Improved Linear BMI Systems via Population Averaging

We investigate population averaging as a preprocessing stage for linear FIR BMIs. Population averaging is a biologically-inspired technique based on spatial constraints and neuronal correlation. We achieve a statistically significant improvement in accuracy while substantially (45%) reducing model parameters. Further analysis is performed to show that population averaging improves model accuracy by reducing variance in estimating the firing rate from spike bins. However, we find that population averaging provides a greater accuracy improvement than other groupings which also reduce firing rate variance. Our results suggest that appropriate spatial organization of neural signals enhances BMI performance

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

[2]  J. Chapin,et al.  Distinct temporal activity patterns in the rat M1 and red nucleus during skilled versus unskilled limb movement , 2004, Behavioural Brain Research.

[3]  S. Haykin,et al.  Adaptive Filter Theory , 1986 .

[4]  P. Ulinski.  Fundamentals of Computational Neuroscience , 2007 .

[5]  J.C. Sanchez,et al.  Learning the contributions of the motor, premotor, and posterior parietal cortices for hand trajectory reconstruction in a brain machine interface , 2003, First International IEEE EMBS Conference on Neural Engineering, 2003. Conference Proceedings..

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

[7]  V. Mountcastle.  The columnar organization of the neocortex. , 1997, Brain : a journal of neurology.

[8]  G. Buzsáki,et al.  Somadendritic backpropagation of action potentials in cortical pyramidal cells of the awake rat. , 1998, Journal of neurophysiology.

[9]  V. Kvasnicka,et al.  Neural and Adaptive Systems: Fundamentals Through Simulations , 2001, IEEE Trans. Neural Networks.

[10]  M. Laubach,et al.  Redundancy and Synergy of Neuronal Ensembles in Motor Cortex , 2005, The Journal of Neuroscience.

[11]  M. Nicolelis,et al.  Reconstructing the Engram: Simultaneous, Multisite, Many Single Neuron Recordings , 1997, Neuron.

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