Indoor Location Fingerprinting Algorithm Based on Path Loss Parameter Estimation and Bayesian Inference

For indoor positioning methods based on Wi-Fi fingerprint, a high- density location fingerprint database usually needs to be constructed to ensure high-precision positioning requirements. At the same time, when the indoor area is huge or the number of reference points (RPs) is large and densely distributed, the computational burden of the online phase will be increased. To solve the above two problems, we propose an indoor location fingerprinting algorithm based on path loss parameter estimation and Bayesian inference (FA-PEBI). In the off-line phase, first, we collect location fingerprints from a few RPs in different rooms; second, the location fingerprints collected are filtered; third, the path loss parameters (PLPs) in different rooms are trained by using a logarithmic distance path loss (LDPL) model; and finally, predict the fingerprint information of the other locations in that room based on the trained parameters. In the online phase, the real-time fingerprint information of the user is first filtered, and then, the room where the user is located is predetermined by using the Bayesian inference method. Subsequently, the correspondingfingerprintdatabase is selected tomatch based on the regional adaptive selection (RAS) algorithm. Eventually, the ultimate location of the user is obtained based on the Manhattan distance. The experimental results show that the proposed algorithm improves the localization accuracy by at least 16% comparedwith other existing methods, both in the Wireless Insite simulation data and MAN dataset, and still outperforms theK -nearest neighbor (KNN) algorithm when the fingerprint collection effort in the off- line phase is reduced by half.

Automated summary

For indoor positioning based on Wi-Fi fingerprint, a high-density location fingerprint database is needed. To solve the problems of database size and computational burden, an algorithm based on path loss parameter estimation and Bayesian inference is proposed. Experimental results show that the algorithm improves localization accuracy by at least 16% and outperforms the K-nearest neighbor algorithm when fingerprint collection effort is reduced by half.