Measuring Uncertainty in Signal Fingerprinting with Gaussian Processes Going Deep
This work addresses uncertainty modeling in indoor positioning, an incremental improvement for location-based services.
The paper tackles the problem of measuring uncertainty in signal fingerprinting for indoor positioning by identifying a pitfall in using Gaussian Processes and proposing Deep Gaussian Processes as a more informative alternative, achieving improved uncertainty measurement as evaluated on simulated and real datasets.
In indoor positioning, signal fluctuation is highly location-dependent. However, signal uncertainty is one critical yet commonly overlooked dimension of the radio signal to be fingerprinted. This paper reviews the commonly used Gaussian Processes (GP) for probabilistic positioning and points out the pitfall of using GP to model signal fingerprint uncertainty. This paper also proposes Deep Gaussian Processes (DGP) as a more informative alternative to address the issue. How DGP better measures uncertainty in signal fingerprinting is evaluated via simulated and realistically collected datasets.