Back to Search
Start Over
Multisubject Learning for Common Spatial Patterns in Motor-Imagery BCI
- Source :
- Computational Intelligence and Neuroscience, Vol 2011 (2011), Computational Intelligence and Neuroscience, COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
- Publication Year :
- 2011
- Publisher :
- Hindawi Limited, 2011.
-
Abstract
- Motor-imagery-based brain-computer interfaces (BCIs) commonly use the common spatial pattern filter (CSP) as preprocessing step before feature extraction and classification. The CSP method is a supervised algorithm and therefore needs subject-specific training data for calibration, which is very time consuming to collect. In order to reduce the amount of calibration data that is needed for a new subject, one can apply multitask (from now on called multisubject) machine learning techniques to the preprocessing phase. Here, the goal of multisubject learning is to learn a spatial filter for a new subject based on its own data and that of other subjects. This paper outlines the details of the multitask CSP algorithm and shows results on two data sets. In certain subjects a clear improvement can be seen, especially when the number of training trials is relatively low.
- Subjects :
- Technology and Engineering
General Computer Science
Article Subject
Calibration (statistics)
Computer science
General Mathematics
Feature extraction
Motor Activity
Machine learning
computer.software_genre
lcsh:Computer applications to medicine. Medical informatics
lcsh:RC321-571
User-Computer Interface
Motor imagery
Artificial Intelligence
Medicine and Health Sciences
Preprocessor
Humans
lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry
Brain–computer interface
Spatial filter
business.industry
General Neuroscience
General Medicine
Filter (video)
Spatial ecology
Imagination
lcsh:R858-859.7
Artificial intelligence
business
computer
Algorithms
Research Article
Subjects
Details
- Language :
- English
- ISSN :
- 16875273 and 16875265
- Volume :
- 2011
- Database :
- OpenAIRE
- Journal :
- Computational Intelligence and Neuroscience
- Accession number :
- edsair.doi.dedup.....1b81927eb3aead61b4122426a0e811d6