A Constrained KNN Indoor Positioning Model Based on a Geometric Clustering Fingerprinting Technique

The common algorithms based on RSSI presently available are unstable in the indoor environment. Hence，a constrained KNN positioning algorithm with geometrical information via clustering fingerprints is proposed to resolve this issue. Firstly，the geometric clustering fingerprints are built according to the structural layout. Then，the concept of geometric strength of sporadic(USS) for a sample point’s geometry characterization is introduced. The value of USS is used for identifying the RP control network structure in which the mobile terminal is located to dynamically choose the keyparameter K for KNN. When the nearest point(NP) is decided，an optimal polygon constraint condi-tion is constructed to choose the latter （K一1)neighbour points. It can be summarized as a constrain-ed KNN indoor localization model based on a geometric clustering fingerprinting technique. The re-cults of series of tests indicate that the new algorithm can more effectively estimate the location of amobile terminal. Clustered fingerprints plays a key role in improving the position accuracy，thus theimpact of this new KNN algorithm should not be overlooked.