Open AccessWeak signal estimation in chaotic clutter using wavelet analysis and symmetric LS-SVM regression
Author(s) -
Hongyan Xing,
Jin Tian-Li
Publication year - 2010
Publication title -
wuli xuebao
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.199
H-Index - 47
ISSN - 1000-3290
DOI - 10.7498/aps.59.140
Subject(s) - clutter , chaotic , pattern recognition (psychology) , computer science , support vector machine , artificial intelligence , lorenz system , wavelet , signal (programming language) , noise (video) , algorithm , mathematics , radar , telecommunications , image (mathematics) , programming language
This article examines the theory of phase space reconstruction in complicated nonlinear system and further proposes a new methodan advanced Least Square Support Vector Machine (LS-SVM) modelto detect weak signals from a chaotic clutter. This method functions in following sequences1) db3 wavelet decomposition of the signals2) LS-SVM predictionwhich includes increasing the symmetry constraint and improving the kernel function3) Reconstruction. It is established a one-step predictive model that detects the weak signalincluding transient signal and period signalsfrom the predictive error in the chaotic sequences. It is illustrated in the experimentwhich is conducted to detect weak signals from Lorenz chaotic background and Sea Clutterthat 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 modelsthe new method presents great value in prediction accuracy and detection threshold.