Mitigating fiber nonlinearity using support vector machine with genetic algorithm

We applied genetic algorithm to optimize the parameters of support vector machine for improving prediction accuracy. The proposed method is measured experimentally in 16-QAM coherent communication system for mitigating the fiber-nonlinearity-induced impairments.

[1]  Patrick Siarry,et al.  A survey on optimization metaheuristics , 2013, Inf. Sci..

[2]  J. Xu,et al.  Experimental observation of non-linear mode conversion in few-mode fiber , 2015, 2015 Conference on Lasers and Electro-Optics (CLEO).

[3]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[4]  E. Giacoumidis,et al.  Kerr-induced nonlinearity reduction in coherent optical OFDM by low complexity support vector machine regression-based equalization , 2016, 2016 Optical Fiber Communications Conference and Exhibition (OFC).

[5]  N. Kokash.  An introduction to heuristic algorithms , 2005 .

[6]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.