Discovery and recognition of unknown activities

Human activity recognition plays a significant role in enabling pervasive applications as it abstracts low-level noisy sensor data into high-level human activities, which applications can respond to. In this paper, we identify a new research question in activity recognition -- discovering and learning unknown activities that have not been pre-defined or observed. As pervasive systems intend to be deployed in a real-world environment for a long period of time, it is infeasible, to expect that users will only perform a set of pre-defined activities. Users might perform the same activities in a different manner, or perform a new type of activity. Failing to detect or update the activity model to incorporate new patterns or activities will outdate the model and result in unsatisfactory service delivery. To address this question, we explore the solution space and propose an estimation-based approach to not only discover and learn new activities over time, but also benefit from no need to store any historic sensor data.