Variable Selection for Motor Cortical Control of Directions

In our previous work, a non-stereotypical brain machine interface system was implemented with freely-moving rats, and a nonlinear support vector machine (SVM) classifier was used to map neural signals in the rats' motor cortices onto a set of discrete classes of directions (left and right). In this paper, we provide a comprehensive analysis about the selection of neurons and temporal parameters, which is critical to the success of the system. We also show that pre-processing by principal component analysis (PCA) can reduce dimensions and improve accuracy

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

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

[3]  Olivier Chapelle,et al.  Model Selection for Support Vector Machines , 1999, NIPS.

[4]  José Carlos Príncipe,et al.  Ascertaining the importance of neurons to develop better brain-machine interfaces , 2004, IEEE Transactions on Biomedical Engineering.

[5]  J. Si,et al.  Principle component feature detector for motor cortical control , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[6]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[7]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

[8]  J. Si,et al.  Closed-loop cortical control of direction using support vector machines , 2005, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[9]  M. Nicolelis,et al.  Optimizing a Linear Algorithm for Real-Time Robotic Control using Chronic Cortical Ensemble Recordings in Monkeys , 2004, Journal of Cognitive Neuroscience.