Remarks on Emotion Recognition from Breath Gas Information

摘要：

This paper investigates emotion recognition from breath gas information. A breath gas sensing system is designed by using a quartz crystal resonator with a plasma-polymer film as a sensor. For computational experiment of emotion recognition, the machine learning-based approach, such as artificial neural network and support vector machine, is investigated. In emotion recognition experiments by using gathered breath gas data under psychological experiments, the obtained average emotion recognition rate is 70％ for two emotions: relaxation / comfortableness (positive emotion) and stress / displeasure (negative emotion). Experimental results show that using breath gas information is feasible and the neural network or support vector machine is suited for this task.

关键词： Emotion Breath Gas sensor Neural network Support vector machine

作者: Kazuhiko Takahashi Iwao Sugimoto

作者单位: Department of Information Systems Design Doshisha University Kyoto,Japan School of Computer Science Tokyo University of Technology Tokyo,Japan

会议类型: 国际会议

会议名称: 2009 IEEE International Conference on Robotics and Biomimetics(2009 IEEE 机器人与仿生技术国际会议 ROBIO 2009)

会议地点: 桂林

会议语种:英文

页码: 938-943

在线出版日期: 2009-12-19（万方平台首次上网日期，不代表论文的发表时间）