EEG-based classification for elbow versus shoulder torque intentions involving stroke subjects

Jie Zhou*, Jun Yao, Jie Deng, Julius P A Dewald

*Corresponding author for this work

Research output: Contribution to journalArticle

32 Citations (Scopus)

Abstract

The ultimate aim for classifying elbow versus shoulder torque intentions is to develop robust brain-computer interface (BCI) devices for patients who suffer from movement disorders following brain injury such as stroke. In this paper, we investigate the advanced classification approach classifier-enhanced time-frequency synthesized spatial pattern algorithm (classifier-enhanced TFSP) in classifying a subject's intent of generating an isometric shoulder abduction (SABD) or elbow flexion (EF) torque using signals obtained from 163 scalp electroencephalographic (EEG) electrodes. Two classifiers, the support vector classifier (SVC) and the classification and regression tree (CART), are integrated in the TFSP algorithm that decomposes the signal into a weighted time, frequency and spatial feature space. The resulting high-performing methods (SVC-TFSP and CART-TFSP) are then applied to experimental data collected in four healthy subjects and two stroke subjects. Results are compared with the original TFSP, and significantly higher reliability in both healthy subjects (92% averaged over four healthy subjects) and stroke subjects (75% averaged over two subjects) are achieved. The accuracies of classifier-enhanced TFSP methods are further improved after a rejection scheme is applied (∼100% in healthy subjects and >80% in stroke subjects). The results are among the highest reliability reported in literature for tasks with spatial representations on the motor cortex as close as shoulder and elbow. The paper also discusses the impact of applying rejection strategy in detail and reports the existence of an optimal rejection rate on a stroke subject. The results indicate that the proposed algorithms are promising for future use of rehabilitative BCI applications in neurologically impaired patients.

Original languageEnglish (US)
Pages (from-to)443-452
Number of pages10
JournalComputers in Biology and Medicine
Volume39
Issue number5
DOIs
StatePublished - May 1 2009

Fingerprint

Torque
Elbow
Classifiers
Stroke
Healthy Volunteers
Brain-Computer Interfaces
Brain computer interface
Movement Disorders
Motor Cortex
Scalp
Brain Injuries
Brain
Electrodes
Equipment and Supplies
Rejection (Psychology)

Keywords

  • Brain-computer interface
  • Classification
  • Classification and regression tree
  • Elbow flexion
  • Electroencephalograph (EEG)
  • Shoulder abduction
  • Stroke
  • Support-vector machine
  • Time-frequency synthesized spatial pattern algorithm

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

@article{d9ad187465b64baea94818a8e0c722d7,
title = "EEG-based classification for elbow versus shoulder torque intentions involving stroke subjects",
abstract = "The ultimate aim for classifying elbow versus shoulder torque intentions is to develop robust brain-computer interface (BCI) devices for patients who suffer from movement disorders following brain injury such as stroke. In this paper, we investigate the advanced classification approach classifier-enhanced time-frequency synthesized spatial pattern algorithm (classifier-enhanced TFSP) in classifying a subject's intent of generating an isometric shoulder abduction (SABD) or elbow flexion (EF) torque using signals obtained from 163 scalp electroencephalographic (EEG) electrodes. Two classifiers, the support vector classifier (SVC) and the classification and regression tree (CART), are integrated in the TFSP algorithm that decomposes the signal into a weighted time, frequency and spatial feature space. The resulting high-performing methods (SVC-TFSP and CART-TFSP) are then applied to experimental data collected in four healthy subjects and two stroke subjects. Results are compared with the original TFSP, and significantly higher reliability in both healthy subjects (92{\%} averaged over four healthy subjects) and stroke subjects (75{\%} averaged over two subjects) are achieved. The accuracies of classifier-enhanced TFSP methods are further improved after a rejection scheme is applied (∼100{\%} in healthy subjects and >80{\%} in stroke subjects). The results are among the highest reliability reported in literature for tasks with spatial representations on the motor cortex as close as shoulder and elbow. The paper also discusses the impact of applying rejection strategy in detail and reports the existence of an optimal rejection rate on a stroke subject. The results indicate that the proposed algorithms are promising for future use of rehabilitative BCI applications in neurologically impaired patients.",
keywords = "Brain-computer interface, Classification, Classification and regression tree, Elbow flexion, Electroencephalograph (EEG), Shoulder abduction, Stroke, Support-vector machine, Time-frequency synthesized spatial pattern algorithm",
author = "Jie Zhou and Jun Yao and Jie Deng and Dewald, {Julius P A}",
year = "2009",
month = "5",
day = "1",
doi = "10.1016/j.compbiomed.2009.02.004",
language = "English (US)",
volume = "39",
pages = "443--452",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",
number = "5",

}

EEG-based classification for elbow versus shoulder torque intentions involving stroke subjects. / Zhou, Jie; Yao, Jun; Deng, Jie; Dewald, Julius P A.

In: Computers in Biology and Medicine, Vol. 39, No. 5, 01.05.2009, p. 443-452.

Research output: Contribution to journalArticle

TY - JOUR

T1 - EEG-based classification for elbow versus shoulder torque intentions involving stroke subjects

AU - Zhou, Jie

AU - Yao, Jun

AU - Deng, Jie

AU - Dewald, Julius P A

PY - 2009/5/1

Y1 - 2009/5/1

N2 - The ultimate aim for classifying elbow versus shoulder torque intentions is to develop robust brain-computer interface (BCI) devices for patients who suffer from movement disorders following brain injury such as stroke. In this paper, we investigate the advanced classification approach classifier-enhanced time-frequency synthesized spatial pattern algorithm (classifier-enhanced TFSP) in classifying a subject's intent of generating an isometric shoulder abduction (SABD) or elbow flexion (EF) torque using signals obtained from 163 scalp electroencephalographic (EEG) electrodes. Two classifiers, the support vector classifier (SVC) and the classification and regression tree (CART), are integrated in the TFSP algorithm that decomposes the signal into a weighted time, frequency and spatial feature space. The resulting high-performing methods (SVC-TFSP and CART-TFSP) are then applied to experimental data collected in four healthy subjects and two stroke subjects. Results are compared with the original TFSP, and significantly higher reliability in both healthy subjects (92% averaged over four healthy subjects) and stroke subjects (75% averaged over two subjects) are achieved. The accuracies of classifier-enhanced TFSP methods are further improved after a rejection scheme is applied (∼100% in healthy subjects and >80% in stroke subjects). The results are among the highest reliability reported in literature for tasks with spatial representations on the motor cortex as close as shoulder and elbow. The paper also discusses the impact of applying rejection strategy in detail and reports the existence of an optimal rejection rate on a stroke subject. The results indicate that the proposed algorithms are promising for future use of rehabilitative BCI applications in neurologically impaired patients.

AB - The ultimate aim for classifying elbow versus shoulder torque intentions is to develop robust brain-computer interface (BCI) devices for patients who suffer from movement disorders following brain injury such as stroke. In this paper, we investigate the advanced classification approach classifier-enhanced time-frequency synthesized spatial pattern algorithm (classifier-enhanced TFSP) in classifying a subject's intent of generating an isometric shoulder abduction (SABD) or elbow flexion (EF) torque using signals obtained from 163 scalp electroencephalographic (EEG) electrodes. Two classifiers, the support vector classifier (SVC) and the classification and regression tree (CART), are integrated in the TFSP algorithm that decomposes the signal into a weighted time, frequency and spatial feature space. The resulting high-performing methods (SVC-TFSP and CART-TFSP) are then applied to experimental data collected in four healthy subjects and two stroke subjects. Results are compared with the original TFSP, and significantly higher reliability in both healthy subjects (92% averaged over four healthy subjects) and stroke subjects (75% averaged over two subjects) are achieved. The accuracies of classifier-enhanced TFSP methods are further improved after a rejection scheme is applied (∼100% in healthy subjects and >80% in stroke subjects). The results are among the highest reliability reported in literature for tasks with spatial representations on the motor cortex as close as shoulder and elbow. The paper also discusses the impact of applying rejection strategy in detail and reports the existence of an optimal rejection rate on a stroke subject. The results indicate that the proposed algorithms are promising for future use of rehabilitative BCI applications in neurologically impaired patients.

KW - Brain-computer interface

KW - Classification

KW - Classification and regression tree

KW - Elbow flexion

KW - Electroencephalograph (EEG)

KW - Shoulder abduction

KW - Stroke

KW - Support-vector machine

KW - Time-frequency synthesized spatial pattern algorithm

UR - http://www.scopus.com/inward/record.url?scp=67349113149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67349113149&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2009.02.004

DO - 10.1016/j.compbiomed.2009.02.004

M3 - Article

C2 - 19380125

AN - SCOPUS:67349113149

VL - 39

SP - 443

EP - 452

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

IS - 5

ER -