A parallel point-process filter for estimation of goal-directed movements from neural signals

• Main Authors: Modir Shanechi, Maryam (Contributor), Wornell, Gregory W. (Contributor), Williams, Ziv (Contributor), Brown, Emery N. (Contributor)
• Other Authors: Harvard University- (Contributor), Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers, 2012-05-07T20:36:09Z.
• Subjects: Article
• Online Access: Get fulltext

Brain machine interfaces work by mapping the relevant neural activity to the intended movement known as 'decoding'. Here, we develop a recursive Bayesian decoder for goal-directed movements from neural observations, which exploits the optimal feedback control model of the sensorimotor system to build better prior state-space models. These controlled state models depend on the movement duration that is not known a priori. We thus consider a discretization of the task duration and develop a decoder consisting of a bank of parallel point-process filters, each combining the neural observation with the controlled state model of a discretization point. The final reconstruction is made by optimally combining these filter estimates. Using very coarse discretization and hence only a few parallel branches, our decoder reduces the root mean square (RMS) error in trajectory reconstruction in reaches made by a rhesus monkey by approximately 40%.
National Institutes of Health (U.S.) (Grant No. DP1- 0D003646-01)
National Institutes of Health (U.S.) (Grant R01-EB006385)
Microsoft Research