Research Repository

Wavelet design by means of multi-objective GAs for motor imagery EEG analysis

Asensio-Cubero, J and Galvan, E and Panlaniappan, R and Gan, JQ (2011) 'Wavelet design by means of multi-objective GAs for motor imagery EEG analysis.' In: M�ller-Putz, GR and Scherer, R and Billinger, M and Kreilinger, A and Kaiser, V and Neuper, C, (eds.) The 5th International Brain-Computer Interface Conference. Verlag der Technischen Universitat Graz, 60 - 63. ISBN 9783851251401

[img]
Preview
Text
graz_bci_2011.pdf

Download (196kB) | Preview

Abstract

Wavelet-based analysis has been broadly used in the study of brain-computer interfaces (BCI), but in most cases these wavelet functions have not been designed taking into account the requirements of this field. In this study we propose a method to automatically generate wavelet-like functions by means of genetic algorithms. Results strongly indicate that it is possible to generate (evolve) wavelet functions that improve the classification accuracy compared to other well-known wavelets (e.g. Daubechies and Coiflets).

Item Type: Book Section
Subjects: P Language and Literature > P Philology. Linguistics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Faculty of Science and Health > Computer Science and Electronic Engineering, School of
Depositing User: Users 161 not found.
Date Deposited: 29 Aug 2013 22:40
Last Modified: 17 Aug 2017 18:07
URI: http://repository.essex.ac.uk/id/eprint/4252

Actions (login required)

View Item View Item