A support system for context awareness in a group home using sound cues

In this study, we have proposed an audio notification system that indicates the real-time situation of persons in a group home environment without visual surveillance. In this paper, we present an approach to predict the events in a real living environment and notify them using sound cues. The notification system comprises a predicting and a notification function. The predicting function estimates a personpsilas real-time situation using a Bayesian network and sensed information; the notification function informs recipients of the predicted situation and the confidence level of the prediction by means of sound cues. We use natural sounds as sound cues, considering the use of our system at a group home of elderly people. We estimate the usefulness of our method under a simple test environment. The results show that the method is useful for monitoring persons by employing sound effects that are appropriate to usage environments. As a future study, we will conduct a field test on an implemented system and improve it for practical use in a group home.