A bayesian model for exploiting application constraints to enable unsupervised training of a P300-based BCI
Pieter-Jan Kindermans, David Verstraeten, Benjamin Schrauwen, Pieter-Jan Kindermans, David Verstraeten, Benjamin Schrauwen
Abstract
This work introduces a novel classifier for a P300-based speller, which, contrary to common methods, can be trained entirely unsupervisedly using an Expectation Maximization approach, eliminating the need for costly dataset collection or tedious calibration sessions. We use publicly available datasets for validation of our method and show that our unsupervised classifier performs competitively with supervised state-of-the-art spellers. Finally, we demonstrate the added value of our method in different experimental settings which reflect realistic usage situations of increasing difficulty and which would be difficult or impossible to tackle with existing supervised or adaptive methods.
Conflict of interest statement
Competing Interests: The authors have declared that no competing interests exist.
Figures
References
- Vidal JJ. Toward direct brain-computer communication. Annual Review of Biophysics and Bioengineering. 1973;2:157–180.
- Wolpaw JR, Birbaumer N, McFarland DJ, Pfurtscheller G, Vaughan TM. Brain-computer interfaces for communication and control. Clinical Neurophysiology. 2002;113:767–791.
- Farwell L, Donchin E. Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials. Electroencephalography and Clinical Neurophysiology. 1988;70:510–523.
- Nijboer F, Sellers E, Mellinger J, Jordan M, Matuz T, et al. A P300-based brain-computer interface for people with amyotrophic lateral sclerosis. Clinical Neurophysiology. 2008;119:1909–1916.
- Vaughan T, McFarland D, Schalk G, Sarnacki W, Krusienski D, et al. The wadsworth BCI research and development program: at home with BCI. Neural Systems and Rehabilitation Engineering, IEEE Transactions on. 2006;14:229–233.
- Krauledat M, Tangermann M, Blankertz B, Müller KR. Towards zero training for braincomputer interfacing. PLoS ONE. 2008;3:e2967.
- Cecotti H, Graser A. Convolutional neural networks for P300 detection with application to brain-computer interfaces. IEEE Trans on Pattern Analysis and Machine Intelligence. 2010;99
- Picton TW. The P300 wave of the human event-related potential. J Clin Neurophysiol. 1992;9:456–479.
- Donchin E, Spencer K, Wijesinghe R. The mental prosthesis: assessing the speed of a P300-based brain-computer interface. Rehabilitation Engineering, IEEE Transactions on. 2000;8:174–179.
- Blankertz B, Muller KR, Curio G, Vaughan T, Schalk G, et al. The BCI competition 2003: progress and perspectives in detection and discrimination of EEG single trials. IEEE Trans on Biomedical Engineering. 2004;51:1044–1051.
- Blankertz B, Muller KR, Krusienski D, Schalk G, Wolpaw J, et al. The BCI competition iii: validating alternative approaches to actual bci problems. IEEE Trans on Neural Systems and Rehabilitation Engineering. 2006;14:153–159.
- Yanez-Suarez O, Bougrain L, Saavedra C, Bojorges E, Gentiletti G. 2012. P300-speller publicdomain database.
- Hoffmann U, Garcia G, Vesin JM, Diserens K, Ebrahimi T Neural Engineering, 2005. Conference Proceedings. 2nd International IEEE EMBS Conference on; 2005. A boosting approach to P300 detection with application to brain-computer interfaces. pp. 97–100.
- Liu Y, Zhou Z, Hu D, Dong G Neural Networks and Brain, 2005. ICNN B ′05. volume 3. International Conference on.; 2005. T-weighted approach for neural information processing in P300 based brain-computer interface. pp. 1535–1539.
- Xu N, Gao X, Hong B, Miao X, Gao S, et al. BCI competition 2003-data set iib: enhancing P300 wave detection using ICA-based subspace projections for BCI applications. IEEE Trans on Biomedical Engineering. 2004;51:1067–1072.
- Kindermans PJ, Verstraeten D, Buteneers P, Schrauwen B. 5th international Brain-Computer Interface Conference, Proceedings; 2011. How do you like your P300 speller : adaptive, accurate and simple?
- Rakotomamonjy A, Guigue V. BCI competition iii: Dataset ii- ensemble of SVMs for BCI P300 speller. IEEE Trans on Biomedical Engineering. 2008;55:1147–1154.
- Toh KA. Deterministic neural classification. Neural Computation. 2008;20:1565–1595.
- Lu S, Guan C, Zhang H. Unsupervised brain computer interface based on intersubject information and online adaptation. IEEE Trans on Neural Systems and Rehabilitation Engineering. 2009;17:135–145.
- Panicker R, Puthusserypady S, Sun Y. Adaptation in P300 brain-computer interfaces: A twoclassifier cotraining approach. IEEE Trans on Biomedical Engineering. 2010;57:2927–2935.
- Li Y, Guan C, Li H, Chin Z. A self-training semi-supervised SVM algorithm and its application in an EEG-based brain computer interface speller system. Pattern Recognition Letters. 2008;29:1285–1294.
- Dahne S, Hohne J, Tangermann M. 5th international brain-computer interface conference, Proceedings; 2011. Adaptive classification improves control performance in ERP-based bcis.
- Fisher RA. The use of multiple measurements in taxonomic problems. Annals of Human Genetics. 1936;7:179–188.
- Bishop CM. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer, 1 edition 2007
- Hoffmann U, Vesin JM, Ebrahimi T, Diserens K. An efficient P300-based brain–computer interface for disabled subjects. Journal of Neuroscience Methods. 2008;167:115–125.
- Dornhege G, del R Millan J, Hinterberger T, McFarland DJ, Mueller KR. Towards Brain- Computer Interfacing. MIT Press; 2007.
- Xu P, Yang P, Lei X, Yao D. An enhanced probabilistic LDA for multi-class brain computer interface. PLoS ONE. 2011;6:e14634.
- Blankertz B, Lemm S, Treder M, Haufe S, Muller KR. Single-trial analysis and classification of ERP components, a tutorial. NeuroImage. 2011;56:814–825.
- Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society Series B (Methodological) 1977;39:1–38.
Source: PubMed