Depth neural network system and method based on modulation mode recognition of underwater acoustic communication

Abstract

The invention provides a depth neural network system and a method based on modulation mode identification of underwater acoustic communication. The system comprises: a data preprocessing part for preprocessing data of a plurality of modulation modes transmitted through underwater acoustic communication; A first layer neural network generates a feature extraction set of the first layer according toa plurality of modulation mode data transmitted from the pretreated underwater acoustic communication; The second layer neural network generates the second layer high-level feature set; The third layer neural network generates higher level feature set, the fourth layer neural network classifies and identifies the initial data by the feature set extracted in front; The fifth layer is the neural network layer, which generates the final modulation mode judgment and outputs the identified modulation mode. The depth neural network system and method based on the modulation mode recognition of underwater acoustic communication can simulate the actual use situation, improve the use effect in the actual underwater acoustic communication, more conveniently and efficiently complete the modulation recognition of underwater acoustic communication, and improve the accuracy of recognition and judgment.

Description

technical field [0001] The invention relates to the technical field of deep learning neural networks, in particular to a deep neural network system and method based on identification of underwater acoustic communication modulation modes. Background technique [0002] Due to the complex and changeable propagation environment in underwater acoustic communication, it is usually very difficult to realize. Channel characteristics such as narrow bandwidth and inter-symbol interference (ISI) in underwater acoustic communication have a significant impact on the performance of underwater acoustic communication systems. As a key link in communication systems, modulation recognition is used in many cooperative and non-cooperative communication systems for signal recognition and demodulation. However, the low signal-to-noise ratio (SNR) and time-varying characteristics of underwater acoustic channels make signal modulation identification very difficult. Currently commonly used technol...

AI Technical Summary

Problems solved by technology

The current CNN system is mainly used in the field of image recognition, speech recognition, etc., and there are few deep neural network methods directly used in the communication field

However, the research on the method and method of using deep learning technology for underwater acoustic communication modulation recognition has not yet been fully carried out.

Images