Variable Selection for Motor Cortical Control of Directions

Author

Hu, Jing ; Si, Jennie ; Olson, Byron P. ; He, Jiping

Author_Institution

Dept. of Electr. Eng., Arizona State Univ., Tempe, AZ

fYear

2005

fDate

16-19 March 2005

Firstpage

78

Lastpage

81

Abstract

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

Keywords

bioelectric potentials; brain; handicapped aids; medical signal processing; neurophysiology; principal component analysis; signal classification; support vector machines; freely-moving rats; motor cortical direction control; neural signals; nonlinear support vector machine classifier; nonstereotypical brain machine interface system; principal component analysis; variable selection; Brain modeling; Electric variables control; Input variables; Light emitting diodes; Machine learning; Neurons; Principal component analysis; Rats; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Engineering, 2005. Conference Proceedings. 2nd International IEEE EMBS Conference on

Conference_Location

Arlington, VA

Print_ISBN

0-7803-8710-4

Type

conf

DOI

10.1109/CNE.2005.1419557

Filename

1419557