Digital Signal Modulation Classification With Data Augmentation Using Generative Adversarial Nets in Cognitive Radio Networks

Abstract

Automated modulation classification plays a very important part in cognitive radio networks. Deep learning is also a powerful tool that we could not overlook its potential in addressing signal modulation recognition problem. In our last work, we propose a new data conversion algorithm in order to gain a better classification accuracy of communication signal modulation, but we still believe that the convolution neural network (CNN) can work better. However, its application to signal modulation recognition is often hampered by insufficient data and overfitting. Here, we propose a smart approach to programmatic data augmentation method by using the auxiliary classifier generative adversarial networks (ACGANs). The famous CNN model, AlexNet, has been utilized to be the classifier and ACGAN to be the generator, which will enlarge our data set. In order to alleviate the common issues in the traditional generative adversarial nets training, such as discriminator overfitting, generator disconverge, and mode collapse, we apply several training tricks in our training. With the result on original data set as our baseline, we will evaluate our result on enlarged data set to validate the ACGAN’s performance. The result shows that we can gain 0.1~6% increase in the classification accuracy in the ACGAN-based data set.