Multi-sensor-based ambient sensing system for the estimation of comfort/discomfort during desk work

A multi-sensor-based ambient sensing system is proposed for estimating the user's comfort/discomfort in response to the lighting condition during desk work. The user's comfort/discomfort is estimated according to facial expression, body sway, writing motion and frequency of drinking measured by sensors embedded in the environment. The purpose of the system is to make a robust estimation even under a lighting condition that induces different feelings of comfort depending on the person. To this end, optimal sensor information is selected adaptively depending on the lighting condition among sensor information measured by multiple sensors. It is experimentally confirmed that the user's comfort/discomfort can be estimated even in such mild lighting conditions. The recognition rate of user's comfort on a seven-point scale is 72% when using only ambient sensors (i.e., the subject does not wear sensors)P.