An Accurate WiFi Indoor Positioning Algorithm for Complex Pedestrian Environments

This paper proposes a precise WiFi fingerprinting indoor positioning algorithm for complex pedestrian environments. We transform the disturbed received signal strength (RSS) from the original space to latent space using the improved probabilistic linear discriminant analysis (PLDA). In the latent space, Bayes rule is used to calculate the posterior probability of the similarity between the test point and the reference points, and the
${K}$
reference points with the highest posterior probability are weighted to estimate the position. Actual on-site experiments involving three floors demonstrate that the mean localization error of the proposed algorithm is 1.38 m, which outperforms the Horus algorithm by 29% under the same test conditions. In addition, by studying the variability of mean value of RSS in different pedestrian environments, the fingerprint maps in different states of personnel movement are simulated. By using which, the average localization error of the proposed algorithm increases slightly to 1.63m, while the workload required during the offline training phase is significantly reduced.