基于缺失信号的图重构  

GRAPH RECONSTRUCTION BASED ON INCOMPLETE DATA

作　　者：韩诗期 王俊义[1,2] 李然[2,3] Han Shiqi;Wang Junyi;Li Ran(School of Information and Communication,Guilin University of Electronic Technology,Guilin 541004,Guangxi,China;Key Laboratory of Cognitive Radio and Information Processing,Ministry of Education,Guilin 541004,Guangxi,China;School of Telecommunication Engineering,Xidian University,Xi’an 710071,Shaanxi,China)

机构地区：[1]桂林电子科技大学信息与通信学院,广西桂林541004 [2]“认知无线电与信号处理”教育部重点实验室,广西桂林541004 [3]西安电子科技大学通信工程学院,陕西西安710071

出　　处：《计算机应用与软件》2022年第5期78-84,109,共8页Computer Applications and Software

基　　金：国家自然科学基金项目(61966007);“认知无线电与信号处理”教育部重点实验室基金项目(CRKL180106);“广西无线宽带通信与信号处理重点实验室”基金项目(GXKL06180107)。

摘　　要：在使用图信号处理工具之前需要知道信号的底层图,即信号的空间结构。但在实际场景中,尤其是对于缺失信号而言,图未必是已知的。对此提出一种缺失信号的图学习模型。利用信号的空间变分和稀疏惩罚项来学习图,同时利用空间变分和时间变分及学到的图重构信号,重复迭代直至目标函数值最小时得到最优解。实验结果表明在信号缺失的情况下,该模型依然能够合理学习到图结构,并且在实测温度数据中聚类和信号重构的效果要优于常用的聚类算法和图信号重构算法。Before using the graph signal processing(GSP)tools,it is essential to construct a meaningful underlying graph,namely structure of data.However,such a graph is not always available,especially for incomplete signal.This paper proposes a graph learning model for deficient data.The spatio variation and sparse penalty term of signal were used to learn the graph.The spatio variation,temporal variation and the graph had been learned were applied to recover the data.The condition for obtaining the optimal solution was the minimum value of the objective function.The experimental results show that simply using defective data can also reasonably infer the graph and behave better in temperature data than common clustering and graph signal reconstruction algorithms.

关 键 词：图信号处理 图学习 概率图模型 图信号重构 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]