The performance of PPM using neural network and symbol decoding for diffused indoor optical wireless links

Artificial Neural network (ANN) can be an attractive alternative for adaptive equalization especially while channel is nonlinear or non-stationary. Pulse position modulation (PPM) requires the least average optical power compared to other modulation schemes in line-of-sight links but suffer severely in diffused links. The performance of PPM in a diffused channel can be improved by using different equalization techniques. In this work equalization using ANN is proposed and studied. The ANN equalized PPM shows promising results and its performance is comparable to the traditional equalization techniques. The performance can further be enhanced by using 'soft' decision decoding and the simulation results show a 2 dB gain in signal-to-noise. ©2007 IEEE.