Optical Encoding Model Based on OAM Beam Superposition and Machine Learning Detection

Abstract

An optical encoding model based on the coher-ent superposition of two Laguerre-Gaussian modes carrying orbital angular momentum is presented using Machine Learning detection method. In the encoding process, the intensity profile for the encoded data is generated based on selection of $p$ and $\ell$ indices, while the decoding process is performed using support vector machine algorithm. Different encoding systems are designed and tested via simulations to verify the robustness of the proposed optical encoding model, finding a BER = 10–9 for 10.2 dB of signal-to-noise ratio in the best of the case.