Distances for WiFi Based Topological Indoor Mapping
This work addresses indoor localization for applications like navigation or smart environments, but it is incremental as it focuses on comparing existing distance measures rather than introducing a new method.
The paper tackled the problem of indoor localization and mapping using WiFi signals by comparing distance measures between likelihoods of received signal strength indicators, finding that the Earth Mover's Distance was most beneficial and, when combined with kernel density estimation, successfully retained the topological structure of rooms in a real-world office scenario.
For localization and mapping of indoor environments through WiFi signals, locations are often represented as likelihoods of the received signal strength indicator. In this work we compare various measures of distance between such likelihoods in combination with different methods for estimation and representation. In particular, we show that among the considered distance measures the Earth Mover's Distance seems the most beneficial for the localization task. Combined with kernel density estimation we were able to retain the topological structure of rooms in a real-world office scenario.