A Localization Method Based on Principal Component Analysis

A DV-Hop localization method works by transforming the distance to all beacon nodes from hops to units of length measurement using the average size of a hop as a correction factor. Despite its advantages, however, the location results based on DV-Hop is not very stable since the variations of the topology of the beacon nodes and noise. Multicollinearity among the beacon nodes will be found with beacon nodes become into line. If we still use ordinary least square to form the model, then the multicollinearity is harmful to the estimate of the parameters, expanding the error of the model, and destroying the robustness of the model. In this work, we propose a novel approach that uses principal component analysis in order to eliminate the impact of multicollinearity and noise while reducing its localization error. Theoretical analysis and simulation results show that the proposed method has better performance than the ordinary DV-Hop algorithms.