基于稀疏贝叶斯学习的协同进化时间序列缺失数据预测算法  

Missing Data Prediction Algorithm Based on Sparse Bayesian Learning in Coevolving Time Series

作　　者：宋晓祥 郭艳 李宁 余东平 SONG Xiao-xiang;GUO Yan;LI Ning;YU Dong-ping(College of Communications Engineering,Army Engineering University of PLA,Nanjing 210007,China)

机构地区：[1]陆军工程大学通信工程学院

出　　处：《计算机科学》2019年第7期217-223,共7页Computer Science

基　　金：国家自然科学基金(61571463,61371124,61472445);江苏省自然科学基金(BK20171401)资助

摘　　要：针对大多数已有算法在预测协同进化时间序列中的缺失数据时只适用于缺失数据较少情况的问题,提出了一种高效的缺失数据预测算法。首先,应用压缩感知理论,将协同进化时间序列中的缺失数据预测问题建模成多稀疏向量恢复问题;其次,从稀疏表示向量是否足够稀疏和感知矩阵是否满足有限等距特性两个方面分析了模型的性能;最后,针对协同进化时间序列的特点设计了一种基于稀疏贝叶斯学习的高效恢复算法,该算法可以通过学习得到部分支持信息,从而同时解决多个稀疏向量的恢复问题。仿真结果表明,所提算法可以同时有效地预测出多个时间序列中的缺失数据。In view of most of the existing algorithms in predicting the missing data in the coevolving time series are only feasible to be applied to the case where only a low ratio of collected data are missing,an efficient missing data prediction method was proposed in this paper.Firstly,the compressive sensing theory is applied to model the missing data prediction problem in the coevolving time series to the problem of multiple sparse vectors recovery.Secondly,the validity of the model is analyzed from two aspects:whether the sparse representation vector is sufficiently sparse and the sensing matrix satisfies the restricted isometry property.Finally,the novel recovery algorithm based on sparse Bayesian lear-ning,which can solve multiple sparse vector recovery problems by learning some support information,is designed for the characteristics of coevolving time series.Simulation results show that the proposed algorithm can effectively predict the missing data in multiple time series simultaneously.

关 键 词：协同进化时间序列 缺失数据 稀疏表示向量 感知矩阵 稀疏贝叶斯学习 

分 类 号：TN911.7[电子电信—通信与信息系统]