Variable selection for motor cortical control of directions

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish (US)
Title of host publication2nd International IEEE EMBS Conference on Neural Engineering
Pages78-81
Number of pages4
Volume2005
DOIs
StatePublished - 2005
Event2nd International IEEE EMBS Conference on Neural Engineering, 2005 - Arlington, VA, United States
Duration: Mar 16 2005Mar 19 2005

Other

Other2nd International IEEE EMBS Conference on Neural Engineering, 2005
CountryUnited States
CityArlington, VA
Period3/16/053/19/05

Fingerprint

Rats
Principal component analysis
Neurons
Support vector machines
Brain
Classifiers
Processing

Keywords

  • Brain-machine interface
  • Motor cortical control
  • PCA
  • SVM
  • Variable selection

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hu, J., Si, J., Olson, B. P., & He, J. (2005). Variable selection for motor cortical control of directions. In 2nd International IEEE EMBS Conference on Neural Engineering (Vol. 2005, pp. 78-81). [1419557] https://doi.org/10.1109/CNE.2005.1419557

Variable selection for motor cortical control of directions. / Hu, Jing; Si, Jennie; Olson, Byron P.; He, Jiping.

2nd International IEEE EMBS Conference on Neural Engineering. Vol. 2005 2005. p. 78-81 1419557.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hu, J, Si, J, Olson, BP & He, J 2005, Variable selection for motor cortical control of directions. in 2nd International IEEE EMBS Conference on Neural Engineering. vol. 2005, 1419557, pp. 78-81, 2nd International IEEE EMBS Conference on Neural Engineering, 2005, Arlington, VA, United States, 3/16/05. https://doi.org/10.1109/CNE.2005.1419557
Hu J, Si J, Olson BP, He J. Variable selection for motor cortical control of directions. In 2nd International IEEE EMBS Conference on Neural Engineering. Vol. 2005. 2005. p. 78-81. 1419557 https://doi.org/10.1109/CNE.2005.1419557
Hu, Jing ; Si, Jennie ; Olson, Byron P. ; He, Jiping. / Variable selection for motor cortical control of directions. 2nd International IEEE EMBS Conference on Neural Engineering. Vol. 2005 2005. pp. 78-81
@inproceedings{fa752f54cd0f45a29dc57b418ca3d82d,
title = "Variable selection for motor cortical control of directions",
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 = "Brain-machine interface, Motor cortical control, PCA, SVM, Variable selection",
author = "Jing Hu and Jennie Si and Olson, {Byron P.} and Jiping He",
year = "2005",
doi = "10.1109/CNE.2005.1419557",
language = "English (US)",
volume = "2005",
pages = "78--81",
booktitle = "2nd International IEEE EMBS Conference on Neural Engineering",

}

TY - GEN

T1 - Variable selection for motor cortical control of directions

AU - Hu, Jing

AU - Si, Jennie

AU - Olson, Byron P.

AU - He, Jiping

PY - 2005

Y1 - 2005

N2 - 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.

AB - 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.

KW - Brain-machine interface

KW - Motor cortical control

KW - PCA

KW - SVM

KW - Variable selection

UR - http://www.scopus.com/inward/record.url?scp=33744475348&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33744475348&partnerID=8YFLogxK

U2 - 10.1109/CNE.2005.1419557

DO - 10.1109/CNE.2005.1419557

M3 - Conference contribution

AN - SCOPUS:33744475348

VL - 2005

SP - 78

EP - 81

BT - 2nd International IEEE EMBS Conference on Neural Engineering

ER -