Unsupervised adaptation to on-body sensor displacement in acceleration-based activity recognition

A common assumption in activity recognition is that the system remains unchanged between its design and its posterior operation. However, many factors can affect the data distribution between two different experimental sessions including sensor displacement (e.g. due to replacement or slippage), and lead to changes in the classification performance. We propose an unsupervised adaptive classifier that calibrates itself to be robust against changes in the sensor location. It assumes that these changes are mainly reflected in shifts in the feature distributions and uses an online version of expectation-maximisation to estimate those shifts. We tested the method on a synthetic dataset as well as on two activity recognition datasets modeling sensor displacement. Results show that the proposed adaptive algorithm is robust against shift in the feature space due to sensor displacement.

Published in:
2011 15Th Annual International Symposium On Wearable Computers (Iswc), 71-78
Presented at:
IEEE International Symposium on Wearable Computers, ISWC 2011, San Francisco, June 12-15, 2011
Ieee Computer Soc Press, Customer Service Center, Po Box 3014, 10662 Los Vaqueros Circle, Los Alamitos, Ca 90720-1264 Usa

Note: The status of this file is: Involved Laboratories Only

 Record created 2011-03-15, last modified 2018-01-28

External link:
Download fulltext
Rate this document:

Rate this document:
(Not yet reviewed)