Cargando…

Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms

Electroencephalography (EEG) signal classification is a challenging task due to the low signal-to-noise ratio and the usual presence of artifacts from different sources. Different classification techniques, which are usually based on a predefined set of features extracted from the EEG band power dis...

Descripción completa

Detalles Bibliográficos
Autores principales: Aquino-Brítez, Diego, Ortiz, Andrés, Ortega, Julio, León, Javier, Formoso, Marco, Gan, John Q., Escobar, Juan José
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8002580/
https://www.ncbi.nlm.nih.gov/pubmed/33802684
http://dx.doi.org/10.3390/s21062096
_version_ 1783671496787361792
author Aquino-Brítez, Diego
Ortiz, Andrés
Ortega, Julio
León, Javier
Formoso, Marco
Gan, John Q.
Escobar, Juan José
author_facet Aquino-Brítez, Diego
Ortiz, Andrés
Ortega, Julio
León, Javier
Formoso, Marco
Gan, John Q.
Escobar, Juan José
author_sort Aquino-Brítez, Diego
collection PubMed
description Electroencephalography (EEG) signal classification is a challenging task due to the low signal-to-noise ratio and the usual presence of artifacts from different sources. Different classification techniques, which are usually based on a predefined set of features extracted from the EEG band power distribution profile, have been previously proposed. However, the classification of EEG still remains a challenge, depending on the experimental conditions and the responses to be captured. In this context, the use of deep neural networks offers new opportunities to improve the classification performance without the use of a predefined set of features. Nevertheless, Deep Learning architectures include a vast number of hyperparameters on which the performance of the model relies. In this paper, we propose a method for optimizing Deep Learning models, not only the hyperparameters, but also their structure, which is able to propose solutions that consist of different architectures due to different layer combinations. The experimental results corroborate that deep architectures optimized by our method outperform the baseline approaches and result in computationally efficient models. Moreover, we demonstrate that optimized architectures improve the energy efficiency with respect to the baseline models.
format Online
Article
Text
id pubmed-8002580
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-80025802021-03-28 Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms Aquino-Brítez, Diego Ortiz, Andrés Ortega, Julio León, Javier Formoso, Marco Gan, John Q. Escobar, Juan José Sensors (Basel) Article Electroencephalography (EEG) signal classification is a challenging task due to the low signal-to-noise ratio and the usual presence of artifacts from different sources. Different classification techniques, which are usually based on a predefined set of features extracted from the EEG band power distribution profile, have been previously proposed. However, the classification of EEG still remains a challenge, depending on the experimental conditions and the responses to be captured. In this context, the use of deep neural networks offers new opportunities to improve the classification performance without the use of a predefined set of features. Nevertheless, Deep Learning architectures include a vast number of hyperparameters on which the performance of the model relies. In this paper, we propose a method for optimizing Deep Learning models, not only the hyperparameters, but also their structure, which is able to propose solutions that consist of different architectures due to different layer combinations. The experimental results corroborate that deep architectures optimized by our method outperform the baseline approaches and result in computationally efficient models. Moreover, we demonstrate that optimized architectures improve the energy efficiency with respect to the baseline models. MDPI 2021-03-17 /pmc/articles/PMC8002580/ /pubmed/33802684 http://dx.doi.org/10.3390/s21062096 Text en © 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Aquino-Brítez, Diego
Ortiz, Andrés
Ortega, Julio
León, Javier
Formoso, Marco
Gan, John Q.
Escobar, Juan José
Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms
title Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms
title_full Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms
title_fullStr Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms
title_full_unstemmed Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms
title_short Optimization of Deep Architectures for EEG Signal Classification: An AutoML Approach Using Evolutionary Algorithms
title_sort optimization of deep architectures for eeg signal classification: an automl approach using evolutionary algorithms
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8002580/
https://www.ncbi.nlm.nih.gov/pubmed/33802684
http://dx.doi.org/10.3390/s21062096
work_keys_str_mv AT aquinobritezdiego optimizationofdeeparchitecturesforeegsignalclassificationanautomlapproachusingevolutionaryalgorithms
AT ortizandres optimizationofdeeparchitecturesforeegsignalclassificationanautomlapproachusingevolutionaryalgorithms
AT ortegajulio optimizationofdeeparchitecturesforeegsignalclassificationanautomlapproachusingevolutionaryalgorithms
AT leonjavier optimizationofdeeparchitecturesforeegsignalclassificationanautomlapproachusingevolutionaryalgorithms
AT formosomarco optimizationofdeeparchitecturesforeegsignalclassificationanautomlapproachusingevolutionaryalgorithms
AT ganjohnq optimizationofdeeparchitecturesforeegsignalclassificationanautomlapproachusingevolutionaryalgorithms
AT escobarjuanjose optimizationofdeeparchitecturesforeegsignalclassificationanautomlapproachusingevolutionaryalgorithms