| C5.0决策树算法在基于混沌特征的情绪识别中的应用 |
| |
| 引用本文： | 贺方,;聂春燕.C5.0决策树算法在基于混沌特征的情绪识别中的应用[J].长春大学学报,2014(10):1320-1325. |
| |
| 作者姓名： | 贺方 ;聂春燕 |
| |
| 作者单位： | [1]长春理工大学电子信息工程学院,长春130022; [2]长春大学电子信息工程学院,长春130022 |
| |
| 基金项目： | 教育部“春晖计划”项目（Z2014136）; 吉林省自然科学基金项目（201215110） |
| |
| 摘 要： | 生理信号的某些特征参数在不同情绪下会有不同的变化规律,在此基础上,对4种不同情绪(喜、怒、哀、乐)下的多生理信号(心电信号、肌电信号、呼吸信号、皮电信号)的混沌特征参量进行情绪识别。文中采用C5.0决策树分类器算法,以样本的属性作为节点,以属性的取值作为分支的树结构,解决了大样本情况下的机器学习问题。研究结果表明,C5.0决策树这种算法在基于混沌特征参量进行情绪识别方面具有较高的识别率。
|
| 关 键 词： | 多生理信号 C.决策树 情绪识别 |
Application of C5.0 Decision Tree Algorithm in Emotion Recognition Based on Chaos Characteristics |
| |
| Institution: | HE Fang, NIE Chunyan (1. School of Electronics and Information Engineering, Changchun University of Science and Technology, Changchun 130022, China; 2. School of Electronic Information Engineering, Changchun University, Changchun 130022, China ) |
| |
| Abstract: | Some characteristic parameters of physiological signals have different change rules under different emotions, on this basis, the chaotic characteristic parameters of multiple physiological signals （ ECG, EMG, RSP and SC） under the four different emotions （joy, anger, sadness, pleasure） are recognized. This paper adopts C5.0 decision tree classifier algorithm and solves the machine learning problem in the condition of large samples by taking the sample properties as nodes and the attribute value as the tree structure of the branch. Research results show that C5.0 decision tree algorithm has higher recognition rate in emotion recognition based on cha- otic characteristic parameters. |
| |
| Keywords: | multiple physiological signals C5 0 decision tree emotion recognition |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
