PMID- 17355055
OWN - NLM
STAT- MEDLINE
DCOM- 20071217
LR  - 20091111
IS  - 0018-9294 (Print)
IS  - 0018-9294 (Linking)
VI  - 54
IP  - 3
DP  - 2007 Mar
TI  - Single-trial classification of MEG recordings.
PG  - 436-43
AB  - While magnetoencephalography (MEG) is widely used to identify spatial locations 
      of brain activations associated with various tasks, classification of single 
      trials in stimulus-locked experiments remains an open subject. Very significant 
      single-trial classification results have been published using 
      electroencephalogram (EEG) data, but in the MEG case, the weakness of the 
      magnetic fields originating from the relevant sources relative to external noise, 
      and the high dimensionality of the data are difficult obstacles to overcome. We 
      present here very significant MEG single-trial mean classification rates of 
      words. The number of words classified varied from seven to nine and both visual 
      and auditory modalities were studied. These results were obtained by using a 
      variety of blind sources separation methods: spatial principal components 
      analysis (PCA), Infomax independent components analysis (Infomax ICA) and 
      second-order blind identification (SOBI). The sources obtained were classified 
      using two methods, linear discriminant classification (LDC) and v-support vector 
      machine (v-SVM). The data used here, auditory and visual presentations of words, 
      presented nontrivial classification problems, but with Infomax ICA associated 
      with LDC we obtained high classification rates. Our best single-trial mean 
      classification rate was 60.1% for classification of 900 single trials of nine 
      auditory words. On two-class problems rates were as high as 97.5%.
FAU - Guimaraes, Marcos Perreau
AU  - Guimaraes MP
AD  - Center for Study of Language and Information, CSLI 220 Panama Street, Stanford 
      University, Stanford, CA 94305, USA. marcospg@csli.stanford.edu
FAU - Wong, Dik Kin
AU  - Wong DK
FAU - Uy, E Timothy
AU  - Uy ET
FAU - Grosenick, Logan
AU  - Grosenick L
FAU - Suppes, Patrick
AU  - Suppes P
LA  - eng
PT  - Journal Article
PL  - United States
TA  - IEEE Trans Biomed Eng
JT  - IEEE transactions on bio-medical engineering
JID - 0012737
SB  - IM
MH  - *Algorithms
MH  - Brain Mapping/*methods
MH  - Cluster Analysis
MH  - Diagnosis, Computer-Assisted/methods
MH  - Evoked Potentials, Auditory/*physiology
MH  - Evoked Potentials, Visual/*physiology
MH  - Humans
MH  - Magnetoencephalography/*methods
MH  - Pattern Recognition, Automated/*methods
MH  - Principal Component Analysis
MH  - Speech Perception/*physiology
EDAT- 2007/03/16 09:00
MHDA- 2007/12/18 09:00
CRDT- 2007/03/16 09:00
PHST- 2007/03/16 09:00 [pubmed]
PHST- 2007/12/18 09:00 [medline]
PHST- 2007/03/16 09:00 [entrez]
AID - 10.1109/TBME.2006.888824 [doi]
PST - ppublish
SO  - IEEE Trans Biomed Eng. 2007 Mar;54(3):436-43. doi: 10.1109/TBME.2006.888824.