电子测量与仪器学报

陈瑞娟,邓光华,刁小飞,孙智慧,王慧泉.基于 MIC 心率变异性特征选择的情感识别研究[J].电子测量与仪器学报,2020,34(12):57-65

基于 MIC 心率变异性特征选择的情感识别研究

Research on emotion recognition based on feature selectionof heart rate variability by MIC algorithm

DOI：

英文关键词:heart rate variability emotion recognition maximal information coefficient feature selection

基金项目:国家自然科学基金(81901789)、国家重点研发计划课题(2017YFC0806402)、天津市科技计划项目(18ZXRHSY00200)资助

作者	单位
陈瑞娟	1.天津工业大学生命科学学院
邓光华	1.天津工业大学生命科学学院
刁小飞	1.天津工业大学生命科学学院
孙智慧	1.天津工业大学生命科学学院
王慧泉	1.天津工业大学生命科学学院

Author	Institution
Chen Ruijuan	1.School of Life Sciences, Tiangong University
Deng Guanghua	1.School of Life Sciences, Tiangong University
Diao Xiaofei	1.School of Life Sciences, Tiangong University
Sun Zhihui	1.School of Life Sciences, Tiangong University
Wang Huiquan	1.School of Life Sciences, Tiangong University

摘要点击次数: 826

全文下载次数: 744

中文摘要:

心率变异性分析能够在情感识别中发挥重要作用,为了建立心电与情感类别之间的精准模型,提出了基于最大信息系数(maximal information coefficient,MIC)的特征选择方法。使用 Aubt 数据库和设计情感诱发实验进行研究,首先提取了心率变异性时域、频域、非线性及时频域 40 个特征参数,然后基于 MIC 方法结合支持向量机、随机森林、K 近邻算法进行情感建模。结果显示,基于 MIC 特征选择方法,使用 Aubt 数据库针对唤醒度、效价、4 类情感的分类准确度分别为 90%、89%、84%,并进一步选用皮尔森相关系数、ANOVA 特征选择方法与 MIC 进行对比;诱发实验数据中的多种一对一情感识别率均高于 75%。结果表明基于 MIC 特征选择方法能够显著提高分类准确度,对基于心电信号进行情感识别具有重要意义。

英文摘要:

Heart rate variability analysis can play an important role in emotion recognition. In order to establish an accurate model between ECG and emotion categories, a feature selection method based on maximum information coefficient (MIC) is proposed. In this paper, the Aubt database and the design of emotional induction experiments are used for research. First, 40 features based on heart rate variability in time domain, frequency domain, nonlinear and time-frequency domain were extracted, then emotion modelingwas conducted based on the MIC method combined with support vector machine, random forest and K nearest neighbor algorithm. The results show that based on the MIC feature selection method,the classification accuracy of the Aubt database for arousal, valence, and four emotions is 90%, 89%, and 84%, respectively. And further choose Pearson correlation coefficient, ANOVA feature selection method to compare with MIC. In the induced experimental data,the correct classification rate ofmultiple one-to-one emotion recognition is higher than 75%. It shows that the MIC feature selection method can significantly improve the classification accuracy, which is of great significance for emotion recognition based on ECG signals.

查看全文查看/发表评论下载PDF阅读器