Accurate Entrance Position Detection Based on Wi-Fi and GPS Signals Using Machine Learning
This addresses a specific localization challenge for users navigating into buildings, but it is incremental as it builds on existing signal-based methods.
The paper tackled the problem of detecting the main entrance of buildings by combining GPS signal drop and Wi-Fi signal strength increase, achieving an accuracy of one meter in experiments.
This paper aims at detecting an accurate position of the main entrance of the buildings. The proposed approach relies on the fact that the GPS signals drop significantly when the user enters a building. Moreover, as most of the public buildings provide Wi-Fi services, the Wi-Fi received signal strength (RSS) can be utilized in order to detect the entrance of the buildings. The rationale behind this paper is that the GPS signals decrease as the user gets close to the main entrance and the Wi-Fi signal increases as the user approaches the main entrance. Several real experiments have been conducted in order to guarantee the feasibility of the proposed approach. The experiment results have shown an interesting result and the accuracy of the whole system was one meter