Skip to Main Content
Node localization is a main application of wireless sensor networks. However, the measurement error and noise in a real environment make the positioning of information nonlinear and have a great effect on the performance of localization methods. In this paper, we propose a novel isometric mapping (Isomap) node localization algorithm based on partial least squares (PLS-Isomap). For topological stability, the critical outlier points are eliminated by comparing the contribution rate of all data points. Then, we employ the PLS method to solve the Isomap. The adoption of PLS reduces the noise sensitivity of Isomap, which achieves solution by least squares. Moreover, the proposed approach applies a projection method to construct a new kernel matrix between new and original data points. Compared with Isomap and the multidimensional scale method, experimental and simulation results indicate that the PLS-Isomap algorithm has good topological stability, robustness, positioning accuracy, and lower computational complexity.