Research on Improved Multidimensional Scaling Localization Algorithm for Wireless Sensor Network
暂无分享,去创建一个
Wireless sensor networks, which are energy limited, low hardware configuration and proneness to invalidation, puts a high demand on the positioning algorithm. Therefore the improved multidimensional scaling (IMDS) algorithm is proposed. In IMDS, firstly, local positioning areas (LPA) are established by an adaptive search algorithm. So the centralized multidimensional scaling algorithm is changed into a distributed algorithm. Then the shortest path distances between nodes on LPA are corrected with the geometric correction method (GCM) and adjusting weight correction method (AWCM). The distances between nodes become more accurate. Finally, with information of the public nodes of LPA and anchor nodes, we get the wireless sensor nodes coordinates through coordinate transformation by the SMACOF algorithm and the classical multidimensional scaling algorithm.
[1] J. Leeuw. Applications of Convex Analysis to Multidimensional Scaling , 2000 .
[2] Ying Zhang,et al. Localization from connectivity in sensor networks , 2004, IEEE Transactions on Parallel and Distributed Systems.