Radio Frequency Fingerprint Identification Based on Deep Complex Residual Network

• Main Authors: Shenhua Wang, Hongliang Jiang, Xiaofang Fang, Yulong Ying, Jingchao Li, Bin Zhang
• Format: Article
• Language: English
• Published: IEEE 2020-01-01
• Series: IEEE Access
• Subjects: Wireless communication; radio frequency fingerprint; constellation; deep learning; end-to-end; deep complex residual network
• Online Access: https://ieeexplore.ieee.org/document/9253560/

Radio frequency fingerprint identification is a non-password authentication method based on the physical layer hardware of the communication device. Deep learning methods provide new ideas and techniques for radio frequency fingerprint identification. As a bridge between electromagnetic signal recognition and deep learning, the electromagnetic signal recognition method based on statistical constellation still needs to go through data preprocessing and feature engineering, which is contrary to the end-to-end learning method emphasized by deep learning. Moreover, in the process of converting electromagnetic signal waveform data into images, there is inevitably information loss. Establishing a universal radio frequency fingerprint recognition model suitable for wireless communication scenarios is not only conducive to optimizing the communication system, but also can reduce the cost and time of model selection. Therefore, how to design a deep learning radio frequency fingerprint recognition model suitable for wireless communication is an important problem for researchers. Aiming at the problem that the existing radio frequency fingerprint extraction and identification methods have low recognition rate of communication radiation source individuals, a radio frequency fingerprint identification method based on deep complex residual network is proposed. Through the deep complex residual network, the radio frequency fingerprint feature extraction of the communication radiation source individual is integrated with the recognition process, and an end-to-end deep learning model suitable for wireless communication is established, which greatly improves the identification accuracy of the communication radiation source individuals compared with typical constellation based methods.