Research Area:  Machine Learning
Orbital angular momentum (OAM)-encoding has recently emerged as an effective approach for increasing the channel capacity of free-space optical communications. In this letter, OAM-based decoding is formulated as a supervised classification problem. To maintain lower error rate in presence of severe atmospheric turbulence, a new approach that combines effective machine learning tools from persistent homology and convolutional neural networks (CNNs) is proposed to decode the OAM modes. A Gaussian kernel with learnable parameters is proposed in order to connect persistent homology to CNN, allowing the system to extract and distinguish robust and unique topological features for the OAM modes. Simulation results show that the proposed approach achieves up to 20% gains in classification accuracy rate over state-of-the-art of method based on only CNNs. These results essentially show that geometric and topological features play a pivotal role in the OAM mode classification problem.
Keywords:  
orbital angular momentum
free-space
optical communication
atmospheric turbulence
persistent homology
convolutional neural networks
Gaussian kernel
classification problem
Author(s) Name:  Soheil Rostami, Walid Saad, Choong Seon Hong
Journal name:  IEEE Communications Letters
Conferrence name:  
Publisher name:  IEEE
DOI:  https://doi.org/10.1109/LCOMM.2019.2954311
Volume Information:  Volume 24