Matrix Completion Optimization for Localization in Wireless Sensor Networks for Intelligent IoT

作     者：Nguyen, Thu L. N. Shin, Yoan 

作者机构：Soongsil Univ Sch Elect Engn Seoul 156743 South Korea 

出 版 物：《SENSORS》 (传感器)

年 卷 期：2016年第16卷第5期

页      面：722-722页

核心收录：

学科分类：0710[理学-生物学] 071010[理学-生物化学与分子生物学] 0808[工学-电气工程] 07[理学] 0804[工学-仪器科学与技术] 0703[理学-化学] 

基　　金：Human Resources Development program of the KETEP grant - Korea government MOTIE NRF - Korean government MSIP [2014R1A5A1011478] 

主　　题：Internet of Things wireless sensor network localization Euclidean distance matrix completion semi-definite programming modified Newton method 

摘      要：Localization in wireless sensor networks (WSNs) is one of the primary functions of the intelligent Internet of Things (IoT) that offers automatically discoverable services, while the localization accuracy is a key issue to evaluate the quality of those services. In this paper, we develop a framework to solve the Euclidean distance matrix completion problem, which is an important technical problem for distance-based localization in WSNs. The sensor network localization problem is described as a low-rank dimensional Euclidean distance completion problem with known nodes. The task is to find the sensor locations through recovery of missing entries of a squared distance matrix when the dimension of the data is small compared to the number of data points. We solve a relaxation optimization problem using a modification of Newton s method, where the cost function depends on the squared distance matrix. The solution obtained in our scheme achieves a lower complexity and can perform better if we use it as an initial guess for an interactive local search of other higher precision localization scheme. Simulation results show the effectiveness of our approach.