Linked Life Data

19015582

Source:http://linkedlifedata.com/resource/pubmed/id/19015582

Statements in which the resource exists as a subject.
PredicateObject
rdf:type
lifeskim:mentions
pubmed:issue
4
pubmed:dateCreated
2008-11-21
pubmed:abstractText
This paper presents a novel brain-computer interface (BCI) based on motion-onset visual evoked potentials (mVEPs). mVEP has never been used in BCI research, but has been widely studied in basic research. For the BCI application, the brief motion of objects embedded into onscreen virtual buttons is used to evoke mVEP that is time locked to the onset of motion. EEG data registered from 15 subjects are used to investigate the spatio-temporal pattern of mVEP in this paradigm. N2 and P2 components, with distinct temporo-occipital and parietal topography, respectively, are selected as the salient features of the brain response to the attended target that the subject selects by gazing at it. The computer determines the attended target by finding which button elicited prominent N2/P2 components. Besides a simple feature extraction of N2/P2 area calculation, the stepwise linear discriminant analysis is adopted to assess the target detection accuracy of a five-class BCI. A mean accuracy of 98% is achieved when ten trials data are averaged. Even with only three trials, the accuracy remains above 90%, suggesting that the proposed mVEP-based BCI could achieve a high information transfer rate in online implementation.
pubmed:language
eng
pubmed:journal
pubmed:citationSubset
IM
pubmed:status
MEDLINE
pubmed:month
Dec
pubmed:issn
1741-2560
pubmed:author
pubmed:issnType
Print
pubmed:volume
5
pubmed:owner
NLM
pubmed:authorsComplete
Y
pubmed:pagination
477-85
pubmed:meshHeading
pubmed:year
2008
pubmed:articleTitle
A brain-computer interface using motion-onset visual evoked potential.
pubmed:affiliation
Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, 100084, People's Republic of China.
pubmed:publicationType
Journal Article, Research Support, Non-U.S. Gov't