Transient Weak Signal Detection in Chaos Based on RBF Neural Network

Detection of weak signal submerged in chaos is discussed in this paper. Classical statistic detection theory regards chaotic noise as random signal, which weakens the performance of signal detection. Based on chaotic dynamic mechanism, using neural network to establish the forecast model of chaotic time series, restructuring its phase space, for the neural network´s powerful ability of studying and nonlinear processing and local predictability of chaos, the method of neural network prediction and detection transient weak signal in chaos is proposed, the results of theoretical analysis and simulation indicate the effectiveness of the RBFNN predictor. Through reconstructing the phase space of chaotic signal, it can approach to the chaotic dynamics characteristic of the original chaotic system from the jammed chaotic signals. The infection degree of noise is evaluated in quantity in the end. Results show that the proposed RBFNN predictor can provide a further improvement in signal detection performance