Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study

In this paper, we present a method to improve emotion recognition based on the fusion of local cortical activations and dynamic functional network patterns. We estimate the cortical activations using power spectral density (PSD) with the Burg autoregressive model. On the other hand, we estimate the...

Full description

Saved in:
Bibliographic Details
Main Author: Yahya, Fares (author)
Other Authors: Tariq, Usman (author), Alex, Meera (author), Mir, Hasan (author), Al-Nashash, Hasan (author)
Format: article
Published: 2019
Subjects:
Online Access:http://hdl.handle.net/11073/16599
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513436641132544
author Yahya, Fares
author2 Tariq, Usman
Alex, Meera
Mir, Hasan
Al-Nashash, Hasan
author2_role author
author
author
author
author_facet Yahya, Fares
Tariq, Usman
Alex, Meera
Mir, Hasan
Al-Nashash, Hasan
author_role author
dc.creator.none.fl_str_mv Yahya, Fares
Tariq, Usman
Alex, Meera
Mir, Hasan
Al-Nashash, Hasan
dc.date.none.fl_str_mv 2019
2020-02-16T07:51:34Z
2020-02-16T07:51:34Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv F. Al-Shargie, U. Tariq, M. Alex, H. Mir and H. Al-Nashash, "Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study," in IEEE Access, vol. 7, pp. 143550-143562, 2019.
2169-3536
http://hdl.handle.net/11073/16599
10.1109/ACCESS.2019.2944008
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv IEEE Xplore Digital Library
dc.relation.none.fl_str_mv https://doi.org/10.1109/ACCESS.2019.2944008
dc.subject.none.fl_str_mv Emotion
Cortical activation
Functional connectivity network patterns
Fusion
Classification
Electroencephalogram (EEG)
dc.title.none.fl_str_mv Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description In this paper, we present a method to improve emotion recognition based on the fusion of local cortical activations and dynamic functional network patterns. We estimate the cortical activations using power spectral density (PSD) with the Burg autoregressive model. On the other hand, we estimate the functional connectivity networks by utilizing the phase locking value (PLV). The results of cortical activations and connectivity networks show different patterns across three emotions at all frequency bands. Similarly, the results of fusion significantly improve the classification rate in terms of accuracy, sensitivity, specificity and the area under the receiver operator characteristics curve (AROC), p < 0:05. The average improvement with fusion in all evaluation metrics are 6.84% and 4.1% when compared to PSD and PLV alone, respectively. The results clearly demonstrate the advantage of fusion of cortical activations with dynamic functional networks for developing human-computer interaction system in real-world applications.
format article
id aus_d1ff21f33807a2f959601fb4bb27ca00
identifier_str_mv F. Al-Shargie, U. Tariq, M. Alex, H. Mir and H. Al-Nashash, "Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study," in IEEE Access, vol. 7, pp. 143550-143562, 2019.
2169-3536
10.1109/ACCESS.2019.2944008
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/16599
publishDate 2019
publisher.none.fl_str_mv IEEE Xplore Digital Library
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG StudyYahya, FaresTariq, UsmanAlex, MeeraMir, HasanAl-Nashash, HasanEmotionCortical activationFunctional connectivity network patternsFusionClassificationElectroencephalogram (EEG)In this paper, we present a method to improve emotion recognition based on the fusion of local cortical activations and dynamic functional network patterns. We estimate the cortical activations using power spectral density (PSD) with the Burg autoregressive model. On the other hand, we estimate the functional connectivity networks by utilizing the phase locking value (PLV). The results of cortical activations and connectivity networks show different patterns across three emotions at all frequency bands. Similarly, the results of fusion significantly improve the classification rate in terms of accuracy, sensitivity, specificity and the area under the receiver operator characteristics curve (AROC), p < 0:05. The average improvement with fusion in all evaluation metrics are 6.84% and 4.1% when compared to PSD and PLV alone, respectively. The results clearly demonstrate the advantage of fusion of cortical activations with dynamic functional networks for developing human-computer interaction system in real-world applications.IEEE Xplore Digital Library2020-02-16T07:51:34Z2020-02-16T07:51:34Z2019Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfF. Al-Shargie, U. Tariq, M. Alex, H. Mir and H. Al-Nashash, "Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study," in IEEE Access, vol. 7, pp. 143550-143562, 2019.2169-3536http://hdl.handle.net/11073/1659910.1109/ACCESS.2019.2944008en_UShttps://doi.org/10.1109/ACCESS.2019.2944008oai:repository.aus.edu:11073/165992024-08-22T12:08:38Z
spellingShingle Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study
Yahya, Fares
Emotion
Cortical activation
Functional connectivity network patterns
Fusion
Classification
Electroencephalogram (EEG)
status_str publishedVersion
title Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study
title_full Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study
title_fullStr Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study
title_full_unstemmed Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study
title_short Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study
title_sort Emotion Recognition Based on Fusion of Local Cortical Activations and Dynamic Functional Networks Connectivity: An EEG Study
topic Emotion
Cortical activation
Functional connectivity network patterns
Fusion
Classification
Electroencephalogram (EEG)
url http://hdl.handle.net/11073/16599