基于脑电功能连接微状态的情绪状态解码

doi:10.11959/j.issn.2096-6652.202105

Abstract

Abstract:

Emotional state decoding based on electroencephalography (EEG) usually regards individual emotion as a relatively static state and uses spectral power or inter-channel correlations of EEG as features.Based on recent advancement of dynamic functional connectivity analysis in the area of network neuroscience, a method called microstates of functional connectivity was designed and implemented, which clustered the inter-regional functional connectivity patterns of the brain under different emotional states to obtain representative microstates, and the temporal statistics, such as coverage and transition probability were extracted as features for emotional state decoding.Based on a widely used publicly available EEG dataset DEAP, new features in microstates of dynamic functional connectivity analysis achieved regression mean squared errors of 3.87±0.28 and 3.25±0.30 on valence and arousal respectively, which were better than those using traditional spectral power features, 4.07±0.30 (p=0.005) and 3.41±0.31 (p=0.064).The results demonstrate the feasibility of emotional state decoding based on microstates of functional connectivity and provide deeper insight into understanding the neural mechanisms of emotion.

Key words: dynamic functional connectivity, microstate, emotional state decoding, electroencephalography

CLC Number:

R318

Xinke SHEN, Yichao LI, Jin LIU, et al. Emotional state decoding using EEG-based microstates of functional connectivity[J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(1): 49-58.

Figures/Tables 7

References 34

[35]	REINEN J M , CHéN O Y , HUTCHISON R M ,et al. The human cortex possesses a reconfigurable dynamic network architecture that is disrupted in psychosis[J]. Nature Communications, 2018,9(1): 1-15.
[36]	STAM C J , NOLTE G , DAFFERTSHOFER A J . Phase lag index:assessment of functional connectivity from multi channel EEG and MEG with diminished bias from common sources[J]. Human Brain Mapping, 2007,28(11): 1178-1193.
[1]	PICARD R W . Affective computing[M]. MA: MIT Press, 1997.
[2]	PORIA S , CAMBRIA E , BAJPAI R ,et al. A review of affective computing:from unimodal analysis to multimodal fusion[J]. Information Fusion, 2017,37: 98-125.
[3]	HU X , CHEN J J , WANG F ,et al. Ten challenges for EEG-based affective computing[J]. Brain Science Advances, 2019,5(1): 1-20.
[4]	DING Y , HU X , XIA Z Y ,et al. Inter-brain EEG feature extraction and analysis for continuous implicit emotion tagging during video watching[J]. IEEE Transactions on Affective Computing, 2018,12(1): 92-102.
[5]	HU X , YU J W , SONG M D ,et al. EEG correlates of ten positive emotions[J]. Frontiers in Human Neuroscience, 2017,11: 26.
[6]	SCHMIDT L A , TRAINOR L J . Frontal brain electrical activity (EEG) distinguishes valence and intensity of musical emotions[J]. Cognition and Emotion, 2001,15(4): 487-500.
[7]	ZHENG W L , ZHU J Y , LYU B L . Identifying stable patterns over time for emotion recognition from EEG[J]. IEEE Transactions on Affective Computing, 2017,10(3): 417-429.
[8]	PETRANTONAKIS P C , HADJILEONTIADIS L J . Emotion recognition from EEG using higher order crossings[J]. IEEE Transactions on Information Technology in Biomedicine, 2009,14(2): 186-97.
[9]	LI P Y , LIU H A , SI Y J ,et al. EEG based emotion recognition by combining functional connectivity network and local activations[J]. IEEE Transactions on Biomedical Engineering, 2019,66(10): 2869-2881.
[10]	LEE Y Y , HSIEH S . Classifying different emotional states by means of EEG-based functional connectivity patterns[J]. PLOS One, 2014,9(4): e95415.
[11]	WU X , ZHENG W L , LYU B L . Investigating EEG-based functional connectivity patterns for multimodal emotion recognition[J]. arXiv preprint, 2020,arXiv:2004.01973.
[12]	SONG T F , ZHENG W M , SONG P ,et al. EEG emotion recognition using dynamical graph convolutional neural networks[J]. IEEE Transactions on Affective Computing, 2018,11(3): 532-541.
[13]	BASSETT D S , SPORNS O . Network neuroscience[J]. Nature Neuroscience, 2017,20(3): 353-364.
[14]	O'NEILL G C , TEWARIE P , VIDAURRE D ,et al. Dynamics of large-scale electrophysiological networks:a technical review[J]. Neuroimage, 2018,180: 559-576.
[15]	LU Q , BI K , LIU C ,et al. Predicting depression based on dynamic regional connectivity:a windowed Granger causality analysis of MEG recordings[J]. Brain Research, 2013,1535: 52-60.
[16]	CETIN M S , HOUCK J M , RASHID B ,et al. Multimodal classification of schizophrenia patients with MEG and fMRI data using static and dynamic connectivity measures[J]. Frontiers in Neuroscience, 2016,10: 466.
[17]	LEE H , NOH G J , JOO P ,et al. Diversity of functional connectivity patterns is reduced in propofol-induced unconsciousness[J]. Human Brain Mapping, 2017,38(10): 4980-4995.
[18]	MCMENAMIN B W , LANGESLAG S J , SIRBU M ,et al. Network organization unfolds over time during periods of anxious anticipation[J]. Journal of Neuroscience, 2014,34(34): 11261-11273.
[19]	HERMANS E J , HENCKENS M J , JO?LS M ,et al. Dynamic adaptation of large-scale brain networks in response to acute stressors[J]. Trends in Neurosciences, 2014,37(6): 304-314.
[20]	PESSOA L , MCMENAMIN B J . Dynamic networks in the emotional brain[J]. The Neuroscientist, 2017,23(4): 383-396.
[21]	MICHEL C M , KOENIG T J . EEG microstates as a tool for studying the temporal dynamics of whole-brain neuronal networks:a review[J]. Neuroimage, 2018,180: 577-593.
[22]	LEHMANN D , FABER P L , GALDERISI S ,et al. EEG microstate duration and syntax in acute,medication-naive,first-episode schizophrenia:a multi-center study[J]. Psychiatry Research:Neuroimaging, 2005,138(2): 141-156.
[23]	AL ZOUBI O , MAYELI A , TSUCHIYAGAITO A ,et al. EEG microstates temporal dynamics differentiate individuals with mood and anxiety disorders from healthy subjects[J]. Frontiers in Human Neuroscience, 2019,13: 56.
[24]	NISHIDA K , MORISHIMA Y , YOSHIMURA M ,et al. EEG microstates associated with salience and frontoparietal networks in frontotemporal dementia,schizophrenia and Alzheimer’s disease[J]. Clinical Neurophysiology, 2013,124(6): 1106-1114.
[25]	MILZ P , FABER P L , LEHMANN D ,et al. The functional significance of EEG microstates—associations with modalities of thinking[J]. Neuroimage, 2016,125: 643-656.
[26]	DUC N T , LEE B J . Microstate functional connectivity in EEG cognitive tasks revealed by a multivariate Gaussian hidden Markov model with phase locking value[J]. Journal of Neural Engineering, 2019,16(2): 026033.
[27]	KOELSTRA S , MUHL C , SOLEYMANI M ,et al. DEAP:a database for emotion analysis; using physiological signals[J]. IEEE Transactions on Affective Computing, 2011,3(1): 18-31.
[28]	RUSSELL J A . A circumplex model of affect[J]. Journal of Personality and Social Psychology, 1980,39(6): 1161-1178.
[29]	YAN J Z , CHEN S B , DENG S N . A EEG-based emotion recognition model with rhythm and time characteristics[J]. Brain Informatics, 2019,6(1): 7.
[30]	OOSTENVELD R , FRIES P , MARIS E ,et al. FieldTrip:open source software for advanced analysis of MEG,EEG,and invasive electrophysiological data[J]. Computational Intelligence and Neuroscience, 2011: 15869.
[31]	ARTHUR D , VASSILVITSKII S . K-means++:the advantages of careful seeding[C]// Proceeding of the 8th Annual ACM-SIAM Symposium on Discrete Algorithms. New York:ACM Press, 2007.
[32]	WU W , ZHANG Y , JIANG J ,et al. An electroencephalographic signature predicts antidepressant response in major depression[J]. Nature Biotechnology, 2020,38(4): 439-447.
[33]	KATSIGIANNIS S , RAMZAN N . DREAMER:a database for emotion recognition through EEG and ECG signals from wireless low-cost off-the-shelf devices[J]. IEEE Journal of Biomedical and Health Informatics, 2017,22(1): 98-107.
[34]	SHEN X K , HU X , LIU S Z ,et al. Exploring EEG microstates for affective computing:decoding valence and arousal experiences during video watching[C]// Proceedings of the 2020 42nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway:IEEE Press, 2020: 841-846.

Metrics

Recommended 0

No Suggested Reading articles found!

被试编号	效价		唤醒
被试编号	微状态特征	频带能量特征	微状态特征	频带能量特征
1	6.09	5.75	4.31	4.44
2	7.94	7.89	8.33	8.37
3	1.87	1.87	2.22	2.20
4	4.54	5.24	3.59	3.81
5	4.67	5.18	3.48	3.62
6	1.99	1.98	1.90	2.02
7	3.53	3.62	2.96	3.38
8	3.81	3.92	1.98	2.15
9	1.81	2.02	0.90	0.95
10	3.33	3.78	1.94	1.88
11	3.72	4.25	5.18	5.35
12	4.03	4.99	2.82	2.75
13	4.92	5.18	3.37	3.78
14	4.02	4.22	2.86	2.50
15	3.19	4.60	1.82	1.89
16	3.07	3.05	3.19	3.04
17	1.60	1.64	1.32	1.86
18	1.32	1.48	1.71	1.69
19	3.10	2.78	2.98	2.86
20	2.64	2.18	1.44	1.55
21	3.34	3.40	1.60	1.66
22	5.40	5.66	3.28	3.49
23	2.95	3.04	5.69	5.91
24	4.08	4.34	2.02	2.26
25	6.06	6.41	3.24	3.38
26	6.72	7.26	5.53	5.31
27	4.26	4.64	3.74	5.90
28	6.26	6.46	6.18	6.39
29	4.32	4.73	4.41	5.60
30	1.72	1.89	1.56	1.79
31	3.99	3.49	5.88	4.98
32	3.50	3.39	2.45	2.38
平均值	3.87	4.07	3.25	3.41
标准误	0.28	0.30	0.30	0.31

Emotional state decoding using EEG-based microstates of functional connectivity

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 7

References 34

Related Articles 4

Metrics

Recommended 0

[1]	Hanbing GAO, Chi ZHANG, Mingyan JIN, Yang XIAO, Fengyu CONG. Cross-subject emotional EEG recognition based on multi-source domain adaptation [J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(1): 59-64.
[2]	Dongjun LIU, Yuhan WANG, Wenfen LING, Yong PENG, Wanzeng KONG. Emotion recognition based on brain and machine collaborative intelligence [J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(1): 65-75.
[3]	Wenfen LING, Sihan CHEN, Yong PENG, Wanzeng KONG. Multi-modal physiological signal emotion recognition based on 3D hierarchical convolution fusion [J]. Chinese Journal of Intelligent Science and Technology, 2021, 3(1): 76-84.
[4]	Shan LI,Yongchao LI,Ying ZOU,Lin YANG,Yin WANG,Zhijun YAO,Ubin H. Brain abnormalities in depression based on multimodal imaging [J]. Chinese Journal of Intelligent Science and Technology, 2020, 2(2): 116-125.