Authors:
Dieter Devlaminck
1
;
Bart Wyns
1
;
Georges Otte
2
and
Patrick Santens
3
Affiliations:
1
Ghent University, Belgium
;
2
P.C. Guislain, Belgium
;
3
Ghent University Hospital, Belgium
Keyword(s):
Multi-subject learning, Common Spatial Patterns (CSP), Brain-Computer Interfaces (BCI).
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computer Vision, Visualization and Computer Graphics
;
Cybernetics and User Interface Technologies
;
Data Manipulation
;
Detection and Identification
;
Devices
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Information and Systems Security
;
Medical Image Detection, Acquisition, Analysis and Processing
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Soft Computing
Abstract:
Motor imagery based brain-computer interfaces (BCI) commonly use the common spatial pattern filter (CSP) as preprocessing step before feature extraction and classifiction. The CSP method is a supervised algorithm and therefore needs subject specific training data for calibration, which is very time consuming to collect. Instead of letting all that data and effort go to waste, the data of other subjects could be used to further improve results for new subjects. This problem setting is often encountered in multitask learning, from which we will borrow some ideas and apply it to the preprocessing phase.
This paper outlines the details of the multitask CSP algorithm and shows some results on data from the third BCI competition. In some of the subjects a clear improvement can be seen by using information of other subjects, while in some subjects the algorithm determines that a specific model is the best. We also compare the use of a global filter, which is constructed only with data of ot
her subjects, with the case where we ommit any form of spatial filtering. Here, the global filter seems to boost performance in four of the five subjects.
(More)