Learning system for adapting users with user´s state classification by vital sensing

In ambient information systems, not only extracting human behavior with a sensor network but also adaptive autonomous interaction between the environment and humans is an important function. In this paper, we propose a reinforcement learning methodology for acquiring suitable interaction for each person´s daily behavior. This time, we used vital sensors to detect and classify a user´s condition. In an experiment, we show the feasibility of the proposed methodology.