摘要
Detection of weak underwater signals is an area of general interest in marine engineering.A weak signal detection scheme was developed; it combined nonlinear dynamical reconstruction techniques, radial basis function (RBF) neural networks and an extended Kalman filter (EKF).In this method chaos theory was used to model background noise.Noise was predicted by phase space reconstruction techniques and RBF neural networks in a synergistic manner.In the absence of a signal, prediction error stayed low and became relatively large when the input contained a signal.EKF was used to improve the convergence rate of the RBF neural network.Application of the scheme to different experimental data sets showed that the algorithm can detect signals hidden in strong noise even when the signal-to-noise ratio (SNR) is less than -40d B.
基金
Supported by China Postdoctoral Science Foundation No.20080441183
作者简介
Jun-yang candidate Pan was born in 1982. He is a PhD at Northwestern University. His research interests chaos theory and its application acoustic signal processing. Polytechnical are focused on in underwater Corresponding author Email： panjunyang@gmail.comJing Han was born in 1980. He received PhD degree in Information and Communication Engineering at Northwestern Polytechnical University in 2008. His research interests include ditgital communications theory, statistical signal processing and wireless networks, and their applications to mobile radio and underwater acoustic communication systems.Shi-e Yang was born in 1931. He is an academician of Chinese Academy of Engineering. He is a professor of Harbin Engineering University and works in the field of underwater acoustic engineering
