计算机科学 ›› 2025, Vol. 52 ›› Issue (7): 201-209.doi: 10.11896/jsjkx.240500087
房春英, 何元昆, 吴安欣
FANG Chunying, HE Yuankun, WU Anxin
摘要： 随着神经科学和计算方法的不断进步,研究者们对情感与大脑活动之间的关系产生了越来越浓厚的兴趣。在这个领域,复杂网络的连通性和脑电图微状态成为研究热点。脑网络的连通性揭示了不同脑区之间的信息传递和协调程度,对情绪调节过程具有重要影响。微状态是大脑在静息状态下的短时段内的稳定活动模式,其变化反映了大脑功能状态的转换。为进一步研究情感与各脑区的关系和提高情感识别准确率,提出基于脑网络模块连通性和脑电微状态的情感识别方法。该方法通过网络模块连通性分析,将复杂系统进行模块化划分,揭示整体与局部在不同情感下的关系;同时引入微状态分析来探索脑区与情感的对应关系,并且提取各微状态的持续时间、发生频率、覆盖比例以及转换概率作为特征,用于情感识别,发现情感在右半脑更活跃。为了得到更加全面的特征信息,将两种特征拼接融合进行情感识别。在SEED数据集上做了大量实验,结果表明模块连通性特征gamma频段获得最高的平均准确率,为94.07%,微状态特征准确率为87.23%,而融合特征的平均准确率为95.34%,与上述单一方法的特征提取识别准确率相比,准确率分别提升了1.27%和8.11%。
中图分类号:
| [1]LI M,LU B L.Emotion classification based on gamma-bandEEG[C]//2009 Annual International Conference of the IEEE Engineering in medicine and biology society.IEEE,2009:1223-1226. [2]FDEZ J,GUTTENBERG N,WITKOWSKI O,et al.Cross-subject EEG-based emotion recognition through neural networks with stratified normalization[J].Frontiers in neuroscience,2021,15:626277. [3]LI J,ZHANG Z,HE H.Hierarchical convolutional neural networks for EEG-based emotion recognition[J].Cognitive Computation,2018,10:368-380. [4]SUN X,HU B,ZHENG X,et al.Emotion classification based on brain functional connectivity network[C]//2020 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).IEEE,2020:2082-2089. [5]WANG Z,TONG Y,HENG X.Phase-locking value based graph convolutional neural networks for emotion recognition[J].IEEE Access,2019,7:93711-93722. [6]LIU J,HU X,SHEN X,et al.The EEG microstate representation of discrete emotions[J].International Journal of Psychophysiology,2023,186:33-41. [7]PEDERSEN M,OMIDVARNIA A,SHINE J M,et al.Reducing the influence of intramodular connectivity in participation coefficient[J].Network Neuroscience,2020,4(2):416-431. [8]AHMADLOU M,ADELI H.Functional community analysis of brain:a new approach for EEG-based investigation of the brain pathology[J].NeuroImage,2011,58(2):401-408. [9]MICHEL C M,KOENIG T.EEG microstates as a tool for studying the temporal dynamics of whole-brain neuronal networks:a review[J].Neuroimage,2018,180:577-593. [10]KHANNA A,PASCUAL-LEONE A,MICHEL C M,et al.Microstates in resting-state EEG:current status and future directions[J].Neuroscience & Biobehavioral Reviews,2015,49:105-113. [11]SHEN X K,LI Y C,LIU J,et al.Emotional state decoding based on EEG functional connection microstates[J].Journal of Intelligent Science and Technology,2021,3(1):49-58. [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]DING W,ZHANG Y,HUANG L.Using a novel functional brain network approach to locate important nodes for working memory tasks[J].International journal of environmental research and public health,2022,19(6):3564. [14]SAKKALIS V.Review of advanced techniques for the estimation of brain connectivity measured with EEG/MEG[J].Computers in biology and medicine,2011,41(12):1110-1117. [15]JIANG L,FAN Q,REN J,et al.An improved BECT spike detection method with functional brain network features based on PLV[J].Frontiers in Neuroscience,2023,17:1150668. [16]LI C H,DONG Z X,SHAO N N.Research on orientation selectivity of visual neurons based on synchronization analysis[J].Journal of Yanshan University,2021,45(5):456-464. [17]RUBINOV M,SPORNS O.Complex network measures of brain connectivity:uses and interpretations[J].Neuroimage,2010,52(3):1059-1069. [18]BERTOLERO M A,YEO B T T,BASSETT D S,et al.A mechanistic model of connector hubs,modularity and cognition[J].Nature human behaviour,2018,2(10):765-777. [19]POULSEN A T,PEDRONI A,LANGER N,et al.MicrostateEEGlab toolbox:An introductory guide[J/OL].https://www.biorxiv.org/content/10.1101/289850v1.full. [20]LI Z Y,FU Y F.Research on visual imagination recognition based on EEG microstate method[J].Computer Engineering & Science,2021,43(3):465-472. [21]DELORME A,MAKEIG S.EEGLAB:an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis[J].Journal of neuroscience methods,2004,134(1):9-21. [22]PASCUAL-MARQUI R D,MICHEL C M,LEHMANN D.Segmentation of brain electrical activity into microstates:model estimation and validation[J].IEEE Transactions on Biomedical Engineering,1995,42(7):658-665. [23]HUANG H,XIE Q,PAN J,et al.An EEG-based brain computer interface for emotion recognition and its application in patients with disorder of consciousness[J].IEEE Transactions on Affective Computing,2019,12(4):832-842. [24]PETE G,CAPOTOSTO P,ZAPPASODI F,et al.Contrastinghemispheric asymmetries for emotional processing from event-related potentials and behavioral responses[J].Neuropsychology,2018,32(3):317. [25]LIU K,ZHANG X,LI P Y,et al.EEG emotion recognitionbased on brain functional network and co-spatial pattern analysis[J].Computer Application Research,2021,38(5):1344-134. [26]LI P,LIU H,SI Y,et al.EEG based emotion recognition bycombining functional connectivity network and local activations[J].IEEE Transactions on Biomedical Engineering,2019,66(10):2869-2881. [27]KIM S H,NGUYEN N A T,YANG H J,et al.ERAD-Fe:Emotion recognition-assisted deep learning framework[J].IEEE Transactions on Instrumentation and Measurement,2021,70:1-12. [28]YANG X D,MA Z Y,REN Y L,et al.Multidimensional EEG Emotion Recognition Based on Horizontal Visibility Graph Multivariate Joint Motif Entropy[J].Science China Information Sciences,2023,53(12):2406-2422. [29]WEI Z,LI H,MA L,et al.Emotion recognition based on microstate analysis from temporal and spatial patterns of electroencephalogram[J].Frontiers in Neuroscience,2024,18:1355512. [30]CHEN J,ZHAO Z,SHU Q,et al.Feature extraction based on microstate sequences for EEG-based emotion recognition[J].Frontiers in Psychology,2022,13:1065196. |
|
||
首页