邱海云
江西理工大学 赣州 341000
基金项目:国家自然科学基金(61763018)，江西省“03专项及5G项目”(20193ABC03A058)，江西省教育厅重点项目 (GJJ170493)，江西理工大学清江青年英才支持计划
详细信息
作者简介:樊宽刚：男，1981年生，博士后，副教授，研究方向为智能仪器设计、智能轨道交通、汽车电磁兼容等
邱海云：男，1994年生，硕士生，研究方向为自适应信号处理
通讯作者:樊宽刚 kuangangfriend@163.com
中图分类号:TN911.7计量
文章访问数:693
HTML全文浏览量:210
PDF下载量:49
被引次数:0
出版历程
收稿日期:2020-01-03
修回日期:2020-08-06
网络出版日期:2020-08-21
刊出日期:2021-02-23
Robust Nonnegative Least Mean Square Algorithm Based on Sigmoid Framework
Kuan’gang FAN,,Haiyun QIU
Jiangxi University of Science and Technology, Ganzhou 341000, China
Funds:The National Natural Science Foundation of China (61763018), The Special Project and 5G Program of Jiangxi Province (20193ABC03A058), The Education Department of Jiangxi Province (GJJ170493), The Program of Qingjiang Excellent Young Talents, Jiangxi University of Science and Technology
摘要
摘要:脉冲噪声会导致非负算法在迭代过程中存在过大的误差值，进而破坏算法的稳定性使其性能严重下降，对此该文提出一种基于Sigmoid框架的非负最小均方算法(SNNLMS)。该算法将传统的非负代价函数嵌入Sigmoid框架中得到新的代价函数，新的代价函数具有抑制脉冲噪声影响的特性。此外，为了增强SNNLMS算法在稀疏系统识别问题上的鲁棒性，该文还提出基于反比例函数的反比例Sigmoid非负最小均方算法(IP-SNNLMS)。仿真结果表明SNNLMS算法有效地解决了脉冲噪声造成的失调问题；IP-SNNLMS增强了算法鲁棒性，改进了算法在稀疏系统识别问题中收敛速率上的缺陷。
关键词:Sigmoid框架/
非负最小均方/
脉冲噪声/
稀疏系统识别/
反比例函数
Abstract:Impulsive noise causes nonnegative algorithms to yield excessive error during iterations, which will damage the stability of the algorithm and causes performance degradation. In the paper, a NonNegative Least Mean Square algorithm based on the Sigmoid framework (SNNLMS) is proposed. The algorithm embeds the conventional nonnegative cost function into the Sigmoid framework to receive a new cost function. The new cost function has the characteristics of suppressing the impact of impulse noise. In addition, in order to enhance the robustness of the SNNLMS algorithm under sparse system identification, the Inversely-Proportional Sigmoid NonNegative Least Mean Square (IP-SNNLMS) is proposed based on the inversely-proportional function. Simulation results demonstrate that the SNNLMS algorithm effectively solves the problem of misadjustment caused by impulsive noise. IP-SNNLMS enhances the robustness of the algorithm and improves the defect of the convergence rate of the SNNLMS algorithm under the sparse system identification.
Key words:Sigmoid framework/
NonNegative Least Mean Square (NNLMS)/
Impulsive noise/
Sparse system identification/
Inversely-proportional function
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=525dbb33-902d-484b-9a4b-bffe498c8141
