Towards Active Learning Interfaces for Multi-Inhabitant Activity Recognition

Semi-supervised approaches for activity recognition are a promising way to address the labeled data scarcity problem. Those methods only require a small training set in order to be initialized, and the model is continuously updated and improved over time. Among the several solutions existing in the literature, active learning is emerging as an effective technique to significantly boost the recognition rate: when the model is uncertain about the current activity performed by the user, the system asks her to provide the ground truth. This feedback is then used to update the recognition model. While active learning has been mostly proposed in single-inhabitant settings, several questions arise when such a system has to be implemented in a realistic environment with multiple users. Who to ask a feedback when the system is uncertain about a collaborative activity? In this paper, we investigate this and more questions on this topic, proposing a preliminary study of the requirements of an active learning interface for multi-inhabitant settings. In particular, we formalize the problem and we describe the solutions adopted in our system prototype.