Residual learning based RF signal denoising
Yongshi Wang, Lan Tu, Jie Guo, Zhigang Wang · 2018 IEEE International Conference on Applied System Invention (ICASI) · 2018
Radio Frequency (RF) signal has been widely applied to the field of communication and radar for various purpose. However, the radio communication channels are usually complicated and dramatically rugged, giving rise to large signal interference. In this paper, we propose a deep denoising network (DDN) architecture based on residual learning to restrain the impact from the high-frequency additive noise. The model has solid ability to estimate this kind of noise lurking in the signals. A high-quality denoised signal can be obtained by subtracting the estimated noise from the raw signal. As an analysis of the feasibility of this method, we adopt Hausdorff distance as similarity measurement to compare and discuss the proposed method with other commonly used denoising methods. The results show that this method outperforms existing methods in complicated environment.