Application Research of 3D MSVR-DV-Hop Algorithm Based on Node Filtering

Abstract

Wireless sensor network has been widely used as an important means of perceiving and monitoring the real environment. Node location algorithm is the key supporting technology for the normal operation of wireless sensor network nodes. To achieve higher positioning accuracy and improve the adaptability to the network, a beacon-based MSVR-DV-Hop (Multidimensional Support Vector Regression-DV-Hop) algorithm is proposed in three-dimensional scenes. The three stages of hop acquisition, distance estimation and coordinate calculation in classical DV-Hop algorithm are improved, and simulation experiments and result analysis are carried out in three-dimensional scene. The positioning accuracy of this algorithm is significantly improved compared with other algorithms in three-dimensional scenes, positioning error fluctuations are significantly improved in different anisotropic scenes, and positioning error fluctuations are stable in different anisotropic scenes, which has better adaptability and accuracy. Positioning errors in three-dimensional scenes are reduced by at least 56% compared to the classical three-dimensional DV-Hop algorithm and 12% compared to the LMSVR algorithm.