(8) Bereitschaftspotential modeling by DBNN and its application to BCI
Shino Takata, Toshimasa Yamazaki, Maiko Sakamoto,
Human Interface, Part I, HCII 201, Springer-Verlag, M.J. Smith, G. ，pp.636-640，2011-7
In this study, movement-related potentials (MRPs) including Bereitshaftspotential (BP) are modeled by a dynamic Bayesian network model (DBNM). The contains of MRPs 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 by use of the results by the equivalent current dipole source localization (ECDL) after the independent component analysis (ICA), for single-trial electroencephalograms (EEGs) recorded during a 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-EGG-based BCI.
>>
NEXT