EEG Signal Analysis via a Cleaning Procedure based on Multivariate Empirical Mode Decomposition
Esteve Gallego-Jutglà, Tomasz M. Rutkowski, Andrzej Cichocki, Jordi Solé-Casals
2012
Abstract
Artifacts are present in most of the electroencephalography (EEG) recordings, making it difficult to interpret or analyze the data. In this paper a cleaning procedure based on a multivariate extension of empirical mode decomposition is used to improve the quality of the data. This is achieved by applying the cleaning method to raw EEG data. Then, a synchrony measure is applied on the raw and the clean data in order to compare the improvement of the classification rate. Two classifiers are used, linear discriminant analysis and neural networks. For both cases, the classification rate is improved about 20%.
DownloadPaper Citation
in Harvard Style
Gallego-Jutglà E., Rutkowski T., Cichocki A. and Solé-Casals J. (2012). EEG Signal Analysis via a Cleaning Procedure based on Multivariate Empirical Mode Decomposition . In Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: SSCN, (IJCCI 2012) ISBN 978-989-8565-33-4, pages 670-676. DOI: 10.5220/0004182206700676
in Bibtex Style
@conference{sscn12,
author={Esteve Gallego-Jutglà and Tomasz M. Rutkowski and Andrzej Cichocki and Jordi Solé-Casals},
title={EEG Signal Analysis via a Cleaning Procedure based on Multivariate Empirical Mode Decomposition},
booktitle={Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: SSCN, (IJCCI 2012)},
year={2012},
pages={670-676},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004182206700676},
isbn={978-989-8565-33-4},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 4th International Joint Conference on Computational Intelligence - Volume 1: SSCN, (IJCCI 2012)
TI - EEG Signal Analysis via a Cleaning Procedure based on Multivariate Empirical Mode Decomposition
SN - 978-989-8565-33-4
AU - Gallego-Jutglà E.
AU - Rutkowski T.
AU - Cichocki A.
AU - Solé-Casals J.
PY - 2012
SP - 670
EP - 676
DO - 10.5220/0004182206700676