Real-time work environment optimization using multimodal media and body sensor network

Abstract

The ambient environment has a significant influence on our cognition and behavior. We envision an adaptive space that improves our productivity and wellbeing at work and related settings by forming a closed control loop around our responses to the environment's properties. To explore this vision, we created a responsive office named Mediated Atmospheres (MA) that can transform its ambiance as driven by a network of physiological sensors. We conducted a user study investigating near-natural use of the system with a panel of non-experts and experts in the field of the built environment (N = 9). Two control modes were implemented: (1) Learning Mode, where the system learns from the user's response and (2) Preset Mode, where the office responds to the user's physiological state based on predefined rules. Our result showed that using the Learning Mode, participants were able to increase the amount of time in which they were focused when the system optimized for both focus and stress restoration rather than focus alone. Participants were able to double the time in which they achieved high-stress restoration when their environment optimized for restoration rather than focus. Both application modes achieved high System Usability Scores (SUS > 82), which is evidence that our method for compressing the multivariate control problem into a multidimensional model of the user's physiological state is a viable approach for closed-loop control of a multimodal environment. We offer a discussion on the preferred level of control for an office application.