Underwater acoustic communication signal modulation mode identification method based on support vector machine

Abstract

The invention provides an underwater acoustic communication signal modulation mode identification method based on a support vector machine. The method comprises the following steps: preprocessing an underwater acoustic signal containing complex ocean background noise through a nonlinear piecewise exponential function; extracting the time domain L-Z complexity feature, the frequency domain fractalbox dimension feature and the time-frequency domain Renyi entropy feature of the underwater acoustic signal as the input of an SVM classifier, and then selecting a proper kernel function and parameters to complete the modulation mode recognition of the underwater acoustic communication signal. According to the method, the influence of complex ocean background noise is eliminated through a nonlinear transformation preprocessing method, three features in a time domain, a frequency domain and a time-frequency domain are extracted to form feature vectors; compared with a single-feature method, themethod improves the performance obviously. The method can be used for monitoring and identifying shallow sea underwater acoustic communication signals, perceives underwater acoustic communication behaviors of enemies in advance, and improves the coastal defense strength of China.

Description

technical field [0001] The invention relates to the field of information signal processing, in particular to an underwater acoustic communication signal recognition method, involving theories of underwater signal processing, feature recognition, and machine learning. Background technique [0002] The 21st century is an era of ocean development. With the rapid development of science and technology, the ocean has gradually become an important field of human development. Among them, the identification of the modulation mode of underwater acoustic communication signals under non-cooperative conditions is an important research direction in the field of marine security. [0003] In recent years, all major military powers in the world are gradually strengthening their defense and monitoring of the maritime domain. At present, the most advanced underwater monitoring network is Seaweb in the United States, which can use the underwater acoustic network to transmit high-quality data in...

AI Technical Summary

Problems solved by technology

Due to the characteristics of underwater acoustic channels such as strong multi-channel, narrow bandwidth, long delay, and non-Gaussian background noise, traditional modulation method identification methods cannot meet the requirements of underwater acoustic signal modulation identification.

Images