Indoor Localization with Fingerprint Feature Extraction

Abstract

We propose an indoor localization method using FPFE (Fingerprint Feature Extraction) with Bluetooth Low Energy (BLE) beacon fingerprints. FPFE apples either AE or PCA to extract features of beacon fingerprints and then measures the similarity between the features using the concept of the Minkowski distance. FPFE selects k RPs with the k smallest Minkowski distances for estimating the position of the target device. Experiments are conducted to evaluate the localization error of FPFE. The experimental results show that the FPFE achieves an average error of 0.68 m which is better than those of other related BLE fingerprint-based localization methods.