Routine Modeling with Time Series Metric Learning
This work addresses the challenge of non-intrusive and privacy-preserving activity recognition for applications like health monitoring, though it is incremental as it adapts existing sequence-to-sequence models to a new metric learning task.
The paper tackles the problem of recognizing human activity patterns by modeling routines as a metric learning problem, proposing an SS2S architecture based on sequence-to-sequence models to learn distances between time series from inertial data, and shows that clustering with this distance recovers daily routines.
Traditionally, the automatic recognition of human activities is performed with supervised learning algorithms on limited sets of specific activities. This work proposes to recognize recurrent activity patterns, called routines, instead of precisely defined activities. The modeling of routines is defined as a metric learning problem, and an architecture, called SS2S, based on sequence-to-sequence models is proposed to learn a distance between time series. This approach only relies on inertial data and is thus non intrusive and preserves privacy. Experimental results show that a clustering algorithm provided with the learned distance is able to recover daily routines.