An Adaptive Update Algorithm for Fingerprint Database Based on Validity Detection

Maintaining the accuracy of fingerprint-based indoor positioning requires ensuring the validity of the fingerprint database. The main task of fingerprint database maintenance is to detect and update invalid data in a timely manner. In this paper, we address the problem of invalid fingerprint data with the fingerprint matching effectiveness evaluation method and the adaptive update algorithm of fingerprint database. The experimental design and field data collection and analysis were conducted in two typical experimental scenarios: an indoor basketball court and an indoor school building. Experiments with real measurements show that the proposed algorithm improves the performance of updating the fingerprint database in real time and robustness.