Bereitschaftspotential Modeling by DBNM and Its Application to BCI

In this study, movement-related potentials (MRPs) including Bereitschaftspotential (BP) is modeled by a dynamic Bayesian network model (DBNM). The containing the MRPs BP are divided into the early BP, NS' (negative slope) and MP (motor potential) intervals, each of which is represented by a Bayesian network model (BNM). Each BNM is constructed using the results by equivalent current dipole source localization (ECDL) after independent component analysis (ICA), for single-trial EEGs recorded during the hand movement. Nodes in the BNM correspond to the brain sites where dipoles are located. Connecting with the three BNMs yields a DBNM. This model is used to discriminate between the left- and right-hand movements in a framework of single-trial-electroencephalogram (EEG)-based BCI.

[1]  Eric Horvitz,et al.  MSBNx: A Component-Centric Toolkit for Modeling and Inference with Bayesian Networks , 2001 .

[2]  M. Hallett,et al.  What is the Bereitschaftspotential? , 2006, Clinical Neurophysiology.

[3]  David A. Bell,et al.  Learning Bayesian networks from data: An information-theory based approach , 2002, Artif. Intell..

[4]  G. Pfurtscheller,et al.  Brain-Computer Interfaces for Communication and Control. , 2011, Communications of the ACM.

[5]  K Kamijo,et al.  Integrated approach of an artificial neural network and numerical analysis to multiple equivalent current dipole source localization. , 2001, Frontiers of medical and biological engineering : the international journal of the Japan Society of Medical Electronics and Biological Engineering.