利用卷积回声状态网络实现脑电情感识别

doi:10.13190/j.jbupt.2021-078

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (2): 36-43.doi: 10.13190/j.jbupt.2021-078

利用卷积回声状态网络实现脑电情感识别

晁浩, 马庆敏, 刘永利

河南理工大学计算机科学与技术学院, 焦作 454003

收稿日期:2021-04-28 发布日期:2021-12-16
通讯作者: 马庆敏(1995—),女,硕士生,邮箱:maqingmin666@163.com。 E-mail:maqingmin666@163.com
作者简介:晁浩(1981—),男,讲师,硕士生导师。
基金资助:
国家自然科学基金项目(61872126);河南省高等学校重点科研项目(19A520004);河南省高校基本科研业务费专项资金项目(NSFRF1616)

EEG-Based Emotion Recognition by Using Convolutional Echo-State Network

CHAO Hao, MA Qingmin, LIU Yongli

College of Computer Science and Technology, Henan Polytechnic University, Jiaozuo 454003, China

Received:2021-04-28 Published:2021-12-16

摘要/Abstract

摘要： 针对多通道脑电(EEG)的情感识别,提出了一种卷积回声状态网络(CESN)模型。首先构造EEG信号的特征矩阵序列;然后通过卷积操作提取各个样本的高层抽象特征,形成一维特征向量序列;利用具有自反馈功能的蓄水池结构,捕获向量序列的动态时序信息;最后用岭回归来实现情感识别。在情感分析专用生理信号数据集上进行实验的结果表明,EEG信号的动态时序性蕴含着与情感状态相关的区分性信息,所提的CESN模型能够有效地挖掘这种信息,并用于情感分类,解决了卷积神经网络中因使用反向传播算法而导致的局部最优和训练时间过长的问题。

关键词: 多通道脑电信号, 情感识别, 卷积回声状态网络, 特征融合

Abstract: A convolutional echo-state network (CESN) model is proposed for the emotion recognition task based on electroencephalogram (EEG) signals. First, a feature matrix sequence of EEG signal is constructed. Then, high-level abstract features are extracted from the feature matrices via convolution, and one dimension feature vectors are formed. After that, a reservoir with self-feedback function is employed to extract the dynamic temporal information from the feature vector sequence. Finally, the emotion recognition task is realized by ridge regression. The experiment is carried out on the database for emotion analysis using physiological signals datasets. The experiment result shows that the EEG signal segments contain temporal information related to emotion, and the CESN model can mine and utilize the information effectively. In addition, the proposed CESN model can circumvent the problems of the local optimization and long training time, which are caused by back propagation algorithm in convolutional neural network.

Key words: multi-channel electroencephalogram signal, emotion classification, convolutional echo-state network, feature confusion

中图分类号:

TP18

晁浩, 马庆敏, 刘永利. 利用卷积回声状态网络实现脑电情感识别[J]. 北京邮电大学学报, 2022, 45(2): 36-43.

CHAO Hao, MA Qingmin, LIU Yongli. EEG-Based Emotion Recognition by Using Convolutional Echo-State Network[J]. Journal of Beijing University of Posts and Telecommunications, 2022, 45(2): 36-43.

参考文献

[1] HWANG S, HONG K, SON G, et al. Learning CNN features from DE features for EEG-based emotion recognition[J]. Pattern Analysis and Applications, 2020, 23(3):1323-1335.
[2] ER M, CIG H, AYDILEK B B. A new approach to recognition of human emotions using brain signals and music stimuli[J/OL]. Applied Acoustics, 2021, 175:107840-107856[2021-03-12]. https://doi.org/10.1016/j.apacoust.2020.107840.
[3] CAO Q C, ZHANG W L, ZHU Y H. Deep learning-based classification of the polar emotions of "moe" -style cartoon pictures[J]. Tsinghua Science and Technology, 2021, 26(3):275-286.
[4] KEELAWAT P, THAMMASAN N, NUMAO M, et al. A comparative study of window size and channel arrangement on EEG-emotion recognition using deep CNN[J]. Sensors, 2021, 21(5):1678-1696.
[5] PERI R, PARTHASARATHY S, BRADSHAW C, et al. Disentanglement for audio-visual emotion recognition using multitask setup[EB/OL].(2021-03-11)[2021-03-24]. https://arxiv.org/abs/2102.06269.
[6] ABBASCHIAN B J, SIERRA S D, ELMAGHRABY A. Deep learning techniques for speech emotion recognition, from databases to models[J/OL]. Sensors, 2021, 21(4):1249-1275[2021-03-23]. https://www.mdpi.com/1424-8220/21/4/1249.
[7] JIA X, ZHANG T, PHILIP Chen C L, et al. Multi-channel EEG based emotion recognition using temporal convolutional network and broad learning system[C]//2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Piscataway, NJ:IEEE Press, 2020:2452-2457.
[8] XIN Q, HU S H, LIU S Q, et al. Epilepsy EEG classification based on convolution support vector machine[J]. Journal of Medical Imaging and Health Informatics, 2021, 11(1):25-32.
[9] YANG Y L, WU Q F, FU Y Z, et al. Continuous convolutional neural network with 3D input for EEG-based emotion recognition[C]//International Conference on Neural Information Processing. Berlin:Springer, 2018:433-443.
[10] CHEN J X, WANG L Y, JIA X Y, et al. EEG-based emotion recognition using deep convolutional neural network[J]. Computer Engineering and Applications, 2019, 55(18):103-110.
[11] GONZALEZ H A, MUZAFFAR S, YOO J, et al. BioCNN:a hardware inference engine for EEG-based emotion detection[J/OL]. IEEE Access, 2020, 8:140896-140914[2021-03-17]. https://ieeexplore.ieee.org/document/9151874.
[12] JAEGER H, HAAS H. Harnessing nonlinearity:predicting chaotic systems and saving energy in wireless communication[J]. Science, 2004, 304(5667):78-80.
[13] LUKOEVIIUS M L, JAEGER H, SCHRAUWAN H. Reservoir computing trends[J]. KI-Künstliche Intelligenz, 2012, 26(4):365-371.
[14] GAO R, DU L, DURU O, et al. Time series forecasting based on echo state network and empirical wavelet transformation[J/OL].Applied Soft Computing,2021,102:107111-107122[2021-03-19]. https://doi.org/10.1016/j.asoc.2021.107111.
[15] SUN L L, JIN B, YANG H Y, et al. Unsupervised EEG feature extraction based on echo state network[J]. Information Sciences, 2018, 475:1-17.
[16] FOURATI R, AMMAR B, SANCHEZ M J, et al. Unsupervised learning in reservoir computing for EEG-based emotion recognition[J]. IEEE Transactions on Affective Computing, 2020, 99:1-13.
[17] HART A G, OLDING K R, COX A, et al. Echo state networks for reinforcement learning[J]. Journal of Machine Research, 2000, 1:1-48.
[18] LI X, SONG D W, ZHANG P, et al. Emotion recognition from multi-channel EEG data through convolutional recurrent neural network[C]//Proceedings of IEEE International Conference on Bioinformatics and Biomedicine. Piscataway, NJ:IEEE Press, 2016:352-359.
[19] HADEEL H A, ANDERSON A K, ASSAF K. Comparing three models of arousal in the human brain[J]. Social Cognitive and Affective Neuroscience, 2020, 15(1):1-11.
[20] TRIPATHI S, ACHARYA S, SHARMA R D, et al. Using deep and convolutional neural networks for accurate emotion classification on DEAP dataset[C]//Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. Palo Alto:AAAI Press, 2017, 7:4746-4752.
[21] ALTURKI F A, ALSHARABI K, ABDURRAGEBD A M, et al. EEG signal analysis for diagnosing neurological disorders using discrete wavelet transform and intelligent techniques[J]. Sensors, 2020, 20(9):2505-2521.

利用卷积回声状态网络实现脑电情感识别

EEG-Based Emotion Recognition by Using Convolutional Echo-State Network

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

[1]	周雨昊孙哲吴晓非禹可. 基于门控特征融合的中文错别字纠正模型[J]. 北京邮电大学学报, 2023, 46(4): 91-96,122.
[2]	苏兴禹可吴晓非. 基于层次门控交互融合网络的谣言检测方法[J]. 北京邮电大学学报, 2023, 46(4): 97-102.
[3]	宋宇博高嘉振. 改进YOLOv3算法的交通多目标检测方法[J]. 北京邮电大学学报, 2022, 45(5): 103-108.
[4]	李雪, 李晓艳, 王鹏, 孙梦宇, 吕志刚. 结合双注意力与特征融合的孪生网络目标跟踪[J]. 北京邮电大学学报, 2022, 45(4): 116-122.
[5]	刘逸琛, 孙华志, 马春梅, 姜丽芬, 钟长鸿. 一种基于高层特征融合的网络商品分类[J]. 北京邮电大学学报, 2020, 43(5): 98-104,117.
[6]	刘渭滨, 邹智元, 邢薇薇. 模式分类中的特征融合方法[J]. 北京邮电大学学报, 2017, 40(4): 1-8.
[7]	姜晓庆, 夏克文, 夏莘媛, 祖宝开. 采用半定规划多核SVM的语音情感识别[J]. 北京邮电大学学报, 2015, 38(s1): 67-71.