Abstract
With the recently explosive growth of deep learning, automatic modulation recognition has undergone rapid development. Most of the newly proposed methods are dependent on large numbers of labeled samples. We are committed to using fewer labeled samples to perform automatic modulation recognition in the cognitive radio domain. Here, a semi-supervised learning method based on adversarial training is proposed which is called signal classifier generative adversarial network. Most of the prior methods based on this technology involve computer vision applications. However, we improve the existing network structure of a generative adversarial network by adding the encoder network and a signal spatial transform module, allowing our framework to address radio signal processing tasks more efficiently. These two technical improvements effectively avoid nonconvergence and mode collapse problems caused by the complexity of the radio signals. The results of simulations show that compared with well-known deep learning methods, our method improves the classification accuracy on a synthetic radio frequency dataset by 0.1% to 12%. In addition, we verify the advantages of our method in a semi-supervised scenario and obtain a significant increase in accuracy compared with traditional semi-supervised learning methods.
Highlights
Due to fixed spectrum allocations and expanding numbers of wireless devices, spectrum resources are becoming increasingly scarce
The results of simulations show that compared with well-known deep learning methods, our method improves the classification accuracy on a synthetic radio frequency dataset by 0.1% to 12%
We provide a brief introduction to generative adversarial network (GAN), discuss their application in automatic modulation classification, and propose a suitable framework for this field
Summary
Due to fixed spectrum allocations and expanding numbers of wireless devices, spectrum resources are becoming increasingly scarce. CR emphasizes the ability to learn, meaning that CR can interact with its local communication environment and change its own transmission parameters based on the interaction. The ability to perceive the spectrum environment is called spectrum sensing [3]. Spectrum sensing is the basic function of cognitive radio systems. It is a prerequisite for dynamic spectrum management and spectrum sharing. Spectrum resources can be used solely based on environmental awareness and detection. A key enabler in spectrum sensing is automatic modulation recognition (AMR), which is essential in spectrum interference monitoring, radio fault detection, and a wide variety of civilian and military applications
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have