accurately extracts the underlying sources, whereas PCA or independent components analysis does not. The interdependencies of cortical, subcortical, and brainstem networks suggest application of HD to multivariate measures of brain activity. We show first that HD indeed resolves temporal lobe ictal electrocorticographic data into nearly hierarchical form. A previous analysis of these data identified characteristic nonlinearities in the PCA-derived temporal components that resembled those seen in absence (petit mal) seizure electroencephalographic traces. However, the components containing these characteristic nonlinearities accounted for only a small fraction of the power. Analysis of these data with HD reveals furthermore that components containing characteristic nonlinearities, though small, can be at the origin of the hierarchy. This finding supports the link between temporal lobe and absence epilepsy. © 2001 Biomedical Engineering Society. PAC01: 8719Nn, 0545Tp, 0250-r, 0230Lt

[1]  Hualou Liang,et al.  Short-window spectral analysis of cortical event-related potentials by adaptive multivariate autoregressive modeling: data preprocessing, model validation, and variability assessment , 2000, Biological Cybernetics.

[2]  L. Mirsky,et al.  Introduction to Linear Algebra , 1965, The Mathematical Gazette.

[3]  N. D. Schiff,et al.  Common dynamics in temporal lobe seizures and absence seizures , 1999, Neuroscience.

[4]  P. Mitra,et al.  Analysis of dynamic brain imaging data. , 1998, Biophysical journal.

[5]  Katarzyna J. Blinowska,et al.  A new method of the description of the information flow in the brain structures , 1991, Biological Cybernetics.

[6]  K. Imakawa,et al.  Determination of genes involved in the process of implantation: application of GeneChip to scan 6500 genes. , 2000, Biochemical and biophysical research communications.

[7]  C. Granger.  Investigating causal relations by econometric models and cross-spectral methods , 1969 .

[8]  William H. Press,et al.  The Art of Scientific Computing Second Edition , 1998 .

[9]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[10]  F. A. Seiler,et al.  Numerical Recipes in C: The Art of Scientific Computing , 1989 .

[11]  Steven Kay,et al.  Modern Spectral Estimation: Theory and Application , 1988 .

[12]  W Gersch,et al.  Parametric time series models for multivariate EEG analysis. , 1977, Computers and biomedical research, an international journal.

[13]  H. Akaike.  A new look at the statistical model identification , 1974 .

[14]  Jonathan D. Victor,et al.  Characteristic nonlinearities of the 3/s ictal electroencephalogram identified by nonlinear autoregressive analysis , 1995, Biological Cybernetics.

[15]  F. L. D. Silva,et al.  Basic mechanisms of cerebral rhythmic activities , 1990 .

[16]  Terrence J. Sejnowski,et al.  Blind separation and blind deconvolution: an information-theoretic approach , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[17]  Kunkel Jm,et al.  Spontaneous subclavain vein thrombosis: a successful combined approach of local thrombolytic therapy followed by first rib resection. , 1989 .

[18]  Jonathan D. Victor,et al.  A relation between the Akaike criterion and reliability of parameter estimates, with application to nonlinear autoregressive modelling of ictal EEG , 2006, Annals of Biomedical Engineering.

[19]  G. Yule.  On a Method of Investigating Periodicities in Disturbed Series, with Special Reference to Wolfer's Sunspot Numbers , 1927 .

[20]  William W. S. Wei,et al.  Time series analysis - univariate and multivariate methods , 1989 .

[21]  T. Bollerslev.  Generalized autoregressive conditional heteroskedasticity with applications in finance , 1986 .

[22]  M M Mesulam,et al.  Report of IFCN Committee on Basic Mechanisms. Basic mechanisms of cerebral rhythmic activities. , 1990, Electroencephalography and clinical neurophysiology.

[23]  Jonathan D. Victor,et al.  Nonlinear autoregressive analysis of the 3/s ictal electroencephalogram: implications for underlying dynamics , 2004, Biological Cybernetics.