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

• Published in: IEEE transactions on biomedical engineering Vol. 58; no. 2; pp. 355 - 362
• Main Authors: Lotte, Fabien, Guan, Cuntai
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.02.2011; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 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
• DOI: 10.1109/TBME.2010.2082539

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.