Maximum convergence algorithm for WiFi based indoor positioning system

WiFi-based indoor positioning is widely exploited thanks to the existing WiFi infrastructure in buildings and built-in sensors smartphones. The techniques for require high-density training data archive high accuracy with computation complexity. In this paper, approach systems which called maximum convergence algorithm proposed find accurate location by strongest receiver signal small cluster K nearest neighbours (KNN) of other clusters. Also, K-mean clustering deployed each access point reduce complexity offline databases. Moreover, pedestrian dead reckoning (PDR) method Kalman filter information from received strength (RSS) inertial are applied fingerprinting increase efficiency mobile object's position. different experiments performed compare others using KNN PDR. recommended framework demonstrates significant proceed based on results. average precision system can be lower than 1.02 meters when testing laboratory environment an area 7x7 m three points.