Modulation formats recognition technique using artificial neural networks for radio over fiber systems

In this paper, we present and investigate a novel method for modulation formats recognition for radio-over-fiber (RoF) systems. The technique uses the artificial neural network (ANN) in conjunction with the features of asynchronous amplitude histograms of the detected signals at high bit rates using direct detection. The use of ANN method for this purpose mainly driven by its ability to learn complex classification problems and the use of sequential training algorithm to increase the estimation accuracy of all modulation formats. The efficiency of this technique is demonstrated under different transmission impairments such as chromatic dispersion (CD) in the range of 34 to 170 ps/nm, differential group delay (DGD) in the range of 0 - 20 ps and the optical signal to-noise ratio (OSNR) in the range of 4 - 30 dB. The results of numerical simulation for various modulation formats demonstrate successful recognition from a known bit rates with a higher estimation accuracy, which exceeds 99.9%.