Targets Detection in Sea Clutter Based on Echo State Network
Targets Detection in Sea Clutter Based on Echo State Network
复制标题
基于回波状态网络的海杂波目标检测
DOI：
10.4028/www.scientific.net/aef.4.255
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Fang Su
中科院分区：
文献类型：
--
作者：
Zhan Xu;Jianwei Wan;Gang Li;Fang Su
提出了一种预测海杂波时间序列和检测嵌入海杂波的目标的新方法。该方法实际上是一种称为回声状态网络(ESN)的递归神经网络。采用递推最小二乘(RLS)算法更新ESN的输出权值。对一组来自IPIX雷达数据的时间序列进行了检验。数值实验表明，该网络在纯海杂波数据中具有较高的预测精度。此外，ESN的实际数据与预测值之间的均方误差(MSE)可以用来有效地检测目标。
A novel method to predict the sea clutter time series and detect target embedded in sea clutter is presented. The method is actually a recurrent neural network called an echo state network (ESN). A recursive least squares (RLS) algorithm is used for updating the output weights of ESN. A set of time series from IPIX radar data is tested. Numerical experiments reveal that the proposed network shows higher prediction precision in pure sea clutter data. Moreover, the mean squared error (MSE) between real-life data and prediction value by ESN can be used to detect target effectively.
DOI：
10.1109/oceans.2004.1405751
发表时间：
2004-11
期刊：
Oceans '04 MTS/IEEE Techno-Ocean '04 (IEEE Cat. No.04CH37600)
影响因子：
--
作者：
K. Ishu;T. V. D. Zant;V. Becanovic;P. Plöger
通讯作者：
K. Ishu;T. V. D. Zant;V. Becanovic;P. Plöger