Experimentally observed long-tail fast BER (10ns–1µs) histogram (FBH) in presence of NLIN is explained through simulation. Features from FBHs are applied to train an ANN to estimate linear and nonlinear NSRs with <5% error.
© 2020 The Author(s)
You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
Login to access OSA Member Subscription