A Theory of Kernel Extreme Energy Difference for Feature Extraction of EEG Signals

Authors:
Shiliang Sun;Jinbo Li
Affiliations:
Department of Computer Science and Technology, East China Normal University, Shanghai, China 200241;Department of Computer Science and Technology, East China Normal University, Shanghai, China 200241
Venue:
ADMA '09 Proceedings of the 5th International Conference on Advanced Data Mining and Applications
Year:
2009

Citing 3
Cited 0

The nature of statistical learning theory

The nature of statistical learning theory
Kernel Methods for Pattern Analysis

Kernel Methods for Pattern Analysis
The Extreme Energy Ratio Criterion for EEG Feature Extraction

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

Energy features are of great importance for electroencephalogram (EEG) signal classification in the application of brain-computere interfaces (BCI). In this paper, we address the problem of extracting energy features of EEG signals in a feature space induced by kernel functions. The devised method, based on a recently proposed technique extreme energy difference (EED), is called kernel extreme energy difference (KEED). This paper derives solutions which optimize the KEED criterion by the method of Lagrange multipliers.