Abstract
Recently, automatic modulation recognition has been an important research topic in wireless communication. Due to the application of deep learning, it is prospective of using convolution neural networks on raw in-phase and quadrature signals in developing automatic modulation recognition methods. However, the errors introduced during signal reception and processing will greatly deteriorate the classification performance, which affects the practical application of such methods. Therefore, we first analyze and quantify the errors introduced by signal detection and isolation in noncooperative communication through a baseline convolution neural network. In response to these errors, we then design a signal spatial transformer module based on the attention model to eliminate errors by a priori learning of signal structure. By cascading a signal spatial transformer module in front of the baseline classification network, we propose a method that can adaptively resample the signal capture to adjust time drift, symbol rate, and clock recovery. Besides, it can also automatically add a perturbation on the signal carrier to correct frequency offset. By applying this improved model to automatic modulation recognition, we obtain a significant improvement in classification performance compared with several existing methods. Our method significantly improves the prospect of the application of automatic modulation recognition based on deep learning under nonideal synchronization.
Highlights
Automatic modulation recognition (AMR) has been an important topic in wireless communication.AMR is essential in radio fault detection, spectrum interference monitoring, and a wide variety of military and civilian applications
We present the values as r raw sampling are performed on the baseband in-phase and quadrature (IQ) signal
The framework we propose consists of two parts, one is the signal classifierand andthe theother other one is signal spatial transformer module (SSTM)
Summary
Automatic modulation recognition (AMR) has been an important topic in wireless communication.AMR is essential in radio fault detection, spectrum interference monitoring, and a wide variety of military and civilian applications. Most of the maximum likelihood methods based on hypothesis testing have higher computational complexity and are more sensitive to model mismatch problems, which greatly limits their application in wild communication environments. Other methods used manual feature extraction combined with machine learning (ML) to apply classification, as explored in [4,5,6]. These methods based on feature extraction and likelihood are effective in certain scenarios. The feature-based method can achieve the best recognition performance close to the theoretical limit, and it has strong robustness, so it is more widely used
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have