The application of deep learning (DL) to solve physical layer issues has emerged as a\nprominent topic. In this paper, the mitigation of clipping effects for orthogonal frequency division\nmultiplexing (OFDM) systems with the help of a Neural Network (NN) is investigated. Unlike\nconventional clipping recovery algorithms, which involve costly iterative procedures, the DL-based\nmethod learns to directly reconstruct the clipped part of the signal while the unclipped part is\nprotected. Furthermore, an interpretation of the learned weight matrices of the neural network is\npresented. It is observed that parts of the network, in effect, implement transformations very similar\nto the (Inverse) Discrete Fourier Transform (DFT/IDFT) to provide information in both the time and\nfrequency domains. The simulation results show that the proposed method outperforms existing\nalgorithms for recovering clipped OFDM signals in terms of both mean square error (MSE) and Bit\nError Rate (BER).
Loading....