Abstract
A constrained point-process filtering mechanism for prediction of electromyogram (EMG) signals from multichannel neural spike recordings is proposed here. Filters from the Kalman family are inherently suboptimal in dealing with non-Gaussian observations, or a state evolution that deviates from the Gaussianity assumption. To address these limitations, we modeled the non-Gaussian neural spike train observations by using a generalized linear model that encapsulates covariates of neural activity, including the neurons' own spiking history, concurrent ensemble activity, and extrinsic covariates (EMG signals). In order to predict the envelopes of EMGs, we reformulated the Kalman filter in an optimization framework and utilized a nonnegativity constraint. This structure characterizes the nonlinear correspondence between neural activity and EMG signals reasonably. The EMGs were recorded from 12 forearm and hand muscles of a behaving monkey during a grip-force task. In the case of limited training data, the constrained point-process filter improved the prediction accuracy when compared to a conventional Wiener cascade filter (a linear causal filter followed by a static nonlinearity) for different bin sizes and delays between input spikes and EMG output. For longer training datasets, results of the proposed filter and that of the Wiener cascade filter were comparable.
Original language | English (US) |
---|---|
Article number | 2159115 |
Pages (from-to) | 1829-1838 |
Number of pages | 10 |
Journal | IEEE Transactions on Biomedical Engineering |
Volume | 59 |
Issue number | 7 |
DOIs | |
State | Published - 2012 |
Funding
Manuscript received February 2, 2011; revised April 20, 2011; accepted May 18, 2011. Date of publication June 9, 2011; date of current version June 20, 2012. The work of K. Nazarpour and R. C. Miall was supported by The Wellcome Trust, U.K. The work of C. Ethier, J. M. Rebesco, and L. E. Miller was supported by the National Institute of Neurological Disorders and Stroke (NINDS) under Grant NS053603. The work of L. E. Miller was supported by the Searle Foundation through the Chicago Community Trust. The work of C. Ethier was supported by a Postdoctoral Fellowship from the Fonds de la Recherche en Sante du Quebec. The work of J. M. Rebesco was supported by the NINDS Fellowship F31NS062552. The work of L. Paninski was supported by the National Science Foundation CAREER award. Asterisk indicates corresponding author.
Keywords
- Brain-machine interface (BMI)
- Kalman filter
- electromyogram (EMG) signal
- generalized linear model (GLM)
- optimization
ASJC Scopus subject areas
- Biomedical Engineering