Subject-independent mental state classification in single trials

• Published in: Neural networks Vol. 22; no. 9; pp. 1305 - 1312
• Main Authors: Fazli, Siamac, Popescu, Florin, Danóczy, Márton, Blankertz, Benjamin, Müller, Klaus-Robert, Grozea, Cristian
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.11.2009
• Subjects: Algorithms; BCI; Brain - physiology; Calibration; Databases as Topic; Electroencephalography - methods; Humans; Machine learning; Mental Processes - physiology; Regression Analysis; Reproducibility of Results; Time Factors; User-Computer Interface; Zero-training; BCI; Zero-training; Machine learning
• ISSN: 0893-6080; 1879-2782; 1879-2782
• DOI: 10.1016/j.neunet.2009.06.003

Current state-of-the-art in Brain Computer Interfacing (BCI) involves tuning classifiers to subject-specific training data acquired from calibration sessions prior to functional BCI use. Using a large database of EEG recordings from 45 subjects, who took part in movement imagination task experiments, we construct an ensemble of classifiers derived from subject-specific temporal and spatial filters. The ensemble is then sparsified using quadratic regression with ℓ 1 regularization such that the final classifier generalizes reliably to data of subjects not included in the ensemble. Our offline results indicate that BCI-naïve users could start real-time BCI use without any prior calibration at only very limited loss of performance.