Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-04-01 Cooperative journals: 《计算机应用研究》
Abstract: Considering the performance deterioration of orthogonal frequency division multiplexing communication (OFDM) system due to narrowband interference (NBI) , this paper employed deep learning into NBI mitigation of OFDM systems and proposed two structures with convolutional neural network (CNN) . These two structures firstly pre-processed the received data in receiver, then adopted CNN to exploit the interference estimation in time domain. Finally the impact of NBI was removed from received signal. The simulation results demonstrate that the two systems can learn the interference effectively and improve system performance.