基于IMF能量矩的脑电情绪特征提取研究Research on EEG emotion feature extraction based on IMF energy moment
王成龙,韦巍,李天永
摘要(Abstract)：
为了提高脑电信号情绪识别分类的准确率,在小波变换的基础上,结合经验模态分解(EMD)和能量矩提出一种新的脑电特征提取方法。该研究利用小波变换提取左右前额叶(AF3,AF4)、左右额叶(F3,F4)和左右顶叶(FC5,FC6)通道的α波、θ波、β波和γ波节律;对提取的脑电节律进行EMD分解获得固有模态函数(IMF)分量,再进一步提取IMF分量的能量矩特征;最后使用支持向量机实现情感状态评估。实验结果表明,将IMF能量矩用于脑电信号情感识别是可行的。
关键词(KeyWords)： 小波变换;经验模态分解;本征模态函数;能量矩;脑电信号;情感识别
基金项目(Foundation):
作者(Author): 王成龙,韦巍,李天永
DOI: 10.16652/j.issn.1004-373x.2018.20.003
参考文献(References)：
- [1] HUANG N E,SHEN Z,LONG S R,et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis[J]. Proceedings:mathematical, physical and engineering sciences, 1998, 454(1971):903-995.
- [2] SHEN X L,FAN Y L. Sleep stage classification based on EEG signals by using improved Hilbert-Huang transform[J]. Applied mechanics and materials,2012,138:1096-1101.
- [3] LI S,ZHOU W,CAI D,et al. EEG signal classification based on EMD and SVM[J]. Journal of biomedical engineering,2011,28(5):891-894.
- [4]杨鹏圆,李海芳,陈东伟.Hilbert-Huang变换在情感脑电特征提取中的应用[J].计算机工程与设计,2014,35(7):2509-2514.YANG Pengyuan,LI Haifang,CHEN Dongwei. Application of Hilbert-Huang transform in emotion EEG feature extraction[J].Computer engineering and design,2014,35(7):2509-2514.
- [5]陆苗,邹俊忠,张见,等.基于IMF能量熵的脑电情感特征提取研究[J].生物医学工程研究,2016,35(2):71-74.LU Miao,ZOU Junzhong,ZHANG Jian,et al. Emotion electroencephalograph(EEG)recognition based on IMF energy entropy[J]. Journal of biomedical engineering research,2016,35(2):71-74.
- [6] ARASTEH A,JANGHORBANI A,MORADI M H. A survey on EMD sensitivity to SNR for EEG feature extraction in BCI application[C]//Proceedings of 5th International Biomedical Engineering Conference. Cairo:IEEE,2010:175-179.
- [7] CHAI R,LING S H,HUNTER G P,et al. Toward fewer EEG channels and better feature extractor of non-motor imagery mental tasks classification for a wheelchair thought controller[C]//Proceedings of Annual International Conference of the IEEE Engineering in Medicine and Biology Society. San Diego:IEEE,2012:5266-5269.
- [8] MERT A,AKAN A. Emotion recognition from EEG signals by using multivariate empirical mode decomposition[J]. Pattern analysis and applications,2018,21(1):81-89.
- [9] 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.
- [10]秦太龙,杨勇,程珩,等.基于IMF能量矩和神经网络的轴承故障诊断[J].振动、测试与诊断,2008,28(3):229-232.QIN Tailong,YANG Yong,CHENG Hang,et al. Rolling bearing fault diagnosis based on intrinstc mode function energy moment and BP neural network[J]. Journal of vibration,measurement&diagnosis,2008,28(3):229-232.
- [11]毛茅.音乐诱发情绪的心理生理测量及其在服务设计中的应用[D].北京:清华大学,2013.MAO Mao. Psychologically and physiologically measuring music-induced emotion and its application in service design[D].Beijing:Tsinghua University,2013.
- [12] SAMMLER D,GRIGUTSCH M,FRITZ T,et al. Music and emotion:electrophysiological correlates of the processing of pleasant and unpleasant music[J]. Psychophysiology,2007,44(2):293-304.
- [13] CANDRA H,YUWONO M,CHAI R,et al. Investigation of window size in classification of EEG-emotion signal with wavelet entropy and support vector machine[C]//Proceedings of37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Milan:IEEE,2015:7250-7253.
- [14] OOSTENVELD R,PRAAMSTRA P. The five percent electrode system for high-resolution EEG and ERP measurements[J]. Clinical neurophysiology,2001,112(4):713-719.