Regularizing Common Spatial Patterns to Improve BCI Designs: Unified Theory and New Algorithms

One of the most popular feature extraction algorithms for brain-computer interfaces (BCI) is common spatial patterns (CSPs). Despite its known efficiency and widespread use, CSP is also known to be very sensitive to noise and prone to overfitting. To address this issue, it has been recently proposed...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on biomedical engineering Jg. 58; H. 2; S. 355 - 362
Hauptverfasser: Lotte, Fabien, Guan, Cuntai
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York, NY IEEE 01.02.2011
Institute of Electrical and Electronics Engineers
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Algorithm design and analysis
Algorithms
Applied sciences
Artificial Intelligence
Biological and medical sciences
Biotechnology
Brain-computer interfaces (BCI)
common spatial patterns (CSP)
Computer Science
Computer science; control theory; systems
Computer systems and distributed systems. User interface
Computerized, statistical medical data processing and models in biomedicine
Covariance matrix
Eigenvalues and eigenfunctions
Electrodes
Electrodiagnosis. Electric activity recording
Electroencephalography
electroencephalography (EEG)
Electroencephalography - methods
Engineering Sciences
Exact sciences and technology
Humans
Investigative techniques, diagnostic techniques (general aspects)
Life Sciences
Man-Machine Systems
Medical management aid. Diagnosis aid
Medical sciences
Models, Neurological
Nervous system
Noise
Pattern Recognition, Automated - methods
Regression Analysis
regularization
Signal and Image Processing
Signal Processing, Computer-Assisted
Software
subject-to-subject transfer
Training
User-Computer Interface
Human
regularization
Theoretical study
Man machine dialogue
Brain-computer interfaces (BCI)
Electroencephalography
common spatial patterns (CSP)
Pattern recognition
Algorithm
Design
Brain-computer interface
electroencephalography (EEG)
Electrodiagnosis
User interface
subject-to-subject transfer
Signal processing
Biomedical engineering
ISSN:0018-9294, 1558-2531, 1558-2531
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:One of the most popular feature extraction algorithms for brain-computer interfaces (BCI) is common spatial patterns (CSPs). Despite its known efficiency and widespread use, CSP is also known to be very sensitive to noise and prone to overfitting. To address this issue, it has been recently proposed to regularize CSP. In this paper, we present a simple and unifying theoretical framework to design such a regularized CSP (RCSP). We then present a review of existing RCSP algorithms and describe how to cast them in this framework. We also propose four new RCSP algorithms. Finally, we compare the performances of 11 different RCSP (including the four new ones and the original CSP), on electroencephalography data from 17 subjects, from BCI competition datasets. Results showed that the best RCSP methods can outperform CSP by nearly 10% in median classification accuracy and lead to more neurophysiologically relevant spatial filters. They also enable us to perform efficient subject-to-subject transfer. Overall, the best RCSP algorithms were CSP with Tikhonov regularization and weighted Tikhonov regularization, both proposed in this paper.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ObjectType-Article-2
ObjectType-Conference-1
ObjectType-Feature-3
SourceType-Conference Papers & Proceedings-2
ISSN:0018-9294
1558-2531
1558-2531
DOI:10.1109/TBME.2010.2082539