基于稀疏表示的NMF抗混响方法  

Research on anti-reverberation method of NMF based on sparse representation

作　　者：李青[1,2] 潘成胜 杨阳 丁元明[1,2] LI Qing;PAN Cheng-sheng;YANG Yang;DING Yuan-ming(Communication and Network Laboratory,Dalian University,Dalian 116600,China;College of Information Engineering,Dalian University,Dalian 116600,China;School of Electronic and Information Engineering,Nanjing University of Information Science and Technology,Nanjing 210000,China)

机构地区：[1]大连大学通信与网络重点实验室,辽宁大连116622 [2]大连大学信息工程学院,辽宁大连116622 [3]南京信息工程大学电子与信息工程学院,江苏南京210000

出　　处：《舰船科学技术》2023年第17期129-134,共6页Ship Science and Technology

基　　金：国家自然科学基金资助项目(61901079)。

摘　　要：在浅海环境中,由于受到混响的影响,主动声呐接收到的信号混淆不清。针对上述问题,提出一种基于稀疏表示的非负矩阵分解(non-negative matrix factorization,NMF)抗混响方法。利用稀疏表示方法处理主动声呐回波信号,然后根据信号的稀疏性,构建基于非负矩阵分解的Kullback-Leibler(KL)问题,通过梯度下降法给出迭代规则,进而得到了目标信号矩阵中的协方差估计。仿真结果表明,相对其他去混响方法,该方法能够有效抑制混响,提高对水下目标的识别率。In the shallow sea environment,due to the influence of the reverberation,the signal received by the active sound was confusing.In response to the above issues,the article proposes a method of non-negative matrix decomposition based on sparsely expressed sparse expressions(NMF).The above method uses the sparse representation method to process the active sound echo signal,and then builds the Kullback-Leibler(KL)problem based on the sparseness of the signal.The collaborative difference estimation in the signal matrix.The simulation results show that relative to other reverberation methods,this method can effectively suppress the reverberation and improve the recognition rate of underwater targets.

关 键 词：主动声呐 混响抑制 稀疏表示 非负矩阵分解 

分 类 号：U666.7[交通运输工程—船舶及航道工程]