전자전 환경에서 전이학습 기반 저피탐 레이더 변조 신호 분류 성능 분석

초록

As the development of low detection radar technology, accurate detection and modulation classification technology for LPI threat signals is emerging as an important technology. In particular, research on the classification of radar modulation methods has been actively conducted recently by applying deep learning-based image processing technology. However, these deep learning-based approaches have difficulties in securing high-quality learning data when applied to weapon systems. In this paper, we propose a method to improve radar signal classification performance even in a low SNR environment using transfer learning considering the signal reception environment of electronic warfare. It was confirmed that the proposed transfer learning-based classification method showed a classification success rate of over 90% at -12 dB.

키워드