Deep feature pyramid network for EEG emotion recognition

Hou, F; Gao, Q; Song, Y; Wang, Z; Bai, Z; Yang, Y; Tian, Z

Deep feature pyramid network for EEG emotion recognition

Hou, F Gao, Q Song, Y Wang, Z Bai, Z Yang, Y

Tian, Z

Permalink

Publisher:: ELSEVIER SCI LTD
Publication Type:: Journal Article
Citation:: Measurement: Journal of the International Measurement Confederation, 2022, 201
Issue Date:: 2022-09-30

Closed Access

	Filename	Description	Size
	Deep feature pyramid network for EEG emotion recognition.pdf	Published version	7.98 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Hou, F
dc.contributor.author	Gao, Q
dc.contributor.author	Song, Y
dc.contributor.author	Wang, Z
dc.contributor.author	Bai, Z
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.contributor.author	Tian, Z
dc.date.accessioned	2023-03-21T03:22:35Z
dc.date.available	2023-03-21T03:22:35Z
dc.date.issued	2022-09-30
dc.identifier.citation	Measurement: Journal of the International Measurement Confederation, 2022, 201
dc.identifier.issn	0263-2241
dc.identifier.issn	1873-412X
dc.identifier.uri	http://hdl.handle.net/10453/167935
dc.description.abstract	In this work, the Feature Pyramid Network (FPN) is proposed for improving the performance of electroencephalography (EEG) emotion recognition. Differential Entropy (DE) is extracted from each EEG channel as the basic feature. Then the feature matrix was constructed through biharmonic spline interpolation to obtain the correlation information between EEG channels. Next, the proposed FPN is applied to fuse multiscale EEG spatial information for obtaining deeper semantic features. FPN integrates the semantic information of low-level and high-level feature maps through up-sampling and lateral connections. It can reduce the semantic gap between feature maps and increase the receptive field of low-resolution feature maps. Finally, a linear Support Vector Machine (SVM) is utilized for emotion recognition. The experiment results of the proposed method have a state-of-the-art performance of valence (94.29%) and arousal (96.97%) by 70–30 cross-validation on the Database for Emotion Analysis using Physiological Signals (DEAP). And the accuracy of 97.12% was obtained on the SJTU Emotion EEG Dataset (SEED). Moreover, we carried out the LOSO CV experiment on DEAP. The accuracy of valence and arousal reached 80.38% and 82.33%, respectively.
dc.language	English
dc.publisher	ELSEVIER SCI LTD
dc.relation.ispartof	Measurement: Journal of the International Measurement Confederation
dc.relation.isbasedon	10.1016/j.measurement.2022.111724
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0102 Applied Mathematics, 0801 Artificial Intelligence and Image Processing, 0913 Mechanical Engineering
dc.subject.classification	Electrical & Electronic Engineering
dc.title	Deep feature pyramid network for EEG emotion recognition
dc.type	Journal Article
utslib.citation.volume	201
utslib.for	0102 Applied Mathematics
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0913 Mechanical Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-21T03:22:33Z
pubs.publication-status	Published
pubs.volume	201

Abstract:

In this work, the Feature Pyramid Network (FPN) is proposed for improving the performance of electroencephalography (EEG) emotion recognition. Differential Entropy (DE) is extracted from each EEG channel as the basic feature. Then the feature matrix was constructed through biharmonic spline interpolation to obtain the correlation information between EEG channels. Next, the proposed FPN is applied to fuse multiscale EEG spatial information for obtaining deeper semantic features. FPN integrates the semantic information of low-level and high-level feature maps through up-sampling and lateral connections. It can reduce the semantic gap between feature maps and increase the receptive field of low-resolution feature maps. Finally, a linear Support Vector Machine (SVM) is utilized for emotion recognition. The experiment results of the proposed method have a state-of-the-art performance of valence (94.29%) and arousal (96.97%) by 70–30 cross-validation on the Database for Emotion Analysis using Physiological Signals (DEAP). And the accuracy of 97.12% was obtained on the SJTU Emotion EEG Dataset (SEED). Moreover, we carried out the LOSO CV experiment on DEAP. The accuracy of valence and arousal reached 80.38% and 82.33%, respectively.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/167935