Proposal of a consensus builder for environmental condition setting in spaces where people with various preferences coexist

Some services for controlling devices in homes and offices through networks have been proposed. Such services are required to achieve user satisfaction. However, it is difficult to set actuator parameters that build consensus among all users in an environment including users with various preferences. In this study, we propose a device control system for consensus building in such an environment. The proposed system constructs a user stress detection model through parameters for devices, sensor values, and biodata. A user stress detection model is constructed in an office testbed. This study focuses on the influence of temperature and light color on user stress, so we vary the parameters for air conditioning and light color when collecting experimental data. We use the LF/HF ratio used for general stress detection. Experimental results show user stress value related to environmental temperature for each user. We also show that user stress is reduced by changing light color. In addition, we construct a user stress detection model using experiment data, and propose a control algorithm for consensus building.