Deep Learning for Large-Scale Real-World ACARS and ADS-B Radio Signal Classification

Abstract

Radio signal classification has a very wide range of applications in the field of wireless communications and electromagnetic spectrum management. In recent years, deep learning has been used to solve the problem of radio signal classification and has achieved good results. However, the radio signal data currently used are very limited in scale. In order to verify the performance of the deep learning-based radio signal classification on real-world radio signal data, in this paper, we conduct experiments on large-scale real-world ACARS and ADS-B signal data with sample sizes of 900 000 and 13 000 000,, respectively, and with categories of 3143 and 5157, respectively. We use the same inception-residual neural network model structure for ACARS signal classification and ADS-B signal classification to verify the ability of a single basic deep neural network model structure to process different types of radio signals, i.e., communication bursts in ACARS and pulse bursts in ADS-B. We build an experimental system for radio signal deep learning experiments. The experimental results show that the signal classification accuracy of ACARS and ADS-B is 98.1% and 96.3%, respectively. When the signal-to-noise ratio (with injected additive white Gaussian noise) is greater than 9 dB, the classification accuracy is greater than 92%. These experimental results validate the ability of deep learning to classify large-scale real-world radio signals. The results of the transfer learning experiment show that the model trained on large-scale ADS-B datasets is more conducive to the learning and training of new tasks than the model trained on small-scale datasets.