Robust Learning of Mixture Models and Its Application on Trial Pruning for EEG Signal Analysis
This paper presents a novel method based on deterministic annealing to circumvent the problem of the sensitivity to atypical observations associated with the maximum likelihood (ML) estimator via conventional EM algorithm for mixture models. In order to learn the mixture models in a robust way, the parameters of mixture model are estimated by trimmed likelihood estimator (TLE), and the learning process is controlled by temperature based on the principle of maximum entropy. Moreover, we apply the proposed method to the single-trial electroencephalography (EEG) classification task. The motivation of this work is to eliminate the negative effects of artifacts in EEG data, which usually exist in real-life environments, and the experimental results demonstrate that the proposed method can successfully detect the outliers and therefore achieve more reliable result.
KeywordsDeterministic annealing mixture models robust learning trial pruning EEG signals
Unable to display preview. Download preview PDF.
- 8.Millán, J.R.: On the need for on-line learning in brain–computer interfaces. In: Proceedings of International Joint Conference on Neural Networks, Budapest, Hungary, pp. 2877–2882 (2004)Google Scholar
- 9.Buttfield, A., Millán, J.R.: Online classifier adaptation in brain-computer interfaces. Techical Report, IDIAP–RR 06-16 (2006)Google Scholar
- 15.Nguyen, D.T., Chen, L., Chan, C.K.: An outlier-aware data clustering algorithm in mixture model. In: Proceedings of 7th IEEE International Conference on Information, Communication and Signal Processing, Macau, China, pp. 1–5 (2009)Google Scholar
- 22.Grant, M., Boyd, S.: CVX: Matlab software for disciplined convex programming, version 1.21, http://cvxr.com/cvx
- 24.Machine Learning Repository website, http://archive.ics.uci.edu/ml/index.html
- 25.BCI competition IV website, http://bbci.de/competition/iv/
- 27.Zhao, Q., Miller, D.J.: A deterministic, annealing-based approach for learning and model selection in finite mixture models. In: Proceedings of 29th IEEE International Conference on Acoustics, Speech, and Signal Processing, Montreal, Canada, pp. V-457–V-460 (2004)Google Scholar