Cargando…

EEG-Based Emotion Classification Using Improved Cross-Connected Convolutional Neural Network

The use of electroencephalography to recognize human emotions is a key technology for advancing human–computer interactions. This study proposes an improved deep convolutional neural network model for emotion classification using a non-end-to-end training method that combines bottom-, middle-, and t...

Descripción completa

Detalles Bibliográficos
Autores principales: Dai, Jinxiao, Xi, Xugang, Li, Ge, Wang, Ting
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9394254/
https://www.ncbi.nlm.nih.gov/pubmed/35892418
http://dx.doi.org/10.3390/brainsci12080977
_version_ 1784771447561912320
author Dai, Jinxiao
Xi, Xugang
Li, Ge
Wang, Ting
author_facet Dai, Jinxiao
Xi, Xugang
Li, Ge
Wang, Ting
author_sort Dai, Jinxiao
collection PubMed
description The use of electroencephalography to recognize human emotions is a key technology for advancing human–computer interactions. This study proposes an improved deep convolutional neural network model for emotion classification using a non-end-to-end training method that combines bottom-, middle-, and top-layer convolution features. Four sets of experiments using 4500 samples were conducted to verify model performance. Simultaneously, feature visualization technology was used to extract the three-layer features obtained by the model, and a scatterplot analysis was performed. The proposed model achieved a very high accuracy of 93.7%, and the extracted features exhibited the best separability among the tested models. We found that adding redundant layers did not improve model performance, and removing the data of specific channels did not significantly reduce the classification effect of the model. These results indicate that the proposed model allows for emotion recognition with a higher accuracy and speed than the previously reported models. We believe that our approach can be implemented in various applications that require the quick and accurate identification of human emotions.
format Online
Article
Text
id pubmed-9394254
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93942542022-08-23 EEG-Based Emotion Classification Using Improved Cross-Connected Convolutional Neural Network Dai, Jinxiao Xi, Xugang Li, Ge Wang, Ting Brain Sci Article The use of electroencephalography to recognize human emotions is a key technology for advancing human–computer interactions. This study proposes an improved deep convolutional neural network model for emotion classification using a non-end-to-end training method that combines bottom-, middle-, and top-layer convolution features. Four sets of experiments using 4500 samples were conducted to verify model performance. Simultaneously, feature visualization technology was used to extract the three-layer features obtained by the model, and a scatterplot analysis was performed. The proposed model achieved a very high accuracy of 93.7%, and the extracted features exhibited the best separability among the tested models. We found that adding redundant layers did not improve model performance, and removing the data of specific channels did not significantly reduce the classification effect of the model. These results indicate that the proposed model allows for emotion recognition with a higher accuracy and speed than the previously reported models. We believe that our approach can be implemented in various applications that require the quick and accurate identification of human emotions. MDPI 2022-07-24 /pmc/articles/PMC9394254/ /pubmed/35892418 http://dx.doi.org/10.3390/brainsci12080977 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/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 (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Dai, Jinxiao
Xi, Xugang
Li, Ge
Wang, Ting
EEG-Based Emotion Classification Using Improved Cross-Connected Convolutional Neural Network
title EEG-Based Emotion Classification Using Improved Cross-Connected Convolutional Neural Network
title_full EEG-Based Emotion Classification Using Improved Cross-Connected Convolutional Neural Network
title_fullStr EEG-Based Emotion Classification Using Improved Cross-Connected Convolutional Neural Network
title_full_unstemmed EEG-Based Emotion Classification Using Improved Cross-Connected Convolutional Neural Network
title_short EEG-Based Emotion Classification Using Improved Cross-Connected Convolutional Neural Network
title_sort eeg-based emotion classification using improved cross-connected convolutional neural network
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9394254/
https://www.ncbi.nlm.nih.gov/pubmed/35892418
http://dx.doi.org/10.3390/brainsci12080977
work_keys_str_mv AT daijinxiao eegbasedemotionclassificationusingimprovedcrossconnectedconvolutionalneuralnetwork
AT xixugang eegbasedemotionclassificationusingimprovedcrossconnectedconvolutionalneuralnetwork
AT lige eegbasedemotionclassificationusingimprovedcrossconnectedconvolutionalneuralnetwork
AT wangting eegbasedemotionclassificationusingimprovedcrossconnectedconvolutionalneuralnetwork