The Bit Error Performance of Diffuse Indoor Optical Wireless Channel PPM System Employing Artificial Neural Networks for Channel Equalization

The Bit Error Rate (BER) performance of a Pulse Position Modulation (PPM) scheme for non Line-Of-Sight (LOS) indoor optical links employing channel equalization based on the Artificial Neural Network (ANN) is reported in the paper. Channel equalization is achieved by training a MultiLayer Perceptrons (MLP) ANN. A comparative study of the unequalized 'Soft' decision decoding and the 'Hard' decision decoding along with the neural equalized 'Soft' decision decoding is presented for different bit resolutions for optical channels with different delay spread. The authors show that the unequalized 'Hard' decision decoding performs the worst for all values of normalized delayed spread becoming impractical beyond normalized delayed spread of 0.6.