计算机科学 ›› 2023, Vol. 50 ›› Issue (6A): 220600128-8.doi: 10.11896/jsjkx.220600128
罗瑞奇, 严金林, 胡新荣, 丁磊
LUO Ruiqi, YAN Jinlin, HU Xinrong, DING Lei
摘要: 脑电信号应用于情感识别的研究近年来受到广泛的关注,将时间序列映射为可见图表示,通过可见图边和节点的度量能够有效进行脑电情感识别。传统可见图算法忽略了多通道脑电信号间的相关性,难以保留时间序列上复杂的特征信息。因此提出一种多重有向加权可见图提取脑电信号特征的方法,并将脑电信号特征用于情感识别。首先将脑电信号转换成有向加权网络图,强化信号的特征表示,使用加权聚类系数表征复杂网络结构,以多重复杂网络建立脑电连接矩阵,最后采用卷积神经网络进行特征学习,通过学习后获得情感识别结果。多重有向加权可见图构建的复杂网络模型在公开数据集验证的准确率达到了93.85%,优于现有的简单可见图方法;多重加权可见图与单变量可见图相比,情感识别准确率提高了9.4%。实验结果表明,该方法在跨被试者数据上同样适用,具有很好的鲁棒性。
中图分类号:
[1]LI Y,ZHENG W,WANG L,et al.From regional to globalbrain:A novel hierarchical spatial-temporal neural network model for EEG emotion recognition[J].IEEE Transactions on Affective Computing,2019,13(2):568-578. [2]CAO Y,CAI L,WANG J,et al.Characterization of complexity in the electroencephalograph activity of Alzheimer′s disease based on fuzzy entropy[J].Chaos:An Interdisciplinary Journal of Nonlinear Science,2015,25(8):083116. [3]RODRIGUEZ-BERMUDEZ G,GARCIA-LAENCINA P J.Analysis of EEG signals using nonlinear dynamics and chaos:a review[J].Applied Aathematics & Information Sciences,2015,9(5):2309. [4]SMALL M,ZHANG J,XU X.Transforming time series into complex networks[C]//International Conference on Complex Sciences.Berlin:Springer,2009:2078-2089. [5]XIANG R,ZHANG J,XU X K,et al.Multiscale characterization of recurrence-based phase space networks constructed from time series[J].Chaos:An Interdisciplinary Journal of Nonlinear Science,2012,22(1):013107. [6]SPORNS O.The human connectome:a complex network[J].Annals of the New York Academy of Sciences,2011,1224(1):109-125. [7]ZANGENEH S M,MAGHOOLI K,SETAREHDAN S K,et al.Emotion classification through nonlinear EEG analysis using machine learning methods[J].Int.Clin.Neurosci.J,2018,5:135-149. [8]HARMON-JONES E,GABLE P A,PETERSON C K.The role of asymmetric frontal cortical activity in emotion-related phenomena:A review and update[J].Biological Psychology,2010,84(3):451-462. [9]PAUL S,MAZUMDER A,GHOSH P,et al.EEG based emo-tion recognition system using MFDFA as feature extractor[C]//2015 International Conference on Robotics,Automation,Control and Embedded Systems(RACE).IEEE,2015:1-5. [10]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. [11]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. [12]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. [13]ALGUMAEI M,HETTIARACHCHI I T,VEERABHADRAPPA R,et al.Wavelet Packet Energy Features for EEG-Based Emotion Recognition[C]//2021 IEEE International Conference on Systems,Man,and Cybernetics(SMC).IEEE,2021:1935-1940. [14]JOSHI V M,GHONGADE R B.EEG based emotion detection using fourth order spectral moment and deep learning[J].Biomedical Signal Processing and Control,2021,68:102755. [15]LACASA L,LUQUE B,BALLESTEROS F,et al.From timeseries to complex networks:The visibility graph[J].Procee-dings of the National Academy of Sciences,2008,105(13):4972-4975. [16]LUQUE B,LACASA L,BALLESTEROS F,et al.Horizontal visibility graphs:Exact results for random time series[J].Physical Review E,2009,80(4):046103. [17]WANG J,YANG C,WANG R,et al.Functional brain networks in Alzheimer’s disease:EEG analysis based on limited penetrable visibility graph and phase space method[J].Physica A:Statistical Mechanics and its Applications,2016,460:174-187. [18]ZHU G,LI Y,WEN P P.Epileptic seizure detection in EEGs signals using a fast weighted horizontal visibility algorithm[J].Computer Methods and Programs in Biomedicine,2014,115(2):64-75. [19]SAMANTA K,CHATTERJEE S,BOSE R.Cross-subject motor imagery tasks EEG signal classification employing multiplex weighted visibility graph and deep feature extraction[J].IEEE Sensors Letters,2019,4(1):1-4. [20]LI X,SONG D,ZHANG P,et al.Exploring EEG features incross-subject emotion recognition[J].Frontiers in neuroscience,2018,12:162. [21]LU Y,WANG M,WU W,et al.Dynamic entropy-based pattern learning to identify emotions from EEG signals across indivi-duals[J].Measurement,2020,150:107003. [22]CIMTAY Y,EKMEKCIOGLU E.Investigating the use of pretrained convolutional neural network on cross-subject and cross-dataset EEG emotion recognition[J].Sensors,2020,20(7):2034. [23]YAO L,WANG M,LU Y,et al.EEG-Based Emotion Recognition by Exploiting Fused Network Entropy Measures of Complex Networks across Subjects[J].Entropy,2021,23(8):984. [24]LI X,ZHAO Z,SONG D,et al.Latent factor decoding of multi-channel EEG for emotion recognition through autoencoder-like neural networks[J].Frontiers in Neuroscience,2020,14:87. [25]YANG F,ZHAO X,JIANG W,et al.Multi-method fusion ofcross-subject emotion recognition based on high-dimensional EEG features[J].Frontiers in Computational Neuroscience,2019,13:53. [26]ZHANG T,ZHENG W,CUI Z,et al.Spatial-temporal recurrent neural network for emotion recognition[J].IEEE Transactions on Cybernetics,2018,49(3):839-847. [27]SONG T,ZHENG W,SONG P,et al.EEG emotion recognition using dynamical graph convolutional neural networks[J].IEEE Transactions on Affective Computing,2018,11(3):532-541. |
|