HMM and IOHMM modeling of EEG rhythms for asynchronous BCI systems

We compare the use of two Markovian models, HMMs and IOHMMs, to discriminate between three mental tasks for brain computer interface systems using an asynchronous protocol. We show that IOHMMs outperform HMMs but that, probably due to the lack of any prior information on the state dynamics, no practical advantage in the use of these models over their static counterparts is obtained.

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

[2]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[3]  Jeff A. Bilmes,et al.  A gentle tutorial of the em algorithm and its application to parameter estimation for Gaussian mixture and hidden Markov models , 1998 .

[4]  W. J. Nowack.  Neocortical Dynamics and Human EEG Rhythms , 1995, Neurology.

[5]  José del R. Millán,et al.  Brain-Computer Interfaces , 2020, Handbook of Clinical Neurology.

[6]  Yoshua Bengio,et al.  Markovian Models for Sequential Data , 2004 .

[7]  L. Baum,et al.  An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process , 1972 .

[8]  E Donchin,et al.  Brain-computer interface technology: a review of the first international meeting. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[9]  William Z Rymer,et al.  Brain-computer interface technology: a review of the Second International Meeting. , 2003, IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[10]  Yoshua Bengio,et al.  Input-output HMMs for sequence processing , 1996, IEEE Trans. Neural Networks.

[11]  G. McLachlan,et al.  The EM algorithm and extensions , 1996 .

[12]  Christa Neuper,et al.  Hidden Markov models for online classification of single trial EEG data , 2001, Pattern Recognit. Lett..