Classification methods for ongoing EEG and MEG signals
Classification algorithms help predict the qualitative properties of a subject's mental state by extracting useful information from the highly multivariate non-invasive recordings of his brain activity. In particular, applying them to Magneto-encephalography (MEG) and electro-encephalography (E...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2007-01-01
|
Series: | Biological Research |
Subjects: | |
Online Access: | http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0716-97602007000500005 |
id |
doaj-dba3a17828394a2491e60ca394fd3999 |
---|---|
record_format |
Article |
spelling |
doaj-dba3a17828394a2491e60ca394fd39992020-11-24T22:02:59ZengBMCBiological Research0716-97600717-62872007-01-01404415437Classification methods for ongoing EEG and MEG signalsMICHEL BESSERVEKARIM JERBIFRANCOIS LAURENTSYLVAIN BAILLETJACQUES MARTINERIELINE GARNEROClassification algorithms help predict the qualitative properties of a subject's mental state by extracting useful information from the highly multivariate non-invasive recordings of his brain activity. In particular, applying them to Magneto-encephalography (MEG) and electro-encephalography (EEG) is a challenging and promising task with prominent practical applications to e.g. Brain Computer Interface (BCI). In this paper, we first review the principles of the major classification techniques and discuss their application to MEG and EEG data classification. Next, we investigate the behavior of classification methods using real data recorded during a MEG visuomotor experiment. In particular, we study the influence of the classification algorithm, of the quantitative functional variables used in this classifier, and of the validation method. In addition, our findings suggest that by investigating the distribution of classifier coefficients, it is possible to infer knowledge and construct functional interpretations of the underlying neural mechanisms of the performed tasks. Finally, the promising results reported here (up to 97% classification accuracy on 1-second time windows) reflect the considerable potential of MEG for the continuous classification of mental stateshttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0716-97602007000500005brain computer interfaceelectroencephalographymagnetoencephalographyvisuomotor controlSupport Vector Machine |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
MICHEL BESSERVE KARIM JERBI FRANCOIS LAURENT SYLVAIN BAILLET JACQUES MARTINERIE LINE GARNERO |
spellingShingle |
MICHEL BESSERVE KARIM JERBI FRANCOIS LAURENT SYLVAIN BAILLET JACQUES MARTINERIE LINE GARNERO Classification methods for ongoing EEG and MEG signals Biological Research brain computer interface electroencephalography magnetoencephalography visuomotor control Support Vector Machine |
author_facet |
MICHEL BESSERVE KARIM JERBI FRANCOIS LAURENT SYLVAIN BAILLET JACQUES MARTINERIE LINE GARNERO |
author_sort |
MICHEL BESSERVE |
title |
Classification methods for ongoing EEG and MEG signals |
title_short |
Classification methods for ongoing EEG and MEG signals |
title_full |
Classification methods for ongoing EEG and MEG signals |
title_fullStr |
Classification methods for ongoing EEG and MEG signals |
title_full_unstemmed |
Classification methods for ongoing EEG and MEG signals |
title_sort |
classification methods for ongoing eeg and meg signals |
publisher |
BMC |
series |
Biological Research |
issn |
0716-9760 0717-6287 |
publishDate |
2007-01-01 |
description |
Classification algorithms help predict the qualitative properties of a subject's mental state by extracting useful information from the highly multivariate non-invasive recordings of his brain activity. In particular, applying them to Magneto-encephalography (MEG) and electro-encephalography (EEG) is a challenging and promising task with prominent practical applications to e.g. Brain Computer Interface (BCI). In this paper, we first review the principles of the major classification techniques and discuss their application to MEG and EEG data classification. Next, we investigate the behavior of classification methods using real data recorded during a MEG visuomotor experiment. In particular, we study the influence of the classification algorithm, of the quantitative functional variables used in this classifier, and of the validation method. In addition, our findings suggest that by investigating the distribution of classifier coefficients, it is possible to infer knowledge and construct functional interpretations of the underlying neural mechanisms of the performed tasks. Finally, the promising results reported here (up to 97% classification accuracy on 1-second time windows) reflect the considerable potential of MEG for the continuous classification of mental states |
topic |
brain computer interface electroencephalography magnetoencephalography visuomotor control Support Vector Machine |
url |
http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0716-97602007000500005 |
work_keys_str_mv |
AT michelbesserve classificationmethodsforongoingeegandmegsignals AT karimjerbi classificationmethodsforongoingeegandmegsignals AT francoislaurent classificationmethodsforongoingeegandmegsignals AT sylvainbaillet classificationmethodsforongoingeegandmegsignals AT jacquesmartinerie classificationmethodsforongoingeegandmegsignals AT linegarnero classificationmethodsforongoingeegandmegsignals |
_version_ |
1725833716396195840 |