Joint Positioning and Radio Map Generation Based on Stochastic Variational Bayesian Inference for FWIPS

Fingerprinting based WLAN indoor positioning system (FWIPS) provides a promising indoor positioning solution to meet the growing interests for indoor location-based services (e.g., indoor way finding or geo-fencing). FWIPS is preferred because it requires no additional infrastructure for deploying an FWIPS achieving the position estimation by reusing the available WLAN and mobile devices, and is capable of providing absolute position estimation. For fingerprinting based positioning (FbP), a model is created to provide reference values of observable features (e.g., signal strength from access points (APs)) as a function of location during offline stage. One widely applied method to build a complete and an accurate reference database(i.e. radio map (RM)) for FWIPS is carrying out a site survey throughout the region of interest (RoI). Along the site survey, the readings of received signal strength (RSS) from all visible APs at each reference point (RP) are collected. This site survey, however, is time-consuming and labor-intensive, especially in the case that the RoI is large (e.g., an airport or a big mall). This bottleneck hinders the wide commercial applications of FWIPS (e.g., proximity promotions in a shopping center). To diminish the cost of site survey, we propose a probabilistic model, which combines fingerprinting based positioning (FbP) and RM generation based on stochastic variational Bayesian inference (SVBI). This SVBI based position and RSS estimation approach has three properties: i) being able to predict the distribution of the estimated position and RSS, ii) treating each observation of RSS at each RP as an example to learn for FbP and RM generation instead of using the whole RM as an example, and iii) requiring only one time training of the SVBI model for both localization and RSS estimation. We validate the proposed approach via experimental simulation and analysis. Compared to the FbP approaches based on a single-layer neural network (SNN), deep neural network (DNN) and k nearest neighbors (k N N), the proposed SVBI based position estimation outperforms them. The reduction of root mean squared error of the localization is up to 40% comparing to that of SNN based FbP. Moreover, the cumulative positioning accuracy, defined as the cumulative distribution function of the positioning errors, of the proposed FbP and k N N are 92% and 84% within 4 m, respectively. The improvement of the positioning accuracy is up to 8%. Regarding the performance of SVBI based RM generation, it is comparable to that of the manually collected RM and adequate for the applications, which require room level positioning accuracy.