Feasibility of emotion recognition from breath gas information

This paper proposes a smart gas sensing system to achieve emotion recognition using breath gas information. A breath gas sensing system is designed by using a quartz crystal resonator with a plasma-polymer film as a sensor. To collect breath gas data under emotional state, psychological experiments are carried out using a dental rise to excite emotions. In computational experiment of emotion recognition, two emotions of comfortableness and no emotion are considered and the machine learning-based approach such as an artificial neural network (ANN) and a support vector machine (SVM) is investigated. The obtained average emotion recognition rates are 47.5% using the ANN and 67.5% using the SVM, respectively. Experimental results show that using breath gas information is feasible and the machine learning-based approach is well suited for this task.