Perceiving Systems, Computer Vision

Modeling and decoding motor cortical activity using a switching Kalman filter

2004

Article

ps


We present a switching Kalman filter model for the real-time inference of hand kinematics from a population of motor cortical neurons. Firing rates are modeled as a Gaussian mixture where the mean of each Gaussian component is a linear function of hand kinematics. A “hidden state” models the probability of each mixture component and evolves over time in a Markov chain. The model generalizes previous encoding and decoding methods, addresses the non-Gaussian nature of firing rates, and can cope with crudely sorted neural data common in on-line prosthetic applications.

Author(s): Wu, W. and Black, M. J. and Mumford, D. and Gao, Y. and Bienenstock, E. and Donoghue, J. P.
Journal: IEEE Trans. Biomedical Engineering
Volume: 51
Number (issue): 6
Pages: 933--942
Year: 2004
Month: June

Department(s): Perceiving Systems
Bibtex Type: Article (article)
Paper Type: Journal

Links: pdf
pdf from publisher

BibTex

@article{Wu:TransBME:04,
  title = {Modeling and decoding motor cortical activity using a switching {Kalman} filter},
  author = {Wu, W. and Black, M. J. and Mumford, D. and Gao, Y. and Bienenstock, E. and Donoghue, J. P.},
  journal = {IEEE Trans. Biomedical Engineering},
  volume = {51},
  number = {6},
  pages = {933--942},
  month = jun,
  year = {2004},
  doi = {},
  month_numeric = {6}
}