面向脑电情感识别的改进多分类RVM模型研究
|
摘要
从相关向量机(RVM)和支持向量机(SVM)的相似性以及RVM的稀疏特性出发,将RVM应用于脑电信号(EEG)的情感识别中。针对一对一(OAO)和一对多(OAA)两种多分类方法各自的特点和不足,提出了一种全新的两层多分类模型(OAA-OAO),改进现有OAO算法中无效投票影响最终决策的现象。设计情感EEG信号识别对比实验,验证基于RVM的改进多分类算法在脑电信号情感识别中的应用。对于实验室采集的情感脑电信号,提取其非线性特征(功率谱熵、样本熵和Hurst指数)并采用主成分分析法进行降维。将OAA-OAO-RVM算法分别和OAOSVM、OAO-RVM两种识别网络进行对比,分析RVM的识别性能以及OAA-OAO多分类算法的分类性能。结果表明,采用降维后的最优特征集合作为识别网络的输入向量得到的识别性能更高,且RVM表现出的性能优于SVM。同时,改进后的OAA-OAO算法较传统OAO模型的平均识别率提高了7.89%,证明OAA-OAO算法可有效去除一部分无效投票从而使分类精度得到显著提高,验证了此模型是一种有效的多分类模型。
Based on the similarity of Relevance Vector Machine(RVM)and Support Vector Machine(SVM)and the sparse characteristics of RVM, RVM is applied to the electroencephalogram(EEG)signal emotional recognition. Aiming at the characteristics and deficiencies of the two methods of One-Against-One(OAO)and One-Against-All(OAA), this paper proposes a new two-layer multi-classification model(OAA-OAO)to improve the effect of invalid voting on the final decision-making in the existing OAO algorithm. A series of emotional EEG signal recognition experiments are designed to verify the effectiveness of improved multi-classification algorithm based on RVM in EEG emotion recognition.For the emotional EEG signal collected by the laboratory, this paper extracts the nonlinear features(power spectral entropy,sample entropy and Hurst index)and reduces the dimension by Principal Component Analysis(PCA). OAA-OAO-RVM is compared with OAO-SVM and OAO-RVM respectively, the recognition performance of RVM and the classification performance of OAA-OAO is analyzed. The results show that using the optimal feature set after dimension reduction as input vector of the recognition network has higher recognition rate, and the performance of RVM is better than that of SVM. At the same time, the average recognition rate of OAA-OAO is 7.89% higher than that of OAO, which proves that the OAA-OAO algorithm can effectively remove part of the invalid votes so that the classification accuracy can be improved obviously and this model is an effective multi-classification model.
Based on the similarity of Relevance Vector Machine(RVM)and Support Vector Machine(SVM)and the sparse characteristics of RVM, RVM is applied to the electroencephalogram(EEG)signal emotional recognition. Aiming at the characteristics and deficiencies of the two methods of One-Against-One(OAO)and One-Against-All(OAA), this paper proposes a new two-layer multi-classification model(OAA-OAO)to improve the effect of invalid voting on the final decision-making in the existing OAO algorithm. A series of emotional EEG signal recognition experiments are designed to verify the effectiveness of improved multi-classification algorithm based on RVM in EEG emotion recognition.For the emotional EEG signal collected by the laboratory, this paper extracts the nonlinear features(power spectral entropy,sample entropy and Hurst index)and reduces the dimension by Principal Component Analysis(PCA). OAA-OAO-RVM is compared with OAO-SVM and OAO-RVM respectively, the recognition performance of RVM and the classification performance of OAA-OAO is analyzed. The results show that using the optimal feature set after dimension reduction as input vector of the recognition network has higher recognition rate, and the performance of RVM is better than that of SVM. At the same time, the average recognition rate of OAA-OAO is 7.89% higher than that of OAO, which proves that the OAA-OAO algorithm can effectively remove part of the invalid votes so that the classification accuracy can be improved obviously and this model is an effective multi-classification model.
引文
[1]聂聃.基于脑电的情感识别[D].上海:上海交通大学,2012.
[2]姚慧,孙颖,张雪英.情感语音的非线性动力学特征研究[J].西安电子科技大学学报,2016(5).
[3]时文飞,叶西宁.基于脑电信号的ILDB情感特征提取算法[J].华东理工大学学报,2016,42(2):254-249.
[4]聂聃,王晓韡,段若男,等.基于脑电的情绪识别研究综述[J].中国生物医学工程学报,2012,31(4):596-606.
[5]綦宏志,程龙龙,陈滨津,等.想象动作中动态脑电的信息熵研究[J].中国生物医学工程学报,2007,26(1):74-77.
[6]李立.基于脑电信号样本熵的情感识别[D].太原:太原理工大学,2014.
[7]Isotani T,Lehmann D,Pascual-Marqui R D,et al.Source localization of brain electric activity during positive,neutral and negative emotional states[J].International Congress,2002,1232(2):165-173.
[8]Jatupaiboon N,Pan-Ngum S,Israsena P.Emotion classification using minimal EEG channels and frequency bands[C]//10th International Joint Conference on Computer Science and Software Engineering,2013.
[9]赵国朕,宋金晶,葛燕,等.基于生理大数据的情绪识别研究进展[J].计算机研究与发展,2016,53(1):80-92.
[10]Demidova L,Klyueva I,Sokolova Y,et al.Intellectual approaches to improvement of the classification decisions quality on the base of the SVM classifier[J].Procedia Computer Science,2017,103:222-230.
[11]Tipping M E.Sparse bayesian learning and the relevance vector machine[J].Journal of Machine Learnig Research,2001(1):211-244.
[12]Tipping M E.The Relevance vector machine[C]//Advances in Neural Information Processing Systems,1999:652-658.
[13]Xu Xiangmin,Mao Yunfeng,Xiong Jiani,et al.Classification performance comparison between RVM and SVM[C]//IEEE International Workshop on Conference on Auti-Counterfeiting,Security,Identification,2007.
[14]柳长源.相关向量机多分类算法的研究与应用[D].哈尔滨:哈尔滨工程大学,2013.
[15]Han M,Sun L.EEG signal classification for epilepsy diagnosis based on AR model and RVM[C]//International Conference on Intelligent Control and Information Processing,2010:134-139.
[16]Huang J,Hu X,Geng X.An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine[J].Electric Power Systems Research,2011,81(2):400-407.
[17]Xu J.An extended one-versus-rest support vector machine for multi-label classification[J].Neurocomputing,2011,74(17):3114-3124.
[18]Kalaivani M,Kalaivani V,Anusuya Devi V,et al.Analysis of EEG signal for the detection of brain abnormalities[C]//IJCA Proceedings of International Conference on Simulations in Computing Nexus,2014:1-6.
[19]Raju V V V,Gangamohan P,Gangashetty S V,et al.Application of prosody modification for speech recognition in different emotion conditions[C]//Region 10Conference,2017:951-954.
[20]Kadiri S R,Yegnanarayana B.Epoch extraction from emotional speech using single frequency filtering approach[J].Speech Communication,2017,86:52-63.
[21]张雪英,张婷,孙颖,等.情感语音数据库优化及PAD情感模型量化标注[J].太原理工大学学报,2017,48(3):469-474.
[22]陈曾,刘光远.脑电信号在情感识别中的应用[J].计算机工程,2010,36(9):168-170.
[2]姚慧,孙颖,张雪英.情感语音的非线性动力学特征研究[J].西安电子科技大学学报,2016(5).
[3]时文飞,叶西宁.基于脑电信号的ILDB情感特征提取算法[J].华东理工大学学报,2016,42(2):254-249.
[4]聂聃,王晓韡,段若男,等.基于脑电的情绪识别研究综述[J].中国生物医学工程学报,2012,31(4):596-606.
[5]綦宏志,程龙龙,陈滨津,等.想象动作中动态脑电的信息熵研究[J].中国生物医学工程学报,2007,26(1):74-77.
[6]李立.基于脑电信号样本熵的情感识别[D].太原:太原理工大学,2014.
[7]Isotani T,Lehmann D,Pascual-Marqui R D,et al.Source localization of brain electric activity during positive,neutral and negative emotional states[J].International Congress,2002,1232(2):165-173.
[8]Jatupaiboon N,Pan-Ngum S,Israsena P.Emotion classification using minimal EEG channels and frequency bands[C]//10th International Joint Conference on Computer Science and Software Engineering,2013.
[9]赵国朕,宋金晶,葛燕,等.基于生理大数据的情绪识别研究进展[J].计算机研究与发展,2016,53(1):80-92.
[10]Demidova L,Klyueva I,Sokolova Y,et al.Intellectual approaches to improvement of the classification decisions quality on the base of the SVM classifier[J].Procedia Computer Science,2017,103:222-230.
[11]Tipping M E.Sparse bayesian learning and the relevance vector machine[J].Journal of Machine Learnig Research,2001(1):211-244.
[12]Tipping M E.The Relevance vector machine[C]//Advances in Neural Information Processing Systems,1999:652-658.
[13]Xu Xiangmin,Mao Yunfeng,Xiong Jiani,et al.Classification performance comparison between RVM and SVM[C]//IEEE International Workshop on Conference on Auti-Counterfeiting,Security,Identification,2007.
[14]柳长源.相关向量机多分类算法的研究与应用[D].哈尔滨:哈尔滨工程大学,2013.
[15]Han M,Sun L.EEG signal classification for epilepsy diagnosis based on AR model and RVM[C]//International Conference on Intelligent Control and Information Processing,2010:134-139.
[16]Huang J,Hu X,Geng X.An intelligent fault diagnosis method of high voltage circuit breaker based on improved EMD energy entropy and multi-class support vector machine[J].Electric Power Systems Research,2011,81(2):400-407.
[17]Xu J.An extended one-versus-rest support vector machine for multi-label classification[J].Neurocomputing,2011,74(17):3114-3124.
[18]Kalaivani M,Kalaivani V,Anusuya Devi V,et al.Analysis of EEG signal for the detection of brain abnormalities[C]//IJCA Proceedings of International Conference on Simulations in Computing Nexus,2014:1-6.
[19]Raju V V V,Gangamohan P,Gangashetty S V,et al.Application of prosody modification for speech recognition in different emotion conditions[C]//Region 10Conference,2017:951-954.
[20]Kadiri S R,Yegnanarayana B.Epoch extraction from emotional speech using single frequency filtering approach[J].Speech Communication,2017,86:52-63.
[21]张雪英,张婷,孙颖,等.情感语音数据库优化及PAD情感模型量化标注[J].太原理工大学学报,2017,48(3):469-474.
[22]陈曾,刘光远.脑电信号在情感识别中的应用[J].计算机工程,2010,36(9):168-170.