Deep Learning Based Signal Detection for Hybrid Modulated Faster-than-Nyquist Optical Wireless Communications

Abstract

Faster-than-Nyquist (FTN) is a promising paradigm to improve bandwidth utilization at the expense of additional inter-symbol interference (ISI). To eliminate the influence of the ISI, a deep learning-based detection method is proposed to improve the bit error rate (BER) performance of Fast-than-Nyquist optical wireless communication system with hybrid 4PPM-QPSK modulation. Simulation results demonstrate that compared with the maximum likelihood sequence estimation (MLSE), the system performance can be improved by 2.8dB, 2.5dB, and 1.1dB when the BER is 10– <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> and the acceleration factor T is 1, 0.9 and 0.8, respectively.