摘要:
基于复杂非线性系统的相空间重构理论,提出一种改进的提取混沌背景中微弱信号的最小二乘支持向量机(LS-SVM)的方法.通过将信号以db3小波逐层分解,进行LS-SVM预测,再进行重构,同时通过增加对偶约束项、改进核甬数的方法,建立改进的混沌序列的一步预测模型,从预测误差中检测潭没在混沌背景中的微弱目标信号(包括周期和瞬态信号).最后以Lorenz系统和真实海杂波数据作为混沌背景噪声进行了仿真实验,实验表明此方法能够有效地检测出混沌背景噪声中的微弱信号、抑制噪声对混沌背景信号的影响,与传统RBF神经网络和LS-SVM预测方法相比,预测精度和检测门限方面的性能有显著的提高.
Abstract:
This article examines the theory of phase space reconstruction in complicated nonlinear system and further proposes a new method, an advanced Least Square Support Vector Machine (LS-SVM) model, to detect weak signals from a chaotic clutter. This method functions in following sequences: 1) db3 wavelet decomposition of the signals,2) LS-SVM prediction, which includes increasing the symmetry constraint and improving the kernel function, 3) Reconstruction. It is established a one-step predictive model that detects the weak signal, including transient signal and period signals, from the predictive error in the chaotic sequences. It is illustrated in the experiment, which is conducted to detect weak signals from Lorenz chaotic background and Sea Clutter,that this proposed method is highly effective to detect weak signals from a chaotic background as well as minimize the impact of noise on weak signals. Compare to conventional RBF neural network and LS-SVM models, the new method presents great value in prediction accuracy and detection threshold.
首页
登录
注册
下载: