Modulation signal classification method and system based on circular system limited crossing visibility graph networking

Abstract

A modulation signal classification method based on circular system limited crossing visibility graph networking comprises the following steps: S1, collecting I / Q modulation signals, processing the collected I / Q modulation signals, and converting the dual-channel I / Q modulation signals into four-channel signals; s2, respectively converting the four-channel signals into weighted directed network graphs by adopting a circle system limited crossing visual graph networking method; s3, performing feature extraction on the four weighted directed network graphs to obtain four feature vectors, and performing space expansion on the feature vectors to obtain a fusion feature vector of each I / Q modulation signal; s4, training the modulation signal classification model, wherein the classification precision is smaller than a preset threshold value, adjusting hyper-parameters in the circular system limited crossing visible graph networking method, repeating the steps S2 to S3 until the classificationprecision is larger than or equal to the preset threshold value, obtaining the trained modulation signal classification model, and finishing classification of the I / Q modulation signals through the trained classification model. According to the invention, the classification precision of the I / Q modulation signals can be improved.

Description

technical field [0001] The invention relates to the technical field of I / Q modulation signal classification, in particular to a modulation signal classification method and system for building a network based on circular system finite traversal visual graphs. Background technique [0002] Time series widely exist in the real world, such as the Internet, communication, biology, finance and other fields. Among them, in the field of communication, the modulation pattern recognition of I / Q modulated signals has received extensive attention. How to extract the hidden information from a large amount of signal data to improve the classification accuracy is one of the basic tasks of current modulated signal data mining. [0003] Regarding the classification of modulated signals, in the prior art, it is impossible to identify I / Q modulated signals with a lower signal-to-noise ratio, such as signal modulation modes below -10 dB. In order to solve this technical problem, researchers ha...

AI Technical Summary

Problems solved by technology

However, the network diagram obtained by these network construction algorithms is relatively simple, and it is impossible to establish a network diagram containing more effective information from time series according to different tasks or user needs.

At the same time, there is no method in the prior art to apply the visual graph algorithm to the classification of radio modulation signals

Images