计算机科学 ›› 2024, Vol. 51 ›› Issue (11A): 231200066-7.doi: 10.11896/jsjkx.231200066
李争平, 李汉文, 王立军
LI Zhengping, LI Hanwen, WANG Lijun
摘要： 深度学习的出现,使得脑电信号研究得到进一步发展。常用的基于深度学习对情绪分类的方法有人工神经网络(Artificial Neural Network,ANN)与深度学习(Deep Learning,DL)等。但脑电信号属于有限样本数据,对于深度学习这类需要大量数据驱动训练从而完成分类任务的网络来说,如何在有限的数据数量下提升分类任务的效果和泛化性能是一个研究重点。针对脑电研究中真实环境对脑电信号的影响以及神经网络模型泛化性问题,充分挖掘脑电信号包含的信息,提出了同时考虑原始脑电信号和DE特征的深度学习模型,并设计实验的数据采集过程和处理过程。在DEAP数据集、SEED数据集和实验采集的数据上进行实验,评估所搭建网络的性能效果和泛化能力,探索深度学习网络在脑电信号上的情绪分类关联关系。使用本文构建的网络模型与特征处理办法,在SEED数据集的情绪三分类上获得了85.62%的准确率,在DEAP数据集原始脑电的效价和唤醒两个维度的情绪二分类上分别获得了59.38%和61.70%的准确率。
中图分类号:
| [1]KAMBLE K,SENGUPTA J.A comprehensive survey on emotion recognition based on electroencephalograph(EEG) signals[J].Multimedia Tools and Applications,2023,82:1-36. [2]PATLAR AKBULUT F.Hybrid deep convolutional model-based emotion recognition using multiple physiological signals[J].Computer Methods in Biomechanics and Biomedical Engineering,2022,25(15):1678-1690. [3]YUVARAJ R,THAGAVEL P,THOMAS J,et al.Comprehen-sive Analysis of Feature Extraction Methods for Emotion Re-cognition from Multichannel EEG Recordings[J].Sensors,2023,23(2):915. [4]DING Y,ROBINSON N,ZHANG S,et al.Tsception:Capturingtemporal dynamics and spatial asymmetry from EEG for emotion recognition[J].IEEE Transactions on Affective Computing,2023,14(3):1-13. [5]CUNNINGHAM P,DELANY S J.k-Nearest neighbour classi-fiers-A Tutorial[J].ACM computing surveys(CSUR),2021,54(6):1-25. [6]THARWAT A,GABER T,IBRAHIM A,et al.Linear discrimi-nant analysis:A detailed tutorial[J].AI Communications,2017,30(2):169-190. [7]NOBLEW S.What is a support vector machine?[J].Nature Biotechnology,2006,24(12):1565-1567. [8]RISHI.An empirical study of the naive Bayes classifier[C]//Workshop on Empirical Methods in Artificial Intelligence(IJCAI 2001).2001:41-46. [9]AHMED M Z I,SINHA N.EEG-based emotion classificationusing LSTM under new paradigm[J].Biomedical Physics & Engineering Express,2021,7(6):065018. [10]LI X,SONG D,ZHANG P,et al.Emotion recognition frommulti-channel EEG data through convolutional recurrent neural network[C]//2016 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).IEEE,2016:352-359. [11]YANG Y,WU Q,QIU M,et al.Emotion recognition frommulti-channel EEG through parallel convolutional recurrent neural network[C]//2018 International Joint Conference on Neural Networks(IJCNN).IEEE,2018:1-7. [12]TAO W,LI C,SONG R,et al.EEG-based emotion recognitionvia channel-wise attention and self attention[J].IEEE Transactions on Affective Computing,2023,14(1):382-393. [13]WANG F,ZHONG S,PENG J,et al.Data augmentation for EEG-based emotion recognition with deep convolutional neural networks[C]//MultiMedia Modeling:24th International Conference(MMM 2018).Bangkok,Thailand,Part II 24.Springer International Publishing,2018:82-93. [14]YANG Y,WU Q,QIN M,et al.Emotion recognition frommulti-channel EEG through parallel convolutional recurrent neural network[C]//2018 International Joint Conference on Neural Networks(IJCNN).IEEE,2018:1-7. [15]ZHENG W L,LUB L.Investigating critical frequency bands and channels for EEG-based emotion recognition with deep neural networks[J].IEEE Transactions on Autonomous Mental Deve-lopment,2015,7(3):162-175. [16]ULLAH I,HUSSAIN M,ABOALSAMH H.An automatedsystem for epilepsy detection using EEG brain signals based on deep learning approach[J].Expert Systems with Applications,2018,107:61-71. [17]BIGDELY-SHAMLO N,TOURYAN J,OJEDA A,et al.Automated EEG mega-analysis I:Spectral and amplitude characteristics across studies[J].NeuroImage,2020,207:116361. [18]WANG X Q.Emotion recognition based on multiple features ofEEG signals[D].Nanjing:Nanjing University of Posts and Telecommunications,2020. [19]LI J Q,LI H F,BAI Y F,et al.Research on Automatic Identification and Removal Method of Ocular Electrographic Artifacts in EEG Signals[J].Computer Engineering and Applications,2018,54(13):148-152,167 [20]YANG Y,WU Q M J,ZHENG W L,et al.EEG-based emotion recognition using hierarchical network with subnetwork nodes[J].IEEE Transactions on Cognitive and Developmental Systems,2017,10(2):408-419. [21]ZHENG W L,LU B L.Investigating critical frequency bandsand channels for EEG-based emotion recognition with deep neural networks[J].IEEE Transactions on autonomous mental development,2015,7(3):162-175. [22]HU J,SHEN L,ALBANIE S,et al.Squeeze-and-Excitation Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2019,42(8):1-1. [23]DING Y,ROBINSON N,ZHANG S,et al.Tsception:Capturing temporal dynamics and spatial asymmetry from EEG for emotion recognition[J].IEEE Transactions on Affective Computing,2023,14(3):2238-2250. [24]PAN C,SHI C,MU H,et al.EEG-based emotion recognitionusing logistic regression with Gaussian kernel and Laplacian prior and investigation of critical frequency bands[J].Applied Sciences,2020,10(5):1619. [25]MAHADEVASWAMY U B,SWATHI P.Sentiment analysisusing bidirectional LSTM network[J].Procedia Computer Science,2023,218:45-56. [26]HU J,SHEN L,SUN G.Squeeze-and-excitation networks[C]//Proceedings of the IEEE conference on computer vision and pattern recognition.2018:7132-7141. [27]JAKKULA V.Tutorial on support vector machine(svm)[J].School of EECS,Washington State University,2006,37(2.5):3. [28]ZHENG W.Multichannel EEG-based emotion recognition via group sparse canonical correlation analysis[J].IEEE Transactions on Cognitive and Developmental Systems,2016,9(3):281-290. [29]WEI C,CHEN L,SONG Z,et al.EEG-based emotion recognition using simple recurrent units network and ensemble learning[J].Biomedical Signal Processing and Control,2020,58:101756. |
|
||
首页