A Maxmin Approach to Optimize Spatial Filters for EEG Single-Trial Classification

Authors:
Motoaki Kawanabe;Carmen Vidaurre;Benjamin Blankertz;Klaus-Robert Müller
Affiliations:
IDA group, FIRST, Fraunhofer Institute, Berlin, Germany 12489 and Computer Science Faculty, Machine Learning department, Berlin Institute of Technology, Berlin, Germany 10587;Computer Science Faculty, Machine Learning department, Berlin Institute of Technology, Berlin, Germany 10587;IDA group, FIRST, Fraunhofer Institute, Berlin, Germany 12489 and Computer Science Faculty, Machine Learning department, Berlin Institute of Technology, Berlin, Germany 10587;Computer Science Faculty, Machine Learning department, Berlin Institute of Technology, Berlin, Germany 10587
Venue:
IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part I: Bio-Inspired Systems: Computational and Ambient Intelligence
Year:
2009

Citing 3
Cited 0

The Handbook of Brain Theory and Neural Networks

The Handbook of Brain Theory and Neural Networks
Brain-Computer Interfacing for Intelligent Systems

IEEE Intelligent Systems
An introduction to kernel-based learning algorithms

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Electroencephalographic single-trial analysis requires methods that are robust with respect to noise, artifacts and non-stationarity among other problems. This work contributes by developing a maxmin approach to robustify the common spatial patterns (CSP) algorithm. By optimizing the worst-case objective function within a prefixed set of the covariance matrices, we can transform the respective complex mathematical program into a simple generalized eigenvalue problem and thus obtain robust spatial filters very efficiently. We test our maxmin CSP method with real world brain-computer interface (BCI) data sets in which we expect substantial fluctuations caused by day-to-day or paradigm-to-paradigm variability or different forms of stimuli. The results clearly show that the proposed method significantly improves the classical CSP approach in multiple BCI scenarios.