Cargando…

Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network

Among electroencephalogram (EEG) signal emotion recognition methods based on deep learning, most methods have difficulty in using a high-quality model due to the low resolution and the small sample size of EEG images. To solve this problem, this study proposes a deep network model based on dynamic e...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhu, Meili, Wang, Qingqing, Luo, Jianglin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8900638/
https://www.ncbi.nlm.nih.gov/pubmed/35264939
http://dx.doi.org/10.3389/fncom.2021.741086
_version_ 1784664164627644416
author Zhu, Meili
Wang, Qingqing
Luo, Jianglin
author_facet Zhu, Meili
Wang, Qingqing
Luo, Jianglin
author_sort Zhu, Meili
collection PubMed
description Among electroencephalogram (EEG) signal emotion recognition methods based on deep learning, most methods have difficulty in using a high-quality model due to the low resolution and the small sample size of EEG images. To solve this problem, this study proposes a deep network model based on dynamic energy features. In this method, first, to reduce the noise superposition caused by feature analysis and extraction, the concept of an energy sequence is proposed. Second, to obtain the feature set reflecting the time persistence and multicomponent complexity of EEG signals, the construction method of the dynamic energy feature set is given. Finally, to make the network model suitable for small datasets, we used fully connected layers and bidirectional long short-term memory (Bi-LSTM) networks. To verify the effectiveness of the proposed method, we used leave one subject out (LOSO) and 10-fold cross validation (CV) strategies to carry out experiments on the SEED and DEAP datasets. The experimental results show that the accuracy of the proposed method can reach 89.42% (SEED) and 77.34% (DEAP).
format Online
Article
Text
id pubmed-8900638
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-89006382022-03-08 Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network Zhu, Meili Wang, Qingqing Luo, Jianglin Front Comput Neurosci Neuroscience Among electroencephalogram (EEG) signal emotion recognition methods based on deep learning, most methods have difficulty in using a high-quality model due to the low resolution and the small sample size of EEG images. To solve this problem, this study proposes a deep network model based on dynamic energy features. In this method, first, to reduce the noise superposition caused by feature analysis and extraction, the concept of an energy sequence is proposed. Second, to obtain the feature set reflecting the time persistence and multicomponent complexity of EEG signals, the construction method of the dynamic energy feature set is given. Finally, to make the network model suitable for small datasets, we used fully connected layers and bidirectional long short-term memory (Bi-LSTM) networks. To verify the effectiveness of the proposed method, we used leave one subject out (LOSO) and 10-fold cross validation (CV) strategies to carry out experiments on the SEED and DEAP datasets. The experimental results show that the accuracy of the proposed method can reach 89.42% (SEED) and 77.34% (DEAP). Frontiers Media S.A. 2022-02-21 /pmc/articles/PMC8900638/ /pubmed/35264939 http://dx.doi.org/10.3389/fncom.2021.741086 Text en Copyright © 2022 Zhu, Wang and Luo. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Zhu, Meili
Wang, Qingqing
Luo, Jianglin
Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network
title Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network
title_full Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network
title_fullStr Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network
title_full_unstemmed Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network
title_short Emotion Recognition Based on Dynamic Energy Features Using a Bi-LSTM Network
title_sort emotion recognition based on dynamic energy features using a bi-lstm network
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8900638/
https://www.ncbi.nlm.nih.gov/pubmed/35264939
http://dx.doi.org/10.3389/fncom.2021.741086
work_keys_str_mv AT zhumeili emotionrecognitionbasedondynamicenergyfeaturesusingabilstmnetwork
AT wangqingqing emotionrecognitionbasedondynamicenergyfeaturesusingabilstmnetwork
AT luojianglin emotionrecognitionbasedondynamicenergyfeaturesusingabilstmnetwork