Location Algorithm for WSNs with Mobile Anchor Node Based on Optimzed K-Nearest Neighbers

Aiming at the problem of low accuracy of node location in the local scope, a location algorithm for wireless sensor network with a mobile anchor node was proposed based on the improved k-nearest neighbor classification algorithm. The algorithm used K most similar reference nodes to calculate the coordinates of the unknown nodes. The location of the reference node is important. The Received Signal Strength Indication relative value between the unknown node and the reference node was acquired by using chi-square distance optimization. The Fisher criterion is used to select the reference nodes with the strong ability within the communication scope of unknown nodes and evaluate the error. The different weights are assigned to the reference nodes distribution, and the reference nodes with low signal intensity are deleted, and the reference nodes with shortest distance is the best. The proposed algorithm optimizes the selection of reference nodes. Experimental results show that the positioning accuracy is optimized by 14.54% with a smaller error distribution range compared with the K-Nearest Neighbor positioning algorithm.