nips nips2004 nips2004-56 nips2004-56-reference knowledge-graph by maker-knowledge-mining

56 nips-2004-Dynamic Bayesian Networks for Brain-Computer Interfaces


Source: pdf

Author: Pradeep Shenoy, Rajesh P. Rao

Abstract: We describe an approach to building brain-computer interfaces (BCI) based on graphical models for probabilistic inference and learning. We show how a dynamic Bayesian network (DBN) can be used to infer probability distributions over brain- and body-states during planning and execution of actions. The DBN is learned directly from observed data and allows measured signals such as EEG and EMG to be interpreted in terms of internal states such as intent to move, preparatory activity, and movement execution. Unlike traditional classification-based approaches to BCI, the proposed approach (1) allows continuous tracking and prediction of internal states over time, and (2) generates control signals based on an entire probability distribution over states rather than binary yes/no decisions. We present preliminary results of brain- and body-state estimation using simultaneous EEG and EMG signals recorded during a self-paced left/right hand movement task. 1


reference text

[1] B. Blankertz, G. Curio, and K.R. Mueller. Classifying single trial EEG: Towards brain computer interfacing. In Advances in Neural Information Processing Systems 12, 2001.

[2] G. Dornhege, B. Blankertz, G. Curio, and K.-R. Mueller. Combining features for BCI. In Advances in Neural Information Processing Systems 15, 2003.

[3] J. D. Bayliss and D. H. Ballard. Recognizing evoked potentials in a virtual environment. In Advances in Neural Information Processing Systems 12, 2000.

[4] P. Meinicke, M. Kaper, F. Hoppe, M. Heumann, and H. Ritter. Improving transfer rates in brain computer interfacing: a case study. In Advances in Neural Information Processing Systems 15, 2003.

[5] J.R. Wolpaw, D.J. McFarland, and T.M. Vaughan. Brain-computer interfaces for communication and control. IEEE Trans Rehab Engg, pages 222–226, 2000. 6 4 2 0 0 500 1000 1500 2000 2500 3000 3500 4000 Supervisory Signal 20 0 −20 −40 −60 −80 0 500 1000 1500 2000 2500 3000 3500 Left action Log(P(state)/P(rest)) zero pre movt post 4000 20 0 −20 −40 −60 −80 0 500 1000 1500 2000 2500 3000 3500 zero pre movt post 4000 Right action Log(P(state)/P(rest)) Figure 6: Probabilistic Estimation of Brain State: The figure shows the supervisory signal, along with a probabilistic measure of the current state for left and right actions respectively. The measure shown is the log ratio of the instantaneous MAP estimate for the relevant state and the estimate for the rest state.

[6] J. R. Wolpaw et al. Brain-computer interface technology: a review of the first international meeting. IEEE Trans Rehab Engg, 8:164–173, 2000.

[7] R. E. Neapolitan. Learning Bayesian Networks. Prentice Hall, NJ, 2004.

[8] M. Jahanshahi and M. Hallet. The Bereitschaftspotential: movement related cortical potentials. Kluwer Academic, New York, 2002.

[9] J. Bilmes and G. Zweig. The graphical models toolkit: An open source software system for speech and time-series processing. In IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing, Orlando FL, 2002.

[10] N. Birbaumer, N. Ghanayim, T. Hinterberger, I. Iverson, B. Kotchubey, A. Kiibler, J. Perelmouter, E. Taub, and H. Flor. A spelling device for the paralyzed. In Nature, 398: 297-298, 1999.