基于PCA-SVM多生理信息融合的情绪识别方法

doi:10.6040/j.issn.1672-3961.0.2014.120

山东大学学报(工学版) ›› 2014, Vol. 44 ›› Issue (6): 70-76.doi: 10.6040/j.issn.1672-3961.0.2014.120

基于PCA-SVM多生理信息融合的情绪识别方法

李发权, 杨立才, 颜红博

山东大学控制科学与工程学院, 山东济南 250061

收稿日期:2014-04-23 修回日期:2014-09-24 出版日期:2014-12-20 发布日期:2014-04-23
通讯作者: 杨立才(1962-),男,山东莘县人,博士,教授,博士生导师,主要研究方向为生物医学信号的检测与处理,人工智能与智能控制等.E-mail:yanglc@sdu.edu.cn E-mail:yanglc@sdu.edu.cn
作者简介:李发权(1989-),男,山东临沂人,硕士研究生,主要研究方向为生物医学信号检测分析.E-mail:limo0314@sina.com

An emotion recognition method of multiphysiological information fusion based on PCA-SVM

LI Faquan, YANG Licai, YAN Hongbo

School of Control Science and Engineering, Shandong University, Jinan 250061, Shandong, China

Received:2014-04-23 Revised:2014-09-24 Online:2014-12-20 Published:2014-04-23

摘要/Abstract

摘要： 为了有效解决情绪识别过程中多种生理信息融合所导致的运算量过大的问题,提出了一种主成分分析(principal component analysis, PCA)与支持向量机(support vector machine, SVM)相结合的情绪识别方法。利用主成分分析法,求出各特征对情绪识别效果的影响权重,通过阈值法选择权重较大的特征组成新的特征子集,从而减少SVM的输入特征维数,降低算法的运算量。试验结果表明,该方法可以有效提高算法的执行效率。

关键词: 情绪识别, 支持向量机, 特征子集, 主成分分析, 信息融合

Abstract: To reduce the complexity of the emotion-recognition algorithm caused by multiphysiological information fusion an emotion recognition method based on Principal Component Analysis (PCA) and Support Vector Machine (SVM) was proposed. The influential weights of emotion recognition were calculated for initial features by the PCA, and the features of which the weights were larger than a certain threshold were selected to compose the new feature set. Thus the dimension of the classifierinputs could be reduced so that the complexity of the algorithm will be simplified. Experimental results showed that the PCA-SVM algorithm for sentiment analysis could effectively improve the efficiency of emotion recognition.

Key words: information fusion, principal component analysis, support vector machine, emotion recognition, feature subset

中图分类号:

TP391.3

李发权, 杨立才, 颜红博. 基于PCA-SVM多生理信息融合的情绪识别方法[J]. 山东大学学报(工学版), 2014, 44(6): 70-76.

LI Faquan, YANG Licai, YAN Hongbo. An emotion recognition method of multiphysiological information fusion based on PCA-SVM[J]. JOURNAL OF SHANDONG UNIVERSITY (ENGINEERING SCIENCE), 2014, 44(6): 70-76.

参考文献

[1] LOIC K, GINEVRA C, GEORGE C. Multimodal emotion recognition in speech-based interaction using facial expression, body gesture and acoustic analysis[J]. Multimodal User Interfaces, 2010, 3(1-2):33-48.
[2] 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, 4(31):595-597. NIE Ran, WANG Xiaowei, DUAN Ruonan, et al. A survey on EEG based emotion recognition[J]. Chinese Journal of Biomedical Engineering, 2012, 4(31):595-597.
[3] JONGHWA K, ELISABETH A. Emotion Recognition based on physiological changes in music Listening[J]. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2008, 12(30):2067-2069.
[4] 牛晓伟,刘光远. 生理信号情感识别的遗传算法研究[J]. 计算机工程与应用, 2009, 45(2):233-235. NIU Xiaowei, LIU Guangyuan. Research on genetic algorithm based on emotion recognition with physiological signals[J]. Compute Engineering and Applications, 2009, 45(2):233-235.
[5] WU C, WEI W, LIN J. Speaking effect removal on emotion recognition from facial expressions based on eigenface conversion[J]. IEEE Transactions on Multimedia, 2013, 8(15):1732-1735.
[6] 刘月华. 典型生理信号综合测量及情绪识别研究[D]. 上海:上海交通大学,2011. LIU Yuehua. Typical physiological signal measurement and emotion recognition study[D]. Shanghai: Shanghai Jiaotong University, 2011.
[7] 党宏社,郭楚佳,张娜. 信息融合技术在情绪识别领域的研究展望[J]. 计算机应用研究, 2013, 12(30):3536-3538. DANG Hongshe, GUO Chujia, ZHANG Na. Research progress of emotion recognition in information fusion[J]. Application Research of Computers, 2013, 12(30):3536-3538.
[8] CHEN H,LIU G. A novel feature selection method for affective recognition based on pulse signal[C]//Proceedings of the Fourth International Symposium on Computational Intelligence and Design. Hangzhou, China:[s.n.], 2011:110-113.
[9] PARK J, KIM J, OH Y. Feature vector classification based speech emotion recognition for service robots[J]. IEEE Transactions on Consumer Electronics, 2009, 3(55):1590-1592.
[10] JOHANNES W, FLORIAN L, ELISABETH A, et al. Exploring fusion methods for multimodal emotion recognition with missing data[J]. IEEE Transactions on Affective Computing, 2011, 4(2):206-212.
[11] 孙洪央. 基于多生理信号的压力状态下情绪识别方法研究[D]. 上海:上海交通大学,2013. SUN Hongyang. Study on emotion recognition methods of stress state based on physiological signals[D]. Shanghai: Shanghai Jiaotong University, 2013.
[12] 计智伟,胡珉,尹建新. 特征选择算法综述[J]. 电子设计工程,2011,19(9):46-51. JI Zhiwei, HU Min, YIN Jianxin. A survey of feature selection algorithm[J]. Electronic Design Engineering, 2011, 19(9):46-51.
[13] RANI P, LIU C, SARKAR N, et al. An empirical study of machine learning techniques for affect recognition in human-robot interaction[J]. Pattern Anal Applic,2006, 9(1):58-69.
[14] 韩小孩,张耀辉. 基于主成分分析的指标权重确定方法[J].四川兵工学报, 2012, 33(10):124-126. HAN Xiaohai, ZHANG Yaohui. Method to determine the index weight based on principal component analysis[J]. Journal of Sichuan Ordnance, 2012, 33(10):124-126.
[15] QUAN C, WAN D, ZHANG B, et al. Reduce the dimensions of emotional features by principal component analysis for speech emotion recognition[C]//Proceedings of the 2013 IEEE/SICE International Symposium on System Integration.Kobe, Japan: IEEE, 2013:222-224.
[16] 徐雅静,汪远征. 主成分分析应用方法的改进[J]. 数学的实践与认识,2006,36(6):68-75. XU Yajing, WANG Yuanzheng. Improving the application of principal component analysis method[J]. Mathematics in Practice and Theory, 2006, 36(6):68-75.
[17] 丁世飞,齐丙娟,谭红艳. 支持向量机理论与算法研究综述[J]. 电子科技大学学报, 2011, 40(1):2-7. DING Shifei, QI Bingjuan, TAN Hongyan. An overview on theory and algorithm of support vector machines[J], Journal of University of Electronic Science and Technology of China, 2011, 40(1):2-7.
[18] 徐红敏,王海英. 支持向量机回归算法及其应用[J]. 北京石油化工学院学报, 2010, 18(1):62-63. XU Hongmin, WANG Haiying. The support vector machine regression algorithm and its application[J]. Journal of Beijing Institute of Petro-chemical Technology, 2010, 18(1):62-63.
[19] PANAGIOTIS C, LEONTIOS H. A novel emotion elicitation index using frontal brain asymmetry for enhanced EEG-based emotion recognition[J]. IEEE Transactions on Information Technology in Biomedicine, 2011, 5(15):737-743.
[20] 杨瑞请,刘光远. 基于BPSO的四种生理信号的情感状态识别[J]. 计算机科学, 2008, 35(3):137-138. YANG Ruiqing, LIU Guangyuan. Emotion recognition using four physiological signals based on BPSO[J]. Computer Science, 2008, 35(3):137-138.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于PCA-SVM多生理信息融合的情绪识别方法

An emotion recognition method of multiphysiological information fusion based on PCA-SVM

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

多维度评价

本文评价

推荐阅读 10

[1]	李颖,王建坤. 基于监督图正则化和信息融合的轻度认知障碍分类方法[J]. 山东大学学报 (工学版), 2023, 53(4): 65-73.
[2]	孟银凤,李庆方. 基于多元函数主成分表示的识别学习[J]. 山东大学学报 (工学版), 2022, 52(3): 1-8.
[3]	孟银凤,杨佳宇,曹付元. 函数型数据的分裂转移式层次聚类算法[J]. 山东大学学报 (工学版), 2022, 52(1): 19-27.
[4]	亓晓燕,刘恒杰,侯秋华,刘啸宇,谭延超,王连成. 融合LSTM和SVM的钢铁企业电力负荷短期预测[J]. 山东大学学报 (工学版), 2021, 51(4): 91-98.
[5]	孙东磊,王艳,于一潇,韩学山,杨明,闫芳晴. 基于BP神经网络的短期光伏集群功率区间预测[J]. 山东大学学报 (工学版), 2020, 50(5): 70-76.
[6]	刘帅,王磊,丁旭涛. 基于Bi-LSTM的脑电情绪识别[J]. 山东大学学报 (工学版), 2020, 50(4): 35-39.
[7]	马昕,王雪. 基于Laplacian支持向量机和序列信息的microRNA-结合残基预测[J]. 山东大学学报 (工学版), 2020, 50(2): 76-82.
[8]	梁志祥,刘晓明,牟颖,刘玉田. 基于深度学习的新能源爬坡事件预测方法[J]. 山东大学学报 (工学版), 2019, 49(5): 24-28.
[9]	严云洋,张慧珍,刘以安,高尚兵. 基于GMM与三维LBP纹理的视频火焰检测[J]. 山东大学学报 (工学版), 2019, 49(1): 1-9.
[10]	李兴,侯振杰,梁久祯,常兴治. 基于线性加速度的多节点人体行为识别[J]. 山东大学学报 (工学版), 2018, 48(6): 56-66.
[11]	叶明全,高凌云,万春圆. 基于人工蜂群和SVM的基因表达数据分类[J]. 山东大学学报(工学版), 2018, 48(3): 10-16.
[12]	唐乐爽,田国会,黄彬. 一种基于DSmT推理的物品融合识别算法[J]. 山东大学学报(工学版), 2018, 48(1): 50-56.
[13]	韩学山,王俊雄,孙东磊,李文博,张心怡,韦志清. 计及空间关联冗余的节点负荷预测方法[J]. 山东大学学报(工学版), 2017, 47(6): 7-12.
[14]	周志杰,赵福均,胡昌华,王力,冯志超,刘涛源. 基于证据推理的航天继电器故障预测方法[J]. 山东大学学报(工学版), 2017, 47(5): 22-29.
[15]	刘岩,李幼军,陈萌. 基于EMD和SVM的抑郁症静息态脑电信号分类研究[J]. 山东大学学报(工学版), 2017, 47(3): 21-26.