WKNN indoor location algorithm based on zone partition by spatial features and restriction of former location

High-precision indoor location algorithm using fingerprint highly relies on the accuracy of database. This paper proposes a WKNN indoor location algorithm based on spatial characteristics partition and former location restriction. In this proposed system, target space of large area is divided into multiple partitions by its spatial characteristics, solving the problem that one fingerprint database cannot achieve total coverage. Also, the restricted relationship between the former and the present position are introduced to increase the quality of chosen candidate reference points, and thus improve the smoothness of the estimation results obviously. A large number of indoor positioning experiments show that this algorithm could effectively improve the indoor positioning accuracy when compared with the traditional WKNN.