Multi-subject EEG classification: Bayesian nonparametrics and multi-task learning

Multi-subject electroencephalography (EEG) classification involves algorithm development for automatic classification of brain waves measured from multiple subjects who undergo the same mental task. Common spatial patterns (CSP) or its probabilistic counterpart, PCSP, is a popular discriminative fea...

Full description

Saved in:
Bibliographic Details
Published inThe 3rd International Winter Conference on Brain-Computer Interface p. 1
Main Author Seungjin Choi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.01.2015
Subjects
Bayes methods
Brain models
Conferences
Electroencephalography
Feature extraction
Probabilistic logic
Online AccessGet full text

Cover

More Information
Summary:Multi-subject electroencephalography (EEG) classification involves algorithm development for automatic classification of brain waves measured from multiple subjects who undergo the same mental task. Common spatial patterns (CSP) or its probabilistic counterpart, PCSP, is a popular discriminative feature extraction method for EEG classification. Models in CSP or PCSP are trained on a subject-by-subject basis so that inter-subject information is neglected. In the case of multi-subject EEG classification, however, it is desirable to capture inter-subject relatedness in learning a model. This paper outlines a brief overview of our recent work on how Bayesian multi-task learning is applied to multi-subject EEG classification, treating subjects as tasks to capture inter-subject relatedness in Bayesian treatment of PCSP.
ISBN:9781479974948
1479974943
DOI:10.1109/IWW-BCI.2015.7073022