Although researchers have developed robust approaches for estimating, location, and user identity, estimating user activities has proven much more challenging. Human activities are so complex and dynamic that it's often unclear what information is even relevant for modeling activities. Robust approaches to recognize user activities requires identifying the relevant information to be sensed and the appropriate sensing technologies. In our effort to develop an approach for automatically estimating hospital-staff activities, we trained a discrete hidden Markov model (HMM) to map contextual information to a user activity. We trained the model and evaluated it using data captured from almost 200 hours of detailed observation and documentation of hospital workers. In this article, we discuss our approach, the results, and how activity recognition could empower our vision of the hospital as a smart environment.

Children with autism have difficulty sustaining their selective attention during therapy sessions. Attention management techniques involve the use of verbal and visual prompting, annotated on top of the physical objects used during therapies. Here, the authors explore how augmented reality helps integrate the physical and digital worlds, mimicking current strategies for attention management in autism. They describe their design decisions when developing the Mobile Object Identification System (Mobis), a mobile augmented reality application that lets teachers superimpose digital content on top of physical objects. The results of a five-week deployment study demonstrate that Mobis is useful and easy to use, increases the sustained and selective attention of children with autism, and elicits positive emotions during therapies. This article is part of a special issue on managing attention.