The tenth international conference on indoor positioning and indoor localization (IPIN2019) will be held September 30 – October 3 at the congress palace of Pisa, Pisa, Italy. The following oral presentation will be delivered.

Wi-Fi fingerprint-based localization is known to be prominent for indoor positioning technology; however, it is still challenging on the sustainability of its performance for long-term use due to distribution drifts of the signal strength across time.

In this paper, we propose a new scheme for solving the large cost of maintaining common Wi-Fi fingerprint-based localization with machine-learning-based way by efficient incremental learning (retraining).

Specifically, we propose a brand new retraining method, called GroupWi-Lo, that focuses on the minimization of parameter variation with respect to the incremental surveys on fingerprint (i.e., calibration).

The experimental results both in the lab and the uncontrolled environment show that GroupWi-Lo achieves competitive performance among the state-of-the-art methods, while its computational cost retains independent of the number of surveys compared with existing the semi-supervised approach and standard incremental training approach.

-presentation information-
A21 – Special session – Machine learning, October 1, 10:20-12:20
GroupWi-Lo: Maintaining Wi-Fi-based Indoor Localization Accurate via Group-wise Total Variation Regularization
Masato Sugasaki*, Kota Tsubouchi**, Masamichi Shimosaka*, Nobuhiko Nishio***,
(*Tokyo Institute of Technology, **Yahoo! Japan Corporation,  ***Ritsumeikan  University)