Modulation recognition method for extracting time-frequency image features by joint entropy and pre-training CNN

Abstract

The invention belongs to the technical field of radar emitter signal modulation recognition, and particularly relates to a modulation recognition method for extracting time-frequency image features byjoint entropy and pre-training CNN. The method includes the following steps: firstly, performing time-frequency transformation on 9 types of radar signal sets to be identified to obtain a time-frequency image; and then based on a pre-training convolutional neural network model imagenet-vgg-verydeep-19 provided by the MatConvNet official website, constituting an FT-VGGNet-fc6 feature migration extraction module from an input layer to an fc6 full connection layer; and then, sending an adjusted image to the feature migration extraction module, and outputting time-frequency image features of radar signals; performing graying on the adjusted image, and manually extracting the Renyi entropy of the processed image; and then, dividing a training set and a test set according to a certain proportion, and selecting the training set to train an SVM classifier; and finally, adopting the trained SVM classifier to recognize the training set of time-frequency images, and adopting a data set composedof 9 types of radar signals with multiple signal-to-noise ratios to verify a recognition rate of an FT-VGGNET-fc6-SVM classifier.

Description

technical field [0001] The invention belongs to the technical field of radar radiation source signal modulation recognition, and in particular relates to a modulation recognition method for extracting time-frequency image features by combining entropy and pre-trained CNN. Background technique [0002] Radar emitter signal modulation identification is an important link in electronic countermeasures and electronic reconnaissance, and plays a very important role in electronic warfare. The commonly used radar radiation source signal modulation recognition methods include the signal modulation recognition method based on five parameters, the intrapulse modulation recognition method based on time-frequency images, and the signal modulation recognition method based on CNN. [0003] The traditional modulation recognition method based on five parameters (carrier frequency, pulse arrival time, pulse amplitude, pulse width, and pulse arrival direction) can obtain other characteristic p...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to propose a modulation recognition method that combines entropy and pre-trained CNN to extract time-frequency image features, utilizes CNN to automatically extract image features to realize automatic feature extraction, and applies principal component analysis (PCA) to reduce the output feature dimension and improve the system Effectiveness, combining the features after dimensionality reduction with artificially extracted Renyi entropy to improve the recognition rate of the system under the condition of low signal-to-noise ratio, and applying SVM to solve the problem of low training accuracy of deep network small samples, and finally realize accurate and fast detection of radar signals identify

Images