Detecting Epileptic Seizures via Non-Uniform Multivariate Embedding of EEG Signals.
Annu Int Conf IEEE Eng Med Biol Soc
; 2021: 1690-1693, 2021 11.
Article
em En
| MEDLINE
| ID: mdl-34891611
ABSTRACT
Efficient real-time detection of epileptic seizures remains a challenging task in clinical practice. In this study, we introduce a new thresholding method to monitor brain activities via a non-uniform multivariate (NUM) embedding of multi-channel electroencephalogram (EEG) signals. Specifically, we present a NUM embedding optimization problem to identify the best embedding parameters. We originate one feature, named non-uniform multivariate multiscale entropy (NUMME), which is extracted from the NUM embedded EEG data. Finally, the extracted feature, compared to an individualized threshold, is used for monitoring and detecting seizure onsets. Experimental results on the real CHB-MIT Scalp EEG database show that our approach achieves a comparable performance to the state-of-art methods. Moreover, it is important to note that we accomplish this without using any sophisticated machine learning algorithms.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Processamento de Sinais Assistido por Computador
/
Epilepsia
Tipo de estudo:
Diagnostic_studies
/
Prognostic_studies
Limite:
Humans
Idioma:
En
Revista:
Annu Int Conf IEEE Eng Med Biol Soc
Ano de publicação:
2021
Tipo de documento:
Article