多特征融合的脑电情绪分类

doi:10.3778/j.issn.1002-8331.2110-0068

摘要/Abstract

摘要： 为进一步探究不同类型特征互补性对脑电情绪分类的影响，提出一种基于多特征融合的脑电情绪分类新方法。对预处理后的脑电信号进行DE、MST和SampEn特征提取，采用双样本T检验去除冗余筛选出最优特征并融合，采用SVM分类模型来识别不同的情绪状态。在SEED-IV数据集上的实验结果表明，单一特征中DE的平均分类准确率最高（77.86%），而融合非线性SampEn特征与功能连接MST属性后平均分类准确率得到进一步提升（84.58%），不同时间段采集的数据上重测实验则证明了该方法的有效性与稳定性。

关键词: 微分熵（DE）, 最小生成树（MST）, 样本熵（SampEn）, 多特征融合, 脑电（EEG）, 情绪分类

Abstract: In order to further explore the influence of the complementarity of different types of features on EEG emotion classification, this paper proposes a new method of EEG emotion classification based on multi-feature fusion. First, it extracts the features of DE, MST and SampEn from the pre-processed EEG signals, then uses the sample t-test to remove the redundancy to screen out the optimal features and fusion them, and finally uses the SVM classification model to identify different emotional states. The experimental results on the SEED-IV dataset show that the average classification accuracy of DE in a single feature is the highest（77.86%）, and the average classification accuracy is further improved（84.58%） after fusing the nonlinear SampEn feature and the function to connect the MST attribute. The retest experiments on the data collected in different time periods have proved the effectiveness and stability of this method.

Key words: differential entropy（DE）, minimum spanning tree（MST）, sample entropy（SampEn）, multi-feature fusion, electroencephalogram（EEG）, emotion classification

梁明晶, 王璐, 温昕, 曹锐. 多特征融合的脑电情绪分类[J]. 计算机工程与应用, 2023, 59(5): 155-159.

LIANG Mingjing, WANG Lu, WEN Xin, CAO Rui. EEG Emotion Classification Based on Multi-Feature Fusion[J]. Computer Engineering and Applications, 2023, 59(5): 155-159.

参考文献

[1] ZHENG W L，LU B L.Investigating critical frequency bands and channels for EEG-Based emotion recognition with deep neural networks[J].IEEE Transactions on Autonomous Mental Development，2015，7（3）：162-175.
[2] GUIDO G.Emotions and the right hemisphere：can new data clarify old models?[J].Neuroscientist，2018，25（3）：258-270.
[3] KELTNER D，SAUTER D，TRACY J，et al.Emotional expression：advances in basic emotion theory[J].Journal of Nonverbal Behavior，2019，43（3）：133-160.
[4] EDGAR P，TORRES E A，HERNáNDEZ-LVAREZ M，et al.EEG-based BCI emotion recognition：a survey[J].Sensors，2020，20（18）：5083-5119.
[5] PAN C，SHI C，MU H，et al.EEG-based emotion recognition using logistic regression with Gaussian kernel and Laplacian prior and investigation of critical frequency bands[J].Applied Sciences，2020，10（5）：1619-1643.
[6] PHAM T D，TRAN D，MA W，et al.Enhancing performance of EEG-based emotion recognition systems using feature smoothing[C]//International Conference on Neural Information Processing，2015：95-102.
[7] 李幼军，钟宁，黄佳进，等.基于高斯核函数支持向量机的脑电信号时频特征情感多类识别[J].北京工业大学学报，2018，44（2）：234-243.
LI Y J，ZHONG N，HUANG J J，et al.Human emotion multi-classification recognition based on the EEG time and frequency features by using a Gaussian kernel function SVM[J].Journal of Beijing University of Technology，2018，44（2）：234-243.
[8] DUAN R N，ZHU J Y，LU B L.Differential entropy feature for EEG-based emotion classification[C]//2013 6th International IEEE/EMBS Conference on Neural Engineering（NER），2013：81-84.
[9] SHI L C，JIAO Y Y，LU B L.Differential entropy feature for EEG-based vigilance estimation[C]//2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society（EMBC），2013：6627-6630.
[10] 刘双.基于融合特征的触觉情感脑电研究[D].天津：天津理工大学，2021.
LIU S.Research on tactile emotional EEG based on fusion feature[D].Tianjin：Tianjin University of Technology，2021.
[11] XIANG J，CAO R，LI L.Emotion recognition based on the sample entropy of EEG[J].Bio-medical Materials and Engineering，2014，24（1）：1185-1192.
[12] 苏建新.基于脑电信号的情绪识别研究[D].南京：南京邮电大学，2015.
SU J X.Emotion recognition research based on EEG signal[D].Nanjing：Nanjing University of Posts and Telecommu-nications，2015.
[13] FARASHI S，KHOSROWABADI R.EEG based emotion recognition using minimum spanning tree[J].Physical and Engineering Sciences in Medicine，2020，43（2）：985-996.
[14] XING M，LEE H，MORRISSEY Z，et al.Altered dynamic electroencephalography connectome phase-space features of emotion regulation in social anxiety[J].NeuroImage，2018，186（1）：338-349.
[15] ZHENG W L，LIU W，LU Y，et al.EmotionMeter：a multimodal framework for recognizing human emotions[J].IEEE Transactions on Cybernetics，2019，49（3）：1110-1122.
[16] MU L，MEMBER B.Emotion classification based on gamma-band EEG[C]//2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society，2009：1323-1326.
[17] YANG Y X，GAO Z K，WANG X M，et al.A recurrence quantification analysis-based channel-frequency convolutional neural network for emotion recognition from EEG[J].Chaos，2018，28（8）：085724.
[18] CAO R，HAO Y，WANG X，et al.EEG functional connectivity underlying emotional valance and arousal using minimum spanning trees[J].Frontiers in Neuroscience，2020，14：355-367.
[19] CHANG C C，LIN C J.LIBSVM：a library for support vector machines[J].ACM Transactions on Intelligent Systems and Technology，2011，2（3）：1-27.
[20] FANG Y，YANG H，ZHANG X，et al.Multi-feature input deep forest for EEG-based emotion recognition[J].Frontiers in Neurorobotics，2021，14：617531.
[21] GAO Z K，LI R M，MA C，et al.Core-brain-network-based multilayer convolutional neural network for emotion recognition[J].IEEE Transactions on Instrumentation and Measurement，2021，70：2510209.
[22] 王雪芹.基于多个EEG信号特征的情绪分类分析与研究[D].南京：南京邮电大学，2020.
WANG X Q.Emotion recognition based on multiple features of EEG signals[D].Nanjing：Nanjing University of Posts and Telecommunications，2020.
[23] ZHENG W L，ZHU J Y，LU B L.Identifying stable patterns over time for emotion recognition from EEG[J].IEEE Transactions on Affective Computing，2017，10（3）：417-429.