一种欠定混合模型下的信源个数估计算法  

An Estimation of Source Signals Number Based on The Underdetermined Mixed Model

作　　者：葛娟 韩锋 杨洋 曾小芳 GE Juan;HAN Feng;YANG Yang;ZENG Xiaofang(Science and Technology on Electronic Information Control Laboratory,Chengdu 610036,China)

机构地区：[1]电子信息控制重点实验室,成都610036

出　　处：《电子信息对抗技术》2021年第2期23-26,共4页Electronic Information Warfare Technology

摘　　要：针对欠定混合模型的信源个数估计问题,提出一种基于时频变换与势函数聚类的混合信号信源个数估计新算法。首先介绍欠定信号混合模型;然后通过时频变换将观测信号变换到时频域进而构造变量构成聚类特性;最终采用势函数聚类的方法估计出信源个数。公式推导和仿真分析都证明该算法可以很好地估计出信源个数。仿真实验结果表明,新提出的算法与其它相同混合模型的算法相比具有更好的性能。In order to solve the problem of source number estimation under the under-determined mixed model,a new algorithm based on time-frequency transformation and potential function clustering is proposed.First,the mixed model of the under-determined mixed signals is introduced.Then,the observed signals are transformed to time-frequency domain by time-frequency transformation,and then variables are constructed to form clustering characteristics.Finally,the potential function clustering algorithm is adopted to estimate the number of source signals.Formula derivation and simulation analysis show that the proposed algorithm can estimate the number of sources well.Compared with other algorithms with the same hybrid model,the proposed algorithm has better performance.

关 键 词：欠定混合模型 信源个数估计 时频变换 势函数聚类 

分 类 号：TN971.1[电子电信—信号与信息处理]