Region clustering based fingerprint model for flexible Wi-Fi fingerprinting

Abstract

Wi-Fi fingerprint, a mainstream technology of Indoor Location Base Service (ILBS), estimates location through a radiomap that places received signal strength (RSS) as AP and location. However, the semi-regularity of the radiomap due to the diversity of the service area limits the fingerprint locally. To solve this problem, in this paper, we propose a Region Clustering based Fingerprint Model that combines a Region Clustering algorithm and a Region Fingerprint network that enables an integrated Wi-Fi fingerprint. The proposed model consists of RCA, which extracts regions from the global radiomap and selects regions, and RFN, which estimates locations regardless of the size of regions. The proposed RCA divides the service area into optimal regions in the offline phase using clustering and standardizes the radio map by matching each area to the same size. Also, it selects a standardized radio map in the online phase and delivers it to the positioning network. In addition, the proposed RFN estimates the location through reference pointwise Bi-LSTM. Through this, the proposed RCF model is capable of flexible fingerprinting in any size of the service area and can provide stable positioning in terms of performance.