A low-cost OSNR monitoring method using artificial neural networks trained by frequency spectra of low-speed sampling signals is proposed. The monitoring range from 10.5 to 28.5 dB with error less than ± 0.5 dB is achieved.

© 2020 The Author(s)

PDF Article


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