Optimal placement of access points for indoor positioning using a genetic algorithm

Currently, building accurate indoor positioning systems is a crucial challenge facing scientific researchers. One of the most effective metrics that increases positioning accuracy is the placement of access points (APs) in the service area. In this paper, we propose a genetic algorithm based framework, GenoPlacement, to solve APs placement problem. GenoPlacement handles different types of building walls such as concrete, brick, and glass. Our objective is to find an APs setup with unique fingerprints at each signal test point (STP) while maximizing diversity among these fingerprints. To evaluate GenoPlacement, we compare the proposed objective function with the traditional one which maximizes the received signal strength at each STP. Then, we compare GenoPlacement with two nominated approaches. The results confirm that building indoor positioning system considering the optimal places of APs decreases the positioning error down to four meters at 90% precision.