No Cover Image

Journal article 822 views 127 downloads

EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder

Junxiu Liu, Guopei Wu, Yuling Luo, Senhui Qiu, Scott Yang Orcid Logo, Wei Li, Yifei Bi

Frontiers in Systems Neuroscience, Volume: 14

Swansea University Author: Scott Yang Orcid Logo

  • 58945.pdf

    PDF | Version of Record

    © 2020 Liu, Wu, Luo, Qiu, Yang, Li and Bi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY)

    Download (2.44MB)

Check full text

DOI (Published version): 10.3389/fnsys.2020.00043

Abstract

Emotion classification based on brain–computer interface (BCI) systems is an appealing research topic. Recently, deep learning has been employed for the emotion classifications of BCI systems and compared to traditional classification methods improved results have been obtained. In this paper, a nov...

Full description

Published in: Frontiers in Systems Neuroscience
ISSN: 1662-5137
Published: Frontiers Media SA 2020
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa58945
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2021-12-07T09:57:12Z
last_indexed 2021-12-31T04:28:59Z
id cronfa58945
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2021-12-30T13:31:33.7168961</datestamp><bib-version>v2</bib-version><id>58945</id><entry>2021-12-07</entry><title>EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder</title><swanseaauthors><author><sid>81dc663ca0e68c60908d35b1d2ec3a9b</sid><ORCID>0000-0002-6618-7483</ORCID><firstname>Scott</firstname><surname>Yang</surname><name>Scott Yang</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2021-12-07</date><deptcode>SCS</deptcode><abstract>Emotion classification based on brain&#x2013;computer interface (BCI) systems is an appealing research topic. Recently, deep learning has been employed for the emotion classifications of BCI systems and compared to traditional classification methods improved results have been obtained. In this paper, a novel deep neural network is proposed for emotion classification using EEG systems, which combines the Convolutional Neural Network (CNN), Sparse Autoencoder (SAE), and Deep Neural Network (DNN) together. In the proposed network, the features extracted by the CNN are first sent to SAE for encoding and decoding. Then the data with reduced redundancy are used as the input features of a DNN for classification task. The public datasets of DEAP and SEED are used for testing. Experimental results show that the proposed network is more effective than conventional CNN methods on the emotion recognitions. For the DEAP dataset, the highest recognition accuracies of 89.49% and 92.86% are achieved for valence and arousal, respectively. For the SEED dataset, however, the best recognition accuracy reaches 96.77%. By combining the CNN, SAE, and DNN and training them separately, the proposed network is shown as an efficient method with a faster convergence than the conventional CNN.</abstract><type>Journal Article</type><journal>Frontiers in Systems Neuroscience</journal><volume>14</volume><journalNumber/><paginationStart/><paginationEnd/><publisher>Frontiers Media SA</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic>1662-5137</issnElectronic><keywords>EEG, emotion recognition, convolutional neural network, sparse autoencoder, deep neural network</keywords><publishedDay>2</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2020</publishedYear><publishedDate>2020-09-02</publishedDate><doi>10.3389/fnsys.2020.00043</doi><url/><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders>National Natural Science Foundation of China under Grant 61976063, the funding of Overseas 100 Talents Program of Guangxi Higher Education, research funds of Diecai Project of Guangxi Normal Univesity, Guangxi Key Lab of Multi-source Information Mining and Security (19-A-03-02) and Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing, the Young and Middle-aged Teachers&#x2019; Research Ability Improvement Project in Guangxi Universities under Grant 2020KY02030, and the Innovation Project of Guangxi Graduate Education under Grant YCSW2020102</funders><lastEdited>2021-12-30T13:31:33.7168961</lastEdited><Created>2021-12-07T09:56:39.5414656</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Junxiu</firstname><surname>Liu</surname><order>1</order></author><author><firstname>Guopei</firstname><surname>Wu</surname><order>2</order></author><author><firstname>Yuling</firstname><surname>Luo</surname><order>3</order></author><author><firstname>Senhui</firstname><surname>Qiu</surname><order>4</order></author><author><firstname>Scott</firstname><surname>Yang</surname><orcid>0000-0002-6618-7483</orcid><order>5</order></author><author><firstname>Wei</firstname><surname>Li</surname><order>6</order></author><author><firstname>Yifei</firstname><surname>Bi</surname><order>7</order></author></authors><documents><document><filename>58945__21965__1d167fd271664a82ae6daf656d49604e.pdf</filename><originalFilename>58945.pdf</originalFilename><uploaded>2021-12-30T13:30:37.5899273</uploaded><type>Output</type><contentLength>2556829</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>&#xA9; 2020 Liu, Wu, Luo, Qiu, Yang, Li and Bi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY)</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>http://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling 2021-12-30T13:31:33.7168961 v2 58945 2021-12-07 EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder 81dc663ca0e68c60908d35b1d2ec3a9b 0000-0002-6618-7483 Scott Yang Scott Yang true false 2021-12-07 SCS Emotion classification based on brain–computer interface (BCI) systems is an appealing research topic. Recently, deep learning has been employed for the emotion classifications of BCI systems and compared to traditional classification methods improved results have been obtained. In this paper, a novel deep neural network is proposed for emotion classification using EEG systems, which combines the Convolutional Neural Network (CNN), Sparse Autoencoder (SAE), and Deep Neural Network (DNN) together. In the proposed network, the features extracted by the CNN are first sent to SAE for encoding and decoding. Then the data with reduced redundancy are used as the input features of a DNN for classification task. The public datasets of DEAP and SEED are used for testing. Experimental results show that the proposed network is more effective than conventional CNN methods on the emotion recognitions. For the DEAP dataset, the highest recognition accuracies of 89.49% and 92.86% are achieved for valence and arousal, respectively. For the SEED dataset, however, the best recognition accuracy reaches 96.77%. By combining the CNN, SAE, and DNN and training them separately, the proposed network is shown as an efficient method with a faster convergence than the conventional CNN. Journal Article Frontiers in Systems Neuroscience 14 Frontiers Media SA 1662-5137 EEG, emotion recognition, convolutional neural network, sparse autoencoder, deep neural network 2 9 2020 2020-09-02 10.3389/fnsys.2020.00043 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University National Natural Science Foundation of China under Grant 61976063, the funding of Overseas 100 Talents Program of Guangxi Higher Education, research funds of Diecai Project of Guangxi Normal Univesity, Guangxi Key Lab of Multi-source Information Mining and Security (19-A-03-02) and Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing, the Young and Middle-aged Teachers’ Research Ability Improvement Project in Guangxi Universities under Grant 2020KY02030, and the Innovation Project of Guangxi Graduate Education under Grant YCSW2020102 2021-12-30T13:31:33.7168961 2021-12-07T09:56:39.5414656 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Junxiu Liu 1 Guopei Wu 2 Yuling Luo 3 Senhui Qiu 4 Scott Yang 0000-0002-6618-7483 5 Wei Li 6 Yifei Bi 7 58945__21965__1d167fd271664a82ae6daf656d49604e.pdf 58945.pdf 2021-12-30T13:30:37.5899273 Output 2556829 application/pdf Version of Record true © 2020 Liu, Wu, Luo, Qiu, Yang, Li and Bi. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) true eng http://creativecommons.org/licenses/by/4.0/
title EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder
spellingShingle EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder
Scott Yang
title_short EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder
title_full EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder
title_fullStr EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder
title_full_unstemmed EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder
title_sort EEG-Based Emotion Classification Using a Deep Neural Network and Sparse Autoencoder
author_id_str_mv 81dc663ca0e68c60908d35b1d2ec3a9b
author_id_fullname_str_mv 81dc663ca0e68c60908d35b1d2ec3a9b_***_Scott Yang
author Scott Yang
author2 Junxiu Liu
Guopei Wu
Yuling Luo
Senhui Qiu
Scott Yang
Wei Li
Yifei Bi
format Journal article
container_title Frontiers in Systems Neuroscience
container_volume 14
publishDate 2020
institution Swansea University
issn 1662-5137
doi_str_mv 10.3389/fnsys.2020.00043
publisher Frontiers Media SA
college_str Faculty of Science and Engineering
hierarchytype
hierarchy_top_id facultyofscienceandengineering
hierarchy_top_title Faculty of Science and Engineering
hierarchy_parent_id facultyofscienceandengineering
hierarchy_parent_title Faculty of Science and Engineering
department_str School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str 1
active_str 0
description Emotion classification based on brain–computer interface (BCI) systems is an appealing research topic. Recently, deep learning has been employed for the emotion classifications of BCI systems and compared to traditional classification methods improved results have been obtained. In this paper, a novel deep neural network is proposed for emotion classification using EEG systems, which combines the Convolutional Neural Network (CNN), Sparse Autoencoder (SAE), and Deep Neural Network (DNN) together. In the proposed network, the features extracted by the CNN are first sent to SAE for encoding and decoding. Then the data with reduced redundancy are used as the input features of a DNN for classification task. The public datasets of DEAP and SEED are used for testing. Experimental results show that the proposed network is more effective than conventional CNN methods on the emotion recognitions. For the DEAP dataset, the highest recognition accuracies of 89.49% and 92.86% are achieved for valence and arousal, respectively. For the SEED dataset, however, the best recognition accuracy reaches 96.77%. By combining the CNN, SAE, and DNN and training them separately, the proposed network is shown as an efficient method with a faster convergence than the conventional CNN.
published_date 2020-09-02T04:15:52Z
_version_ 1763754065376837632
score 11.037166

Similar Items