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

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 goaldirected 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%.

• Type: Conference
• Year: 2010
• Where: ICASSP
• Authors: Maryam Modir Shanechi, Gregory W. Wornell, Ziv Williams, Emery N. Brown
• Keywords: Controlled State Model, ICASSP 2010, Neural Observation, Recursive Bayesian Decoder, Signal Processing