Measuring Uncertainty in Signal Fingerprinting with Gaussian Processes Going Deep

TL;DR

This paper examines the limitations of Gaussian Processes in modeling signal uncertainty for indoor positioning and proposes Deep Gaussian Processes as a superior alternative, validated through simulations and real data.

Contribution

It introduces Deep Gaussian Processes for better uncertainty measurement in signal fingerprinting, addressing the shortcomings of standard GPs.

Findings

DGP provides more accurate uncertainty estimates than GP.

DGP improves positioning accuracy in simulated and real datasets.

Standard GP models underestimate uncertainty in signal fingerprinting.

Abstract

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.