A framework for adaptive interaction support based on quality of context information

There is a growing interest in academia and industry for de signing and developing ambient multimedia environments. Numerous sensors, devices and multimedia services are avail able in such environment to support users in their lives. Surprisingly, users often find it difficult in interacting with such environments due to the presence of numerous devices and services. To address this issue, context-aware implicit or automatic interaction mechanisms have been proposed to facilitate easy access of the available devices and services and reduce the cognitive load of the user. However, such implicit interactions often lead to mis-automation due to imprecision in context information. This ultimately causes distrust and dissatisfaction to the user. This paper proposes a framework that considers quality of context information to dynamically adjust the level of implicit interaction and allows a system to operate in different modes ranging from full-automation to action suggestion to simple notification. Our initial user experiments demonstrate that dynamic and alternative mode of interaction not only increases the satisfaction of the users but also helps to avoid distrust in automated actions carried out by the ambient environment under varying contexts.