A Modulation Recognition Algorithm via Hybrid Feature Analysis in Aeronautical Wireless Channel

Kun Liu,Haoqi Bi,Xin Xiang,Zhiying Peng,Yuan Liang

doi:10.1109/access.2021.3090037

Abstract

When communicating in aeronautical wireless channels, the difficulty of radio modulation recognition increases due to the loss of information caused by noise; particularly in circumstances with low signal-to-noise ratios (SNRs), it is difficult to achieve recognition rates exceeding 90.0%. To improve the radio modulation recognition performances of networks at low SNRs in complex electromagnetic environments, a modulation recognition method based on multidimensional feature analysis is proposed in this paper. It is realized through a cascaded structure including a Deep Cross Network (DCN) and an improved Visual Geometry Group Network 16 (VGG16). Our network framework is divided into two modules. In the one-dimensional data analysis module, we take the high-order cumulant of a transmitted signal as the one-dimensional feature input of the DCN. In the two-dimensional data analysis module, the color constellation density of the signal is extracted as the feature map input of the improved VGG16. Finally, we build a cascaded neural network with hybrid feature inputs for modulation recognition. Experimental results show that the recognition rate of our method is higher than 90.0% at an SNR of -4 dB. Compared with other methods, the proposed method has better recognition performance at low SNRs in aeronautical wireless channels.

Highlights

The precise identification of modulation modes is the basis for analyzing intercepted signals under non-cooperative wireless communications
Reference [6] realized signal modulation recognition through the superposition of two convolutional neural networks (CNNs), making use of the constellation map of a transmitted signal to perform shape matching and subdivide the modulation mode, thereby improving the recognition rate of the method at low SNRs; this approach ignores the influences of multipath fading and the Doppler frequency
ANALYSIS OF EXPERIMENTAL RESULTS Aiming at verifying the effectiveness of the method proposed in this paper, we analyze the performance of the proposed network at different SNRs first, and we compare our model with traditional methods and other network models used for analyzing the advantages of multidimensional feature inputs

Summary

INTRODUCTION

The precise identification of modulation modes is the basis for analyzing intercepted signals under non-cooperative wireless communications. Reference [6] realized signal modulation recognition through the superposition of two convolutional neural networks (CNNs), making use of the constellation map of a transmitted signal to perform shape matching and subdivide the modulation mode, thereby improving the recognition rate of the method at low SNRs; this approach ignores the influences of multipath fading and the Doppler frequency. For the purpose of improving the modulation recognition performance of our approach at low SNRs, we select the high-order cumulant and the color constellation density of the signal as the one-dimensional feature and the two-dimensional feature, respectively. We build a DCN and an improved VGG 16 cascaded network framework to perform feature extraction, effectively combining the advantages of both types of features and realizing the accurate recognition of the modulation modes of the signal. We summarize the defects of our method and suggest a direction for future research in the fifth section

AERONAUTICAL CHANNEL AND MIXED FEATURE

FEATURE ANALYSIS

ANALYSIS OF EXPERIMENTAL RESULTS

Findings

CONCLUSION