Spatial interpolation method of position fingerprint based on improved CPN network

In order to build a more accurate off-line fingerprint database, it is often necessary to repeat the sampling in different time periods. The more space points in the fingerprint database means the more work of building the database. Sufficient location fingerprint data is the guarantee of positioning accuracy, but the work of building the database is often repeated and time-consuming. In this paper, the K-Means++ algorithm is used to improve the structure of the Counter Propagation neural network and uses the improved Counter Propagation Neural network to interpolate the data of location fingerprint database to enrich the signal value of fingerprint database, so as to reduce the workload of establishing fingerprint database and improve the accuracy of location. Experiments show that using this method to improve the process of establishing traditional fingerprint database can effectively improve the accuracy of location.