Article: An end-to-end radar emitter denoising and recognition method using batch norm removal Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.1 pp.23 - 37 Abstract: Radar emitter recognition is a critical part of electronic countermeasures and determines the implementation of subsequent jamming measures. With the rapid development of deep learning (DL), the radar emitter recognition method based on DL is also widely developed. However, methods based on time-frequency analysis to obtain image features suffered from information loss and computational complexity; end-to-end methods based on raw radar signals had low accuracy at low signal-to-noise ratio (SNR). Therefore, we investigated the frequency distribution of signal and noise, analysed the working principle of batch norm, and proposed to suppress the high-frequency noise by removing the batch norm in the network. Furthermore, we constructed a straightforward end-to-end denoising and recognition network as well as utilised the latest classification network training process to improve the accuracy of radar emitter recognition at low SNR. Experiments validated that the proposed method achieved SOTA result on the well-known DeepSig RadioML 2018.01A. Inderscience Publishers - linking academia, business and industry through research

Title: An end-to-end radar emitter denoising and recognition method using batch norm removal

Authors: Zixin Jiang; Xin Zhao; Bing He; Zhenzhen Wang; Weijie Kang; Jie Zhang

Addresses: Department of Electronic Engineering, PLA Rocket Force University of Engineering, Xi'an, China ' Department of Electronic Engineering, PLA Rocket Force University of Engineering, Xi'an, China ' Department of Electronic Engineering, PLA Rocket Force University of Engineering, Xi'an, China ' Department of Electronic Engineering, PLA Rocket Force University of Engineering, Xi'an, China ' Department of Electronic Engineering, PLA Rocket Force University of Engineering, Xi'an, China ' Department of Electronic Engineering, PLA Rocket Force University of Engineering, Xi'an, China

Abstract: Radar emitter recognition is a critical part of electronic countermeasures and determines the implementation of subsequent jamming measures. With the rapid development of deep learning (DL), the radar emitter recognition method based on DL is also widely developed. However, methods based on time-frequency analysis to obtain image features suffered from information loss and computational complexity; end-to-end methods based on raw radar signals had low accuracy at low signal-to-noise ratio (SNR). Therefore, we investigated the frequency distribution of signal and noise, analysed the working principle of batch norm, and proposed to suppress the high-frequency noise by removing the batch norm in the network. Furthermore, we constructed a straightforward end-to-end denoising and recognition network as well as utilised the latest classification network training process to improve the accuracy of radar emitter recognition at low SNR. Experiments validated that the proposed method achieved SOTA result on the well-known DeepSig RadioML 2018.01A.

Keywords: radar emitter recognition; signal denoising; deep learning; end-to-end; time series.

DOI: 10.1504/IJICT.2025.144010

International Journal of Information and Communication Technology, 2025 Vol.26 No.1, pp.23 - 37

Received: 22 Feb 2024
Accepted: 30 Apr 2024
Published online: 20 Jan 2025 *

Title: An end-to-end radar emitter denoising and recognition method using batch norm removal

Keep up-to-date