Complex Activity Recognition using Wearable Sensors

In this project, we develop a wearable system to recognize simple (i.e., sequential) and complex (i.e., interleaved and concurrent) activities in real life. As far as we know, this is the first reported work of a pattern mining approach to complex activity recognition using wearable sensors. We also propose a real-time, hierarchical model to recognize both simple gestures and complex activities.

This work has been reported in PerCom 2009 and IEEE Transactions on Knowledge and Data Engineering.