Learning Bayesian networks from data: an information-theory based approach
Artificial Intelligence
Hi-index | 0.00 |
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.