A communication signal modulation identification method based on an auto-encoder

Abstract

The invention discloses a communication signal modulation identification method based on an auto-encoder, and belongs to the technical field of communication. The method comprises the following stepsof simulating and generating signals to be classified under various signal-to-noise ratios; preprocessing the signals to be classified; performing feature extraction on the preprocessed signal by using an auto-encoder; carrying out dimension reduction processing on the extracted features by using a kernel principal component analysis KPCA method; generating a data set, randomly generating a training sample and a test sample of each type of modulation signals according to the characteristics obtained by the dimension reduction processing, obtaining a training sample set, a test sample set and acorresponding class label set, and performing normalization processing on the data set; and training the SVM classifier by using the training sample set, inputting the test sample set into the trained classifier, and calculating an average recognition rate. Compared with a time domain feature or a frequency domain feature, the method has better anti-noise performance, the extracted features havebetter intra-class aggregation degree and inter-class separation degree, the calculation complexity is greatly reduced, and the anti-noise performance is good.

Description

technical field [0001] The invention belongs to the technical field of communication, and in particular relates to a communication signal modulation identification method based on an autoencoder. Background technique [0002] With the rapid development of communication technology, digital signal processing and other technologies, and the wide application of new technologies such as spread spectrum communication, frequency hopping communication, and satellite communication, the wireless communication environment is becoming increasingly complex, and different frequencies and adopting Communication signals with different modulation methods. Therefore, people have gradually begun to explore the use of computer-based communication electronic equipment to automatically identify the modulation type of communication signals. The modulation recognition technology of communication signals has a wide range of applications in both military and civilian applications, and has become a r...

AI Technical Summary

Problems solved by technology

[0005]According to the current research status of communication signal modulation recognition, aiming at the low signal-to-noise ratio, the current modulation recognition method generally has the problem of low recognition rate, the present invention The purpose is to provide a modulation recognition method based on an autoencoder that can improve the recognition rate at a lower SNR

Images