基于PSO-kNN算法与多生理参数的压力状态下情绪识别  

Study of Emotion Recognition under Stress Based on Physiological Signals by PSO-kNN Method

作　　者：孙洪央[1] 徐祖洋[1] 王静[1] 雷沛[1] 吴开杰[1] 柴新禹[1] 

机构地区：[1]上海交通大学生物医学工程学院,上海市200240

出　　处：《中国医疗器械杂志》2013年第2期79-83,共5页Chinese Journal of Medical Instrumentation

基　　金：国家重点基础研究发展计划(973项目:2011CB7075003);国家高技术研究发展计划(863项目:2009AA04Z326);国家科技支撑计划(2008BAI65B03);上海市科委重大科技攻关项目(10231204300);上海市体育局科技攻关项目(11JT010)

摘　　要：压力能诱发兴奋、厌烦、恐惧等多种不同的情绪,不同程度的某种压力能诱发不同程度的情绪。本文通过设计情绪诱发实验,分别诱发出被试平静、兴奋、厌烦、恐惧情绪以及低度、中度、高度三种紧张情绪程度。基于这些情绪状态下被试的心率、呼吸率等六种生理信号,去除基线预处理后进行特征提取,结合粒子群优化算法对特征进行选择,采用k近邻算法对压力状态下的不同情绪及紧张情绪程度进行分类。实验结果表明,通过基线去除及粒子群特征选择优化后k近邻分类,与传统k近邻分类相比,具有更好的识别效果。In this paper, experiments were designed for inducing neutral, terrified, excited, annoying emotions, and also low, middle, high, three levels of tension emotions of stress state, respectively. Based on the multi physiological signals generated by the subjects in emotions, such as heart rate and respiration rate and so on, we extracted features from these data which had been eliminated the baseline. Then the Particle Swarm Optimization method was adopted to optimize the features selection from the features of multi physiological signals, and combined with k-Nearest Neighbor algorithm, different emotions and varying degree tensions were classified. The result shows that the classification accuracy of the kNN method with SPO and baseline eliminated is better than the traditional kNN method.

关 键 词：情感计算 情绪识别 心理压力 PSO KNN 

分 类 号：TP301[自动化与计算机技术—计算机系统结构]