Accuracy Enhancement of an Indoor ANN-based Fingerprinting Location System Using Particle Filtering and a Low-Cost Sensor

This paper presents an accuracy enhancement solution to mobiles location tracking systems in indoor wireless local area network (WLAN) environments. The enhancement method consists of the particle filter application to an artificial neural network (ANN) based fingerprinting technique combined with a low-cost sensor (compass). The application of the particle filter has the advantage of using information about the mobile's motion to reduce location errors (caused by the WLAN received signal strength-RSS variations) and to avoid mobile's trajectory discontinuities (caused by the static estimation of the fingerprinting technique). A digital compass has been added to the fingerprinting system to observe the mobile's heading and then improve the trajectory orientation. To apply the filtering process, two models have been proposed: non-linear and linearized filtering models. The first model is obtained from the characterization of the pedestrian's motion with the heading observation. The second model is obtained after the replacement of the heading variable, in the first model, by the pedestrian's velocities along the x and y axes. Experimental results, conducted in a specific in-building environment, showed that the application of the particle filter to the ANN-based fingerprinting system mounted with a compass improves the location accuracy, in terms of mean error, of about 39% and 50% for the cases of non-linear and linearized filtering models, respectively.

[1]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[2]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[3]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[4]  Nando de Freitas,et al.  Sequential Monte Carlo Methods in Practice , 2001, Statistics for Engineering and Information Science.

[5]  Paramvir Bahl,et al.  RADAR: an in-building RF-based user location and tracking system , 2000, Proceedings IEEE INFOCOM 2000. Conference on Computer Communications. Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies (Cat. No.00CH37064).

[6]  Juha-Pekka Makela,et al.  Indoor geolocation science and technology , 2002, IEEE Commun. Mag..

[7]  G. Kitagawa.  Monte Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models , 1996 .

[8]  C. Despins,et al.  Indoor location using received signal strength of IEEE 802.11b access point , 2005, Canadian Conference on Electrical and Computer Engineering, 2005..

[9]  Mauro Brunato,et al.  Statistical learning theory for location fingerprinting in wireless LANs , 2005, Comput. Networks.