WiFi-based indoor positioning system in a multilevel building

This study presents the development of an Indoor Positioning System (IPS) in a three-storey building using WiFi signals. The IPS design is integrated into an Android mobile application using Android Studio. The RSSI signals are detected from WiFi APs using a developed mobile application. The mobile device uses these measurements to localize the position of the user within the building. The study aims to investigate and implement two positioning algorithms, which are the k Nearest Neighbors (kNN) algorithm and the Particle Swarm Optimization (PSO) algorithm. In addition, the Density-based spatial clustering of applications with noise (DBSCAN) was also integrated into the IPS design to remove noise from the path of the mobile device to further improve the accuracy of the system. The results of the study showed that the integration of PSO and DBSCAN algorithms in the IPS yielded an accuracy of 69.27% within 1 meter and an average deviation of 0.94 meter. The performance of the IPS designs under varying environmental conditions was also examined to analyze the effects of the dynamic environment on the system’s performance