Decoding the non-stationary neuron spike trains by dual Monte Carlo point process estimation in motor Brain Machine Interfaces

Decoding algorithm in motor Brain Machine Interfaces translates the neural signals to movement parameters. They usually assume the connection between the neural firings and movements to be stationary, which is not true according to the recent studies that observe the time-varying neuron tuning property. This property results from the neural plasticity and motor learning etc., which leads to the degeneration of the decoding performance when the model is fixed. To track the non-stationary neuron tuning during decoding, we propose a dual model approach based on Monte Carlo point process filtering method that enables the estimation also on the dynamic tuning parameters. When applied on both simulated neural signal and in vivo BMI data, the proposed adaptive method performs better than the one with static tuning parameters, which raises a promising way to design a long-term-performing model for Brain Machine Interfaces decoder.

[1]  M. Hallett,et al.  Rapid plasticity of human cortical movement representation induced by practice. , 1998, Journal of neurophysiology.

[2]  Yiwen Wang,et al.  Decoding the nonstationary neural activity in motor cortex for brain machine interfaces , 2011, Int. J. Imaging Syst. Technol..

[3]  A P Georgopoulos,et al.  On the relations between the direction of two-dimensional arm movements and cell discharge in primate motor cortex , 1982, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[4]  Xi Chen,et al.  Tracking Time Variant Neuron Tuning Properties of Brain Machine Interfaces , 2013 .

[5]  E. Bizzi,et al.  Cortical correlates of learning in monkeys adapting to a new dynamical environment. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[6]  Kip A Ludwig,et al.  Naïve coadaptive cortical control , 2005, Journal of neural engineering.

[7]  Jerald D. Kralik,et al.  Real-time prediction of hand trajectory by ensembles of cortical neurons in primates , 2000, Nature.

[8]  José Carlos Príncipe,et al.  Real time input subset selection for linear time-variant MIMO systems , 2007, Optim. Methods Softw..

[9]  R E Kass,et al.  Recursive bayesian decoding of motor cortical signals by particle filtering. , 2004, Journal of neurophysiology.

[10]  David M. Santucci,et al.  Learning to Control a Brain–Machine Interface for Reaching and Grasping by Primates , 2003, PLoS biology.

[11]  E N Brown,et al.  An analysis of neural receptive field plasticity by point process adaptive filtering , 2001, Proceedings of the National Academy of Sciences of the United States of America.

[12]  José Carlos Príncipe,et al.  Mutual information analysis on non-stationary neuron importance for brain machine interfaces , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  Yiwen Wang,et al.  Instantaneous estimation of motor cortical neural encoding for online brain–machine interfaces , 2010, Journal of neural engineering.

[14]  Jose C. Principe,et al.  Tracking the non-stationary neuron tuning by dual Kalman filter for brain machine interfaces decoding , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[15]  J.P. Donoghue,et al.  Reconstruction of hand movement trajectories from a dynamic ensemble of spiking motor cortical neurons , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  Miguel A. L. Nicolelis,et al.  Real-time control of a robot arm using simultaneously recorded neurons in the motor cortex , 1999, Nature Neuroscience.

[17]  Wei Wu,et al.  Real-Time Decoding of Nonstationary Neural Activity in Motor Cortex , 2008, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[18]  Wei Wu,et al.  Neural Decoding of Cursor Motion Using a Kalman Filter , 2002, NIPS.

[19]  E. Bizzi,et al.  Neuronal Correlates of Motor Performance and Motor Learning in the Primary Motor Cortex of Monkeys Adapting to an External Force Field , 2001, Neuron.

[20]  L. Paninski,et al.  Spatiotemporal tuning of motor cortical neurons for hand position and velocity. , 2004, Journal of neurophysiology.

[21]  S I Helms Tillery,et al.  Training in Cortical Control of Neuroprosthetic Devices Improves Signal Extraction from Small Neuronal Ensembles , 2003, Reviews in the neurosciences.

[22]  Nicholas G. Hatsopoulos,et al.  Brain-machine interface: Instant neural control of a movement signal , 2002, Nature.

[23]  José Carlos Príncipe,et al.  Sequential Monte Carlo Point-Process Estimation of Kinematics from Neural Spiking Activity for Brain-Machine Interfaces , 2009, Neural Computation.

[24]  Miguel A. L. Nicolelis,et al.  Adaptive Decoding for Brain-Machine Interfaces Through Bayesian Parameter Updates , 2011, Neural Computation.

[25]  Andrew S. Whitford,et al.  Cortical control of a prosthetic arm for self-feeding , 2008, Nature.