Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks

This article explores the use of scalar and multivariate autoregressive (AR) models to extract features from the human electroencephalogram (EEG) with which mental tasks can be discriminated. This is part of a larger project to investigate the feasibility of using EEG to allow paralyzed persons to c...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on biomedical engineering Vol. 45; no. 3; pp. 277 - 286
Main Authors: Anderson, C.W., Stolz, E.A., Shamsunder, S.
Format: Journal Article
Language:English
Published: New York, NY IEEE 01.03.1998
Institute of Electrical and Electronics Engineers
Subjects:
Backpropagation
Backpropagation algorithms
Biological and medical sciences
Brain modeling
Correlation methods
Eigenvalues and eigenfunctions
Electrodiagnosis. Electric activity recording
Electroencephalography
Feasibility Studies
Feature extraction
Feedforward neural networks
Humans
Investigative techniques, diagnostic techniques (general aspects)
Karhunen-Loeve transforms
Mathematical models
Mathematical transformations
Matrix algebra
Medical sciences
Mental Processes - physiology
Models, Statistical
Multivariate Analysis
Nervous system
Neural networks
Neural Networks (Computer)
Regression Analysis
Vectors
Wheelchairs
Human
Central nervous system
Electroencephalography
Autoregressive model
Neural network
Multivariate analysis
Mental activity
Electrodiagnosis
Biomedical data processing
Multichannel circuit
Classification
Signal analysis
Pattern extraction
Brain (vertebrata)
ISSN:0018-9294
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article explores the use of scalar and multivariate autoregressive (AR) models to extract features from the human electroencephalogram (EEG) with which mental tasks can be discriminated. This is part of a larger project to investigate the feasibility of using EEG to allow paralyzed persons to control a device such as a wheelchair. EEG signals from four subjects were recorded while they performed two mental tasks. Quarter-second windows of six-channel EEG were transformed into four different representations: scalar AR model coefficients, multivariate AR coefficients, eigenvalues of a correlation matrix, and the Karhunen-Loeve transform of the multivariate AR coefficients. Feature vectors defined by these representations were classified with a standard, feedforward neural network trained via the error backpropagation algorithm. The four representations produced similar results, with the multivariate AR coefficients performing slightly better and more consistently with an average classification accuracy of 91.4% on novel, untrained, EEG signals.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0018-9294
DOI:10.1109/10.661153