DocumentCode
2373462
Title
MLSP Competition, 2010: Description of first place method
Author
Leiva, Jose M. ; Martens, Suzanna M M
Author_Institution
Dept. of Signal Theor. & Comms, Univ. Carlos III de Madrid, Leganés, Spain
fYear
2010
fDate
Aug. 29 2010-Sept. 1 2010
Firstpage
112
Lastpage
113
Abstract
Our winning approach to the 2010 MLSP Competition is based on a generative method for P300-based BCI decoding, successfully applied to visual spellers. Here, generative has a double meaning. On the one hand, we work with a probability density model of the data given the target/non target labeling, as opposed to discriminative (e.g. SVM-based) methods. On the other hand, the natural consequence of this approach is a decoding based on comparing the observation to templates generated from the data.
Keywords
brain-computer interfaces; decoding; probability; MLSP competition; P300-based BCI decoding; probability density model; visual spellers; Additives; Band pass filters; Decorrelation; Noise measurement; Principal component analysis; Signal to noise ratio;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning for Signal Processing (MLSP), 2010 IEEE International Workshop on
Conference_Location
Kittila
ISSN
1551-2541
Print_ISBN
978-1-4244-7875-0
Electronic_ISBN
1551-2541
Type
conf
DOI
10.1109/MLSP.2010.5589243
Filename
5589243
Link To Document