Emotion Recognition Based on a EEG–fNIRS Hybrid Brain Network in the Source Space

<b>Background/Objectives</b>: Studies have shown that emotion recognition based on electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) multimodal physiological signals exhibits superior performance compared to that of unimodal approaches. Nonetheless, there remai...

Full description

Saved in:
Bibliographic Details
Main Authors: Mingxing Hou, Xueying Zhang, Guijun Chen, Lixia Huang, Ying Sun
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Brain Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3425/14/12/1166
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846105503677022208
author Mingxing Hou
Xueying Zhang
Guijun Chen
Lixia Huang
Ying Sun
author_facet Mingxing Hou
Xueying Zhang
Guijun Chen
Lixia Huang
Ying Sun
author_sort Mingxing Hou
collection DOAJ
description <b>Background/Objectives</b>: Studies have shown that emotion recognition based on electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) multimodal physiological signals exhibits superior performance compared to that of unimodal approaches. Nonetheless, there remains a paucity of in-depth investigations analyzing the inherent relationship between EEG and fNIRS and constructing brain networks to improve the performance of emotion recognition. <b>Methods</b>: In this study, we introduce an innovative method to construct hybrid brain networks in the source space based on simultaneous EEG-fNIRS signals for emotion recognition. Specifically, we perform source localization on EEG signals to derive the EEG source signals. Subsequently, causal brain networks are established in the source space by analyzing the Granger causality between the EEG source signals, while coupled brain networks in the source space are formed by assessing the coupling strength between the EEG source signals and the fNIRS signals. The resultant causal brain networks and coupled brain networks are integrated to create hybrid brain networks in the source space, which serve as features for emotion recognition. <b>Results</b>: The effectiveness of our proposed method is validated on multiple emotion datasets. The experimental results indicate that the recognition performance of our approach significantly surpasses that of the baseline method. <b>Conclusions</b>: This work offers a novel perspective on the fusion of EEG and fNIRS signals in an emotion-evoked experimental paradigm and provides a feasible solution for enhancing emotion recognition performance.
format Article
id doaj-art-843c9d13c76e4277a7d73160c725b890
institution Kabale University
issn 2076-3425
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Brain Sciences
spelling doaj-art-843c9d13c76e4277a7d73160c725b8902024-12-27T14:14:39ZengMDPI AGBrain Sciences2076-34252024-11-011412116610.3390/brainsci14121166Emotion Recognition Based on a EEG–fNIRS Hybrid Brain Network in the Source SpaceMingxing Hou0Xueying Zhang1Guijun Chen2Lixia Huang3Ying Sun4College of Integrated Circuits, Taiyuan University of Technology, Taiyuan 030600, ChinaCollege of Electronic Information Engineering, Taiyuan University of Technology, Taiyuan 030600, ChinaCollege of Electronic Information Engineering, Taiyuan University of Technology, Taiyuan 030600, ChinaCollege of Electronic Information Engineering, Taiyuan University of Technology, Taiyuan 030600, ChinaCollege of Electronic Information Engineering, Taiyuan University of Technology, Taiyuan 030600, China<b>Background/Objectives</b>: Studies have shown that emotion recognition based on electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) multimodal physiological signals exhibits superior performance compared to that of unimodal approaches. Nonetheless, there remains a paucity of in-depth investigations analyzing the inherent relationship between EEG and fNIRS and constructing brain networks to improve the performance of emotion recognition. <b>Methods</b>: In this study, we introduce an innovative method to construct hybrid brain networks in the source space based on simultaneous EEG-fNIRS signals for emotion recognition. Specifically, we perform source localization on EEG signals to derive the EEG source signals. Subsequently, causal brain networks are established in the source space by analyzing the Granger causality between the EEG source signals, while coupled brain networks in the source space are formed by assessing the coupling strength between the EEG source signals and the fNIRS signals. The resultant causal brain networks and coupled brain networks are integrated to create hybrid brain networks in the source space, which serve as features for emotion recognition. <b>Results</b>: The effectiveness of our proposed method is validated on multiple emotion datasets. The experimental results indicate that the recognition performance of our approach significantly surpasses that of the baseline method. <b>Conclusions</b>: This work offers a novel perspective on the fusion of EEG and fNIRS signals in an emotion-evoked experimental paradigm and provides a feasible solution for enhancing emotion recognition performance.https://www.mdpi.com/2076-3425/14/12/1166emotion recognitionEEG–fNIRSsource spacebrain network
spellingShingle Mingxing Hou
Xueying Zhang
Guijun Chen
Lixia Huang
Ying Sun
Emotion Recognition Based on a EEG–fNIRS Hybrid Brain Network in the Source Space
Brain Sciences
emotion recognition
EEG–fNIRS
source space
brain network
title Emotion Recognition Based on a EEG–fNIRS Hybrid Brain Network in the Source Space
title_full Emotion Recognition Based on a EEG–fNIRS Hybrid Brain Network in the Source Space
title_fullStr Emotion Recognition Based on a EEG–fNIRS Hybrid Brain Network in the Source Space
title_full_unstemmed Emotion Recognition Based on a EEG–fNIRS Hybrid Brain Network in the Source Space
title_short Emotion Recognition Based on a EEG–fNIRS Hybrid Brain Network in the Source Space
title_sort emotion recognition based on a eeg fnirs hybrid brain network in the source space
topic emotion recognition
EEG–fNIRS
source space
brain network
url https://www.mdpi.com/2076-3425/14/12/1166
work_keys_str_mv AT mingxinghou emotionrecognitionbasedonaeegfnirshybridbrainnetworkinthesourcespace
AT xueyingzhang emotionrecognitionbasedonaeegfnirshybridbrainnetworkinthesourcespace
AT guijunchen emotionrecognitionbasedonaeegfnirshybridbrainnetworkinthesourcespace
AT lixiahuang emotionrecognitionbasedonaeegfnirshybridbrainnetworkinthesourcespace
AT yingsun emotionrecognitionbasedonaeegfnirshybridbrainnetworkinthesourcespace