Supervised machine learning methods are applied and demonstrated experimentally for inband OSNR estimation and modulation format classification in optical communication systems. The proposed methods accurately evaluate coherent signals up to 64QAM using only intensity information.
|Title of host publication||Proceedings of the 42nd European Conference and Exhibition on Optical Communications (ECOC 2016)|
|Number of pages||3|
|Publication status||Published - 2016|
|Event||42nd European Conference on Optical Communication - Dusseldorf, Germany|
Duration: 18 Sep 2016 → 22 Sep 2016
|Conference||42nd European Conference on Optical Communication|
|Period||18/09/2016 → 22/09/2016|