A machine learning-based detection technique for optical fiber nonlinearity mitigation

Abdelkerim Amari (Corresponding author), Xiang Lin, Octavia A. Dobre, Ramachandran Venkatesan, Alex Alvarado

Research output: Contribution to journalArticleAcademicpeer-review

33 Citations (SciVal)
96 Downloads (Pure)


We investigate the performance of a machine learning classi?cation technique, called the Parzen window, to mitigate the ?ber nonlinearity in the context of dispersion managed and dispersion unmanaged systems. The technique is applied for detection at the receiver side, and deals with the non-Gaussian nonlinear effects by designing improved decision boundaries. We also propose a two-stage mitigation technique using digital back propagation and Parzen window for dispersion unmanaged systems. In this case, digital back propagation compensates for the deterministic nonlinearity and the Parzen window deals with the stochastic nonlinear signal-noise interactions, which are not taken into account by digital back propagation. A performance improvement up to 0.4 dB in terms of Q factor is observed.
Original languageEnglish
Article number8660506
Pages (from-to)627-630
Number of pages4
JournalIEEE Photonics Technology Letters
Issue number8
Publication statusPublished - 15 Apr 2019


  • Digital back propagation
  • fiber nonlinearity mitigation
  • machine learning
  • optical communication systems
  • Parzen window


Dive into the research topics of 'A machine learning-based detection technique for optical fiber nonlinearity mitigation'. Together they form a unique fingerprint.

Cite this