We present rare-event classification of polarization transients based on field measurements with data augmentation combined with robot-generated fiber-disturbance data. We compare machine learning methods for accuracy and required number of training sample traces.
© 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