Linear dynamic models for classification of single-trial EEG

This paper investigates the use of linear dynamic models (LDMs) to improve classification of single-trial EEG signals. Existing dynamic classification of EEG uses discrete-state hidden Markov models (HMMs) based on piecewise-stationary assumption, which is inadequate for modeling the highly non-stationary dynamics underlying EEG. The continuous hidden states of LDMs could better describe this continuously changing characteristic of EEG, and thus improve the classification performance. We consider two examples of LDM: a simple local level model (LLM) and a time-varying autoregressive (TVAR) state-space model. AR parameters and band power are used as features. Parameter estimation of the LDMs is performed by using expectation-maximization (EM) algorithm. We also investigate different covariance modeling of Gaussian noises in LDMs for EEG classification. The experimental results on two-class motor-imagery classification show that both types of LDMs outperform the HMM baseline, with the best relative accuracy improvement of 14.8% by LLM with full covariance for Gaussian noises. It may due to that LDMs offer more flexibility in fitting the underlying dynamics of EEG.

[1]  Antti-Veikko I. Rosti,et al.  Linear Gaussian Models for Speech Recognition , 2004 .

[2]  Mark J. F. Gales,et al.  Generalised linear Gaussian models , 2001 .

[3]  Li Deng,et al.  A mixed-level switching dynamic system for continuous speech recognition , 2004, Comput. Speech Lang..

[4]  Gert Pfurtscheller,et al.  Characterization of four-class motor imagery EEG data for the BCI-competition 2005 , 2005, Journal of neural engineering.

[5]  Klaus-Robert Müller,et al.  The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials , 2004, IEEE Transactions on Biomedical Engineering.

[6]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[7]  Geoffrey E. Hinton,et al.  Parameter estimation for linear dynamical systems , 1996 .

[8]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[9]  Simon King,et al.  Speech Recognition Using Linear Dynamic Models , 2007, IEEE Transactions on Audio, Speech, and Language Processing.

[10]  Vladimir Pavlovic,et al.  Impact of dynamic model learning on classification of human motion , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[11]  M Congedo,et al.  A review of classification algorithms for EEG-based brain–computer interfaces , 2007, Journal of neural engineering.

[12]  Li Deng,et al.  Target-directed mixture dynamic models for spontaneous speech recognition , 2004, IEEE Transactions on Speech and Audio Processing.

[13]  Zoubin Ghahramani,et al.  A Unifying Review of Linear Gaussian Models , 1999, Neural Computation.

[14]  Vladimir Pavlovic,et al.  Time-series classification using mixed-state dynamic Bayesian networks , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[15]  Joe Frankel,et al.  Linear dynamic models for automatic speech recognition , 2004 .

[16]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[17]  R. Shumway,et al.  AN APPROACH TO TIME SERIES SMOOTHING AND FORECASTING USING THE EM ALGORITHM , 1982 .

[18]  Seungjin Choi,et al.  PCA-based linear dynamical systems for multichannel EEG classification , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[19]  S. Balqis Samdin,et al.  An expectation-maximization algorithm based Kalman smoother approach for single-trial estimation of event-related potentials , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.