基于有记忆递归神经网络的脑电特征情感识别研究

doi:10.16180/j.cnki.issn1007-7820.2020.11.013

电子科技 ›› 2020, Vol. 33 ›› Issue (11): 67-72.doi: 10.16180/j.cnki.issn1007-7820.2020.11.013

基于有记忆递归神经网络的脑电特征情感识别研究

张悦,胡春燕

上海理工大学光电信息与工程学院,上海 200093

收稿日期:2019-08-05 出版日期:2020-11-15 发布日期:2020-11-27
作者简介:张悦(1993-),女,硕士研究生。研究方向:模式识别、神经网络。|胡春燕(1976-),女,讲师。研究方向:计算机应用、模式识别。
基金资助:
国家自然科学基金青年基金(61703277)

Research on Emotion Recognition of EEG Features Based on the Long Short-term Memory Neural Network

ZHANG Yue,HU Chunyan

School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China

Received:2019-08-05 Online:2020-11-15 Published:2020-11-27
Supported by:
National Natural Science Foundation of China for the Youth(61703277)

摘要/Abstract

摘要：

为了提高脑电信号多分类的情感识别率,文中选用上海交通大学提供的SEED脑电信号数据集,对其进行分频带特征提取。将脑电数据的微分熵特征、微分不对称性特征和有理不对称性特征通过线性动力系统平滑特征后,与功率谱密度特征进行分类效果比较,再利用有记忆递归神经网络的方法进行分类,发现提取的微分熵特征经过分类的效果好。在对3种情感进行分类的过程中,采用长短时记忆神经网络分类相比于其他机器学习方法识别率有所提高,情感识别的平均准确率可达到95.045 9%。

关键词: 脑电信号, SEED数据集, 微分熵, 微分不对称, 有理不对称, 线性动力系统, 有记忆递归神经网络

Abstract:

In order to improve the accuracy rate of the emotional recognition of EEG signals in multi-classification, the SEED dataset published by SJTU is selected as the sample of EEG dataset. The original EEG signal is divided into five frequency bands, and their features are extracted. After the features of the differential entropy, the differential asymmetry and the rational asymmetry of EEG datasets are smoothed by linear dynamic system, the classification effect is compared with the feature of power spectral density. Then, the method of the long short-term memory neural network is used to classify emotion. It is concluded that the classification of the differential entropy feature is effective. Finally, compared with other machine learning methods, the recognition rate is improved, and the average accuracy of emotion recognition reaches 95.045 9%.

Key words: EEG signals, SEED dataset, differential entropy, differential asymmetry, rational asymmetry, linear dynamical system, long short-term memory neural network

中图分类号:

TP391

张悦,胡春燕. 基于有记忆递归神经网络的脑电特征情感识别研究[J]. 电子科技, 2020, 33(11): 67-72.

ZHANG Yue,HU Chunyan. Research on Emotion Recognition of EEG Features Based on the Long Short-term Memory Neural Network[J]. Electronic Science and Technology, 2020, 33(11): 67-72.

图/表 9

图1

图2

图3

图4

图5

表1

图6

表2

表3

参考文献 20

[1]	Barros P, Parisi G I, Weber C, et al. Emotion modulated attention improves expression recognition:a deep learning model[J]. Neurocomputing, 2017,253(8):104-114.
[2]	谢林, 李菲菲, 陈虬. 基于稀疏自动编码机的场景识别算法[J]. 电子科技, 2019,32(1):38-41.
	Xie Lin, Li Feifei, Chen Qiu. Scene Recognition algorithm based on sparse autoencoder[J]. Electronic Science and Technology, 2019,32(1):38-41.
[3]	Koelstra S, Muhl C, Soleymani M, et al. DEAP: a database for emotion analysis using physiological signals[J]. IEEE Transactions on Affective Computing, 2012,3(1):18-31.
[4]	Martinez H P, Bengio Y, Yannakakis G N. Learning deep physiological models of affect[J]. IEEE Computational Intelligence Magazine, 2013,8(2):20-33.
[5]	温万惠. 基于生理信号的情感识别方法研究[D]. 重庆:西南大学, 2010.
	Wen Wanhui. Research on emotion recognition methods based on physiological signals[D]. Chongqing:Southwest University, 2010.
[6]	李志鹏. 情感脑电的通道选择与分类方法研究[D]. 哈尔滨:哈尔滨工业大学, 2017.
	Li Zhipeng. Research on channel selection and emotion classification of EEG[D]. Harbin:Harbin Institute of Technology, 2017.
[7]	Chen J, Hu B, Moore P, et al. Electroencephalogram -based emotion assessment system using ontology and data mining techniques[J]. Applied Soft Computing, 2015,30(5):663-674.
[8]	Shi L C, Jiao Y Y, Lu B L. Differential entropy feature for EEG-based vigilance estimation[C]. Osaka:The Thirty-fifth Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2013.
[9]	Duan R N, Zhu J Y, Lu B L. Differential entropy feature for EEG-based emotion classification[C]. San Diego:The Sixth International IEEE Engineering in Medicine and Biology Society Conference on Neural Engineering, 2013.
[10]	Lin Y P, Yang Y H, Jung T P. Fusion of electroen- cephalogram dynamics and musical contents for estimating emotional responses in music listening[J]. Frontier in Neuroscience, 2014,8(94):33-35.
[11]	Li X, Song D, Zhang P, et al. Emotion recognition from multi-channel EEG data through convolutional recurrent neural network[C]. Kansas City:IEEE International Conference on Bioinformatics and Biomedicine, 2017.
[12]	Lo F, Li C, Wang J, et al. Continuous systolic and diastolic blood pressure estimation utilizing long short-term memory network[C]. Jeju:The Thirty-ninth IEEE Engineering in Medicine and Biology Society, 2017.
[13]	Zhang J, Li S, Yin Z. Pattern classification of instantaneous mental workload using ensemble of convolutional neural networks[J]. International Federation of Automatic Control-Papers on Line, 2017,50(1):14896-14901.
[14]	吴乃玉. 基于EEG 信号的情绪分类研究[D]. 北京:中央民族大学, 2013.
	Wu Naiyu. EEG-based emotion classification research[D]. Beijing:Minzu University of China, 2013.
[15]	Posner J, Russell J A, Peterson B S. The circumplex model of affect: an integrative approach to affective neuroscience, cognitive development, and psychopathology[J]. Development and Psychopathology, 2005,17(3):715-734. doi: 10.1017/S0954579405050340 pmid: 16262989
[16]	Petrantonakis P C, Hadjileontiadis L J. Emotion recognition from EEG using higher order crossings[J]. IEEE Transactions on Information Technology in Biomedicine, 2010,14(2):186-197. pmid: 19858033
[17]	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, 2016,7(99):1-15.
[18]	Li J, Zhang Z, He H. Implementation of EEG emotion recognition system based on hierarchical convolutional neural networks[C]. Beijing:The Eighth International Conference on Brain Inspired Cognitive Systems, 2016.
[19]	Zheng W L, Guo H T, Lu B L. Revealing critical channels and frequency bands for emotion recognition from EEG with deep belief network[C]. Paris:The Seventh International IEEE Engineering in Medicine and Biology Society Conference on Neural Engineering, 2015.
[20]	魏琛, 陈兰岚, 张傲. 基于集成卷积神经网络的脑电情感识别[J]. 华东理工大学学报(自然科学版), 2018,45(1):125-132.
	Wei Chen, Chen Lanlan, Zhang Ao. Emotion recognition of EEG based on ensemble convolutional neural networks[J]. Journal of East China University of Science and Technology, 2018,45(1):125-132.

特征	delta	theta	alpha	beta	gamma
DE	79.39%	85.62%	90.17%	95.43%	97.8%
PSD	57.42%	60.69%	66.84%	68.02%	75.33%
ASM	59.35%	63.98%	68.4%	69.19%	76.75%

分类算法	平均准确率
KNN	62.13%
SVM	75.03%
CNN	87.55%
LSTM	95.04%

文献	分类方法	平均识别率/%
[17]	BDAE	91.01%
[18]	HCNN	88.20%
[19]	DBN	86.65%
[20]	集成CNN	93.12%

基于有记忆递归神经网络的脑电特征情感识别研究

Research on Emotion Recognition of EEG Features Based on the Long Short-term Memory Neural Network

RichHTML

PDF (PC)

赞

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 20

相关文章 1

Metrics

本文评价

推荐阅读 0