Enhancing Convolution Recurrent Network with Graph Signal Processing:High Suppressive Interference Mitigation
简介：In this paper,we propose a novel graph si-gnal processing convolution recurrent network(GSP CRN)for signal enhancement against high suppres-sive interference(HSI)in wireless communications.GSPCRN consists of the short-time graph signal pro-cessing(SGSP)approach and a modified convolution recurrent network.Similar to the traditional short-time time-frequency transformation,SGSP frames the complex-valued communication signal and transforms it to the graph-domain representations,where the con-nection and weight flexibility of each vertex are fully taken into account.In the presence of HSI,SGSP can extract signal features from new graph-domain dimen-sions and empower neural networks for weak signal enhancement.Two SGSP methods,adjacency singu-lar value decomposition and implicit graph transfor-mation,are designed to capture relationships among the sampling points in the segmented signals.Simula-tion results demonstrate that our proposed GSPCRN outperforms existing classic methods in extracting weak signals from the HSI environment.When the interference-to-signal ratio exceeds 27dB,only our proposed GSPCRN can achieve the interference mit-igation.展开
学者：GUOPengchengYuMiaoGuMiaomiaoRenBingyin
关键词：adjacency matrixshort-time graph signal processingsignal enhancementwireless communica-tions
在线出版日期：2026-03-17 （网站首发日期）
