Adaptive Model Fusion for Wearable Sensors Based Human Activity Recognition

Wearable sensors based activity recognition is a research area where inertial measurement units based information is used to recognize human activities. While every human is different the usage of adaptive and personal models has become more attractive approach in the area. In this article, a novel solution is presented how to combine the human independent and personal models more effectively using self-organizing maps based distance as a selection criteria. Moreover, the selection can be done in real time and within wearable device itself. The results show that the approach clearly outperforms the posterior probability based approach in preserving the high recognition accuracy regardless of which model is used. In addition, it does not require so much memory capacity than Euclidean distance based selection.