Feature detection in motor cortical spikes by principal component analysis

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

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Principal component analysis was performed on recorded neural spike trains in rats' motor cortices when rats were involved in real-time control tasks using brain-machine interfaces. The rat with implanted microelectrode array was placed in a conditioning chamber, but freely moving, to decide which one of the two paddles should be activated to shift the cue light to the center. It is found that the principal component feature vectors revealed the importance of individual neurons and windows of time in the decision making process. In addition, one of the first principal components has much higher discriminative capability than others, although it represents only a small percentage of the total variance in the data. Using one to six principal components with a Bayes classifier achieved classification accuracy comparable to that obtained by a more sophisticated high performance support vector classifier.

Original languageEnglish (US)
Pages (from-to)256-262
Number of pages7
JournalIEEE Transactions on Neural Systems and Rehabilitation Engineering
Volume13
Issue number3
DOIs
StatePublished - Sep 2005

Fingerprint

Principal Component Analysis
Principal component analysis
Rats
Classifiers
Brain-Computer Interfaces
Microelectrodes
Motor Cortex
Real time control
Neurons
Cues
Brain
Decision Making
Decision making
Light

Keywords

  • Brain-machine interface (BMI)
  • Cortical control
  • Feature detection
  • Motor systems
  • Principal component analysis (PCA)
  • Spike trains
  • Support vector machines (SVMs)

ASJC Scopus subject areas

  • Rehabilitation
  • Biophysics
  • Bioengineering
  • Health Professions(all)

Cite this

Feature detection in motor cortical spikes by principal component analysis. / Hu, Jing; Si, Jennie; Olson, Byron P.; He, Jiping.

In: IEEE Transactions on Neural Systems and Rehabilitation Engineering, Vol. 13, No. 3, 09.2005, p. 256-262.

Research output: Contribution to journalArticle

@article{f97d40cd105d42c9a9a7e8e49c0c43ca,
title = "Feature detection in motor cortical spikes by principal component analysis",
abstract = "Principal component analysis was performed on recorded neural spike trains in rats' motor cortices when rats were involved in real-time control tasks using brain-machine interfaces. The rat with implanted microelectrode array was placed in a conditioning chamber, but freely moving, to decide which one of the two paddles should be activated to shift the cue light to the center. It is found that the principal component feature vectors revealed the importance of individual neurons and windows of time in the decision making process. In addition, one of the first principal components has much higher discriminative capability than others, although it represents only a small percentage of the total variance in the data. Using one to six principal components with a Bayes classifier achieved classification accuracy comparable to that obtained by a more sophisticated high performance support vector classifier.",
keywords = "Brain-machine interface (BMI), Cortical control, Feature detection, Motor systems, Principal component analysis (PCA), Spike trains, Support vector machines (SVMs)",
author = "Jing Hu and Jennie Si and Olson, {Byron P.} and Jiping He",
year = "2005",
month = "9",
doi = "10.1109/TNSRE.2005.847389",
language = "English (US)",
volume = "13",
pages = "256--262",
journal = "IEEE Transactions on Neural Systems and Rehabilitation Engineering",
issn = "1534-4320",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Feature detection in motor cortical spikes by principal component analysis

AU - Hu, Jing

AU - Si, Jennie

AU - Olson, Byron P.

AU - He, Jiping

PY - 2005/9

Y1 - 2005/9

N2 - Principal component analysis was performed on recorded neural spike trains in rats' motor cortices when rats were involved in real-time control tasks using brain-machine interfaces. The rat with implanted microelectrode array was placed in a conditioning chamber, but freely moving, to decide which one of the two paddles should be activated to shift the cue light to the center. It is found that the principal component feature vectors revealed the importance of individual neurons and windows of time in the decision making process. In addition, one of the first principal components has much higher discriminative capability than others, although it represents only a small percentage of the total variance in the data. Using one to six principal components with a Bayes classifier achieved classification accuracy comparable to that obtained by a more sophisticated high performance support vector classifier.

AB - Principal component analysis was performed on recorded neural spike trains in rats' motor cortices when rats were involved in real-time control tasks using brain-machine interfaces. The rat with implanted microelectrode array was placed in a conditioning chamber, but freely moving, to decide which one of the two paddles should be activated to shift the cue light to the center. It is found that the principal component feature vectors revealed the importance of individual neurons and windows of time in the decision making process. In addition, one of the first principal components has much higher discriminative capability than others, although it represents only a small percentage of the total variance in the data. Using one to six principal components with a Bayes classifier achieved classification accuracy comparable to that obtained by a more sophisticated high performance support vector classifier.

KW - Brain-machine interface (BMI)

KW - Cortical control

KW - Feature detection

KW - Motor systems

KW - Principal component analysis (PCA)

KW - Spike trains

KW - Support vector machines (SVMs)

UR - http://www.scopus.com/inward/record.url?scp=26244464487&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=26244464487&partnerID=8YFLogxK

U2 - 10.1109/TNSRE.2005.847389

DO - 10.1109/TNSRE.2005.847389

M3 - Article

VL - 13

SP - 256

EP - 262

JO - IEEE Transactions on Neural Systems and Rehabilitation Engineering

JF - IEEE Transactions on Neural Systems and Rehabilitation Engineering

SN - 1534-4320

IS - 3

ER -