Bi, X., 2020. A method for modulation recognition of maritime search and rescue communication signal based on neural network. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Research, Special Issue No. 103, pp. 847–850. Coconut Creek (Florida), ISSN 0749-0208.

In order to improve the recognition rate of traditional modulation recognition method of maritime search and rescue communication signal, the modulation recognition method of maritime search and rescue communication signal based on neural network was proposed. The spectrum feature and cumulative quantity extracted from maritime search and rescue communication signal were used as the input. The revised linear unit was used as neuron activation function, and the cross entropy was used as the loss function. In the depth neural network modulation recognizer, the convolution neural network and cyclic neural network were established. Simulation results show that the proposed method can effectively improve the modulation recognition rate of maritime search and rescue communication signal.