基于矩阵补全的无线传感器网络收集数据重建方法

摘要

许多自然科学研究都利用无线传感器网络收集环境数据.收集数据的完整性和准确性决定科研结果的可靠性.然而,数据收集过程中通常会出现数据丢失和数据错误等问题.为提升收集数据的可用性,需要从含有错误元素的不完整数据集中恢复丢失的数据.利用环境数据的低秩特性,提出一种基于弹性网正则化的结构化噪声矩阵补全算法(EnRMC),既能实现丢失数据的有效恢复,也能精确判断收集到错误数据的传感器节点.利用真实数据进行仿真,实验结果表明算法性能优于现有算法,能以较高的精度重建环境数据.%Many natural science researches use Wireless Sensor Networks(WSNs)to collect environmental data,and use it for scientific research. The integrity and accuracy of the collected data determine the reliability of the results. However,data loss and error usually occur during the process of data collection. Therefore,it is necessary to design an effective method to recover the missing data from the incomplete and erroneous sensory data. Based on the low-rank feature of environmental data, we design an Elastic-net Regularization based on Matrix Completion with Structural Noise( EnRMC) algorithm for reconstructing data. The proposed approach can not only effectively recover the missing data,but also exactly detect the sensor nodes with erroneous data. The simulation results show that the proposed algorithm is superior to the existing algorithms,and can reconstruct the environmental data with high precision.