Title :
A Nonlinear Method of Characteristic Extraction for Underwater Target Recognition
Author :
Nan Li ; Xiu-kun Li
Author_Institution :
Coll. of Underwater Acoust. Eng., Harbin Eng. Univ., Harbin, China
Abstract :
Underwater target radiated noise signal possesses the features of non-stationary, non-Gaussian and strong background noise. It´s difficult to detect characteristics at low signal-noise ratio. Empirical Mode decomposition algorithm is used to handle tranquilization of radiation noises, and then filtered sub-band signal is fed into the improved model of stochastic resonance. By changing internal noise intensity of the system, enhancement of the weak periodic signal is realized under the synergies of system, signal and noise. The simulation results show that the weak signal power spectrum value is improved nearly 25 dB when the algorithm is used for detecting characteristics of actual underwater signal.
Keywords :
feature extraction; filtering theory; object recognition; background noise; characteristic extraction; empirical mode decomposition algorithm; filtered subband signal; internal noise intensity; nonlinear method; periodic signal; radiation noise tranquilization; signal power spectrum; signal-noise ratio; underwater target radiated noise signal; underwater target recognition; Gaussian distribution; Noise measurement; Resonant frequency; Stochastic resonance; Time-domain analysis; White noise; Empirical mode decomposition; Period line spectrum; Radiated noise; Stochastic resonance;
Conference_Titel :
Computational Intelligence and Communication Networks (CICN), 2014 International Conference on
Print_ISBN :
978-1-4799-6928-9
DOI :
10.1109/CICN.2014.80
