Study on epileptic seizure detection in EEG signals using largest Lyapunov exponents and logistic regression

"Seizure detection plays a central role in most aspects of epilepsy care. Understanding the complex epileptic signals system is a typical problem in electroencephalographic (EEG) signal processing. This problem requires different analysis to reveal the underlying behavior of EEG signals. An ex...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Quintero-Rincón, Antonio, Flugelman, Máximo, Prendes, Jorge, D'Giano, Carlos
Formato: Artículos de Publicaciones Periódicas acceptedVersion
Lenguaje:Español
Publicado: 2020
Materias:
PROCESAMIENTO DE SEÑALES
EPILEPSIA
ELECTROENCEFALOGRAFIA
Acceso en línea:http://ri.itba.edu.ar/handle/123456789/3056
Aporte de:
Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA) de Instituto Tecnológico de Buenos Aires (ITBA)
id I32-R138-123456789-3056
record_format dspace
spelling I32-R138-123456789-30562022-12-07T13:06:14Z Study on epileptic seizure detection in EEG signals using largest Lyapunov exponents and logistic regression Quintero-Rincón, Antonio Flugelman, Máximo Prendes, Jorge D'Giano, Carlos PROCESAMIENTO DE SEÑALES EPILEPSIA ELECTROENCEFALOGRAFIA "Seizure detection plays a central role in most aspects of epilepsy care. Understanding the complex epileptic signals system is a typical problem in electroencephalographic (EEG) signal processing. This problem requires different analysis to reveal the underlying behavior of EEG signals. An example of this is the non-linear dynamic: mathematical tools applied to biomedical problems with the purpose of extracting features or quantifying EEG data. In this work, we studied epileptic seizure detection independently in each brain rhythms from a multilevel 1D wavelet decomposition followed by the independent component analysis (ICA) representation of multivariate EEG signals. Next, the largest Lyapunov exponents (LLE) and their scaling given by its standard deviation are estimated in order to obtain the vectors to be used during the training and classification stage. With this information, a logistic regression classification is proposed with the aim of discriminating between seizure and non-seizure. Preliminary experiments with 99 epileptic events suggest that the proposed methodology is a powerful tool for detecting seizures in epileptic signals in terms of classification accuracy, sensitivity and specificity." "La detección de convulsiones juega un rol muy importante en el tratamiento de la epilepsia. Entender el sistema complejo de las señales epilépticas es un problema típico en procesamiento de señales electroencefalográficas (EEG). Este problema requiere diferentes tipos de análisis para poder determinar el comportamiento subyacente de las señales EEG. Un ejemplo de esto es la dinámica no lineal: herramientas matemáticas aplicadas a problemas biomédicos con el propósito de extraer características o cuantificar datos del EEG. En este trabajo, estudiamos la detección de crisis epilépticas de forma independiente en cada ritmo cerebral a partir de una descomposición wavelet multinivel 1D seguida de un análisis de componentes independientes (ICA) de señales de EEG multivariadas. A continuación, se estiman los mayores exponentes de Lyapunov (LLE) y su escalamiento dado por su desviación estándar para obtener los vectores que se utilizarán durante la etapa de entrenamiento y clasificación. Con esta información, se propone una clasificación usando la regresión logística con el objetivo de discriminar entre convulsión y no-convulsión. Experimentos preliminares con 99 eventos epilépticos, sugieren que la metodología propuesta es una poderosa herramienta para detectar ataques convulsivos en señaales epilépticas en términos de precisión, sensibilidad y especificidad del clasificador." 2020-09-25T21:00:20Z 2020-09-25T21:00:20Z 2019 Artículos de Publicaciones Periódicas info:eu-repo/semantics/acceptedVersion 0329-5257 http://ri.itba.edu.ar/handle/123456789/3056 es info:eu-repo/semantics/altIdentifier/url//http://revista.sabi.org.ar/index.php/revista/article/view/157 application/pdf
institution Instituto Tecnológico de Buenos Aires (ITBA)
institution_str I-32
repository_str R-138
collection Repositorio Institucional Instituto Tecnológico de Buenos Aires (ITBA)
language Español
topic PROCESAMIENTO DE SEÑALES
EPILEPSIA
ELECTROENCEFALOGRAFIA
spellingShingle PROCESAMIENTO DE SEÑALES
EPILEPSIA
ELECTROENCEFALOGRAFIA
Quintero-Rincón, Antonio
Flugelman, Máximo
Prendes, Jorge
D'Giano, Carlos
Study on epileptic seizure detection in EEG signals using largest Lyapunov exponents and logistic regression
topic_facet PROCESAMIENTO DE SEÑALES
EPILEPSIA
ELECTROENCEFALOGRAFIA
description "Seizure detection plays a central role in most aspects of epilepsy care. Understanding the complex epileptic signals system is a typical problem in electroencephalographic (EEG) signal processing. This problem requires different analysis to reveal the underlying behavior of EEG signals. An example of this is the non-linear dynamic: mathematical tools applied to biomedical problems with the purpose of extracting features or quantifying EEG data. In this work, we studied epileptic seizure detection independently in each brain rhythms from a multilevel 1D wavelet decomposition followed by the independent component analysis (ICA) representation of multivariate EEG signals. Next, the largest Lyapunov exponents (LLE) and their scaling given by its standard deviation are estimated in order to obtain the vectors to be used during the training and classification stage. With this information, a logistic regression classification is proposed with the aim of discriminating between seizure and non-seizure. Preliminary experiments with 99 epileptic events suggest that the proposed methodology is a powerful tool for detecting seizures in epileptic signals in terms of classification accuracy, sensitivity and specificity."
format Artículos de Publicaciones Periódicas
acceptedVersion
author Quintero-Rincón, Antonio
Flugelman, Máximo
Prendes, Jorge
D'Giano, Carlos
author_facet Quintero-Rincón, Antonio
Flugelman, Máximo
Prendes, Jorge
D'Giano, Carlos
author_sort Quintero-Rincón, Antonio
title Study on epileptic seizure detection in EEG signals using largest Lyapunov exponents and logistic regression
title_short Study on epileptic seizure detection in EEG signals using largest Lyapunov exponents and logistic regression
title_full Study on epileptic seizure detection in EEG signals using largest Lyapunov exponents and logistic regression
title_fullStr Study on epileptic seizure detection in EEG signals using largest Lyapunov exponents and logistic regression
title_full_unstemmed Study on epileptic seizure detection in EEG signals using largest Lyapunov exponents and logistic regression
title_sort study on epileptic seizure detection in eeg signals using largest lyapunov exponents and logistic regression
publishDate 2020
url http://ri.itba.edu.ar/handle/123456789/3056
work_keys_str_mv AT quinterorinconantonio studyonepilepticseizuredetectionineegsignalsusinglargestlyapunovexponentsandlogisticregression
AT flugelmanmaximo studyonepilepticseizuredetectionineegsignalsusinglargestlyapunovexponentsandlogisticregression
AT prendesjorge studyonepilepticseizuredetectionineegsignalsusinglargestlyapunovexponentsandlogisticregression
AT dgianocarlos studyonepilepticseizuredetectionineegsignalsusinglargestlyapunovexponentsandlogisticregression
_version_ 1765660771773054976

Ejemplares similares