A method of life signal identification based on BP neural network

Ultra wide band (UWB) life detector can penetrate walls and ruins to detect whether there is a sign of life on the rear. This device will play an important role in anti-terrorism and disaster relief. But because the life signal is low frequency, quasi-periodic, non-stationary and low signal to noise ratio (SNR) and so on, such features restrict the accuracy of identifying life signals. According to the characteristics of life signals, back propagation (BP) neural network is chosen as the life signal recognition method, and the proper network structure is designed with appropriate network parameters selected. Simulation results show that, using BP neural network method can greatly improve the life signal identification accuracy; it is proved to be an effective method in the practical project.