Classification of the intention to generate a shoulder versus elbow torque by means of a time-frequency synthesized spatial patterns BCI algorithm.

Full Abstract

In this paper, we attempt to determine a subject's intention of generating torque at the shoulder or elbow, two neighboring joints, using scalp electroencephalogram signals from 163 electrodes for a brain-computer interface (BCI) application. To achieve this goal, we have applied a time-frequency synthesized spatial patterns (TFSP) BCI algorithm with a presorting procedure. Using this method, we were able to achieve an average recognition rate of 89% in four healthy subjects, which is comparable to the highest rates reported in the literature but now for tasks with much closer spatial representations on the motor cortex. This result demonstrates, for the first time, that the TFSP BCI method can be applied to separate intentions between generating static shoulder versus elbow torque. Furthermore, in this study, the potential application of this BCI algorithm for brain-injured patients was tested in one chronic hemiparetic stroke subject. A recognition rate of 76% was obtained, suggesting that this BCI method can provide a potential control signal for neural prostheses or other movement coordination improving devices for patients following brain injury.

Author information

Author/s: Deng, Jie (J); Yao, Jun (J); Dewald, Julius P A (JP);

Affiliation: Department of Biomedical Engineering, Northwestern University, Chicago, IL, USA.

Grants: 5R01HD 39343-02 (Agency:NICHD NIH HHS) ; R03 HD39804-01A1 (Agency:NICHD NIH HHS)

Journal and publication information

Publication Type: Clinical Trial; Journal Article; Research Support, N.I.H., Extramural; Research Support, Non-U.S. Gov't

Journal: Journal of neural engineering (J Neural Eng), published in England. (Language: eng)

Reference: 2005-Dec; vol 2 (issue 4) : pp 131-8

Dates: Created 2005/11/30; Completed 2006/04/18; Revised 2007/11/14;

PMID: 16317237, status: MEDLINE (last retrieval date: 2/18/2009, IMS Date: )

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

External Links for this article
(including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.