Bayesian multi-subject common spatial patterns with Indian Buffet process priors

Common spatial patterns (CSP) or its probabilistic counterpart, PCSP, is a popular discriminative feature extraction method for electroencephalography (EEG) classification. Models in CSP or PCSP are trained on a subject-by-subject basis so that inter-subject information is not used. In the case of multi-subject EEG classification where brain waves recorded from multiple subjects who undergo the same mental task are available, it is desirable to capture inter-subject relatedness in learning a model. In this paper we present a nonparametric Bayesian model for a multi-subject extension of CSP where subject relatedness is captured by assuming that spatial patterns across subjects share a latent subspace. Spatial patterns and the shared latent subspace are jointly learned by variational inference. We use an infinite latent feature model to automatically infer the dimension of the shared latent subspace, placing Indian Buffet process (IBP) priors on our model. Numerical experiments on BCI competition IV 2a dataset demonstrate the high performance of our method, compared to PCSP and existing Bayesian multi-task CSP models.

[1]  Seungjin Choi,et al.  Composite Common Spatial Pattern for Subject-to-Subject Transfer , 2009, IEEE Signal Processing Letters.

[2]  Thomas L. Griffiths,et al.  Infinite latent feature models and the Indian buffet process , 2005, NIPS.

[3]  Yee Whye Teh,et al.  Stick-breaking Construction for the Indian Buffet Process , 2007, AISTATS.

[4]  Moritz Grosse-Wentrup,et al.  Multisubject Learning for Common Spatial Patterns in Motor-Imagery BCI , 2011, Comput. Intell. Neurosci..

[5]  Cuntai Guan,et al.  Learning from other subjects helps reducing Brain-Computer Interface calibration time , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Seungjin Choi,et al.  Bayesian Multi-task Learning for Common Spatial Patterns , 2011, 2011 International Workshop on Pattern Recognition in NeuroImaging.

[7]  Z J Koles,et al.  The quantitative extraction and topographic mapping of the abnormal components in the clinical EEG. , 1991, Electroencephalography and clinical neurophysiology.

[8]  Liqing Zhang,et al.  Noninvasive BCIs: Multiway Signal-Processing Array Decompositions , 2008, Computer.

[9]  Tom Heskes,et al.  Empirical Bayes for Learning to Learn , 2000, ICML.

[10]  Cuntai Guan,et al.  Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms , 2011, IEEE Transactions on Biomedical Engineering.

[11]  Yiming Yang,et al.  Flexible latent variable models for multi-task learning , 2008, Machine Learning.

[12]  Seungjin Choi,et al.  Bayesian common spatial patterns with Dirichlet process priors for multi-subject EEG classification , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[13]  G. Pfurtscheller,et al.  Designing optimal spatial filters for single-trial EEG classification in a movement task , 1999, Clinical Neurophysiology.

[14]  Hal Daumé,et al.  Infinite Predictor Subspace Models for Multitask Learning , 2010, AISTATS.

[15]  Emery N. Brown,et al.  A probabilistic framework for learning robust common spatial patterns , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  Yee Whye Teh,et al.  Variational Inference for the Indian Buffet Process , 2009, AISTATS.