Journal of Lightwave Technology · 2017 · 81 citations · 19 references
ComputingComputational EngineeringComputer ScienceDigital CommunicationInformation TheoryMachine LearningDigital Signal ProcessingFiber OpticsNonlinear OpticsOptical Communication SystemsOptical ModulationUnsupervised LearningEqualizationK-means ClusteringModulation FormatsOptical Modulation FormatsOptical Nonlinearity CompensationPhase Shift KeyingUnsupervised ClusteringWavelength-division Multiplexing
Fiber-induced intra- and interchannel nonlinearities are experimentally tackled using blind nonlinear equalization (NLE) by unsupervised machine-learning-based clustering (MLC) in ~46-Gb/s single-channel and ~20-Gb/s (middle-channel) multichannel coherent multicarrier signals (orthogonal frequency-division multiplexing (OFDM) based). To that end, we introduce, for the first time, hierarchical and fuzzy-logic C-means (FLC)-based clustering in optical communications. It is shown that among the two proposed MLC algorithms, FLC reveals the highest performance at optimum launched optical powers (LOPs), while at very high LOPs, hierarchical can compensate more effectively nonlinearities only for low-level modulation formats. When employing binary phase-shift keying and quaternary phase-shift keying, FLC outperforms K-means, fast-Newton support vector machines, supervised artificial neural networks, and NLE with deterministic Volterra analysis. In particular, for the middle channel of a QPSK wavelength-division multiplexing coherent optical OFDM system at optimum -5 dBm of LOP and 3200 km of transmission, FLC outperforms Volterra-NLE by 2.5 dB in Q-factor. However, for a 16-QAM single-channel system at 2000 km, the performance benefit of FLC over inverse Volterra-series transfer function reduces to ~0.4 dB at a LOP of 2 dBm (optimum). Even when using novel sophisticated clustering designs in 16 clusters, no more than additional ~0.3-dB Q-factor enhancement is observed. Finally, in contrast to the deterministic Volterra-NLE, MLC algorithms can partially tackle the stochastic parametric noise amplification .
19
Phase-conjugated twin waves for communication beyond the Kerr nonlinearity limit
Xiang Liu, A. R. Chraplyvy, Peter J. Winzer et al. · Nature Photonics · 2013 · 395 citations
Modulation Format Recognition and OSNR Estimation Using CNN-Based Deep Learning
Danshi Wang, Min Zhang, Ze Li et al. · IEEE Photonics Technology Letters · 2017 · 257 citations
Intelligent constellation diagram analyzer using convolutional neural network-based deep learning
Danshi Wang, Min Zhang, Jin Li et al. · Optics Express · 2017 · 238 citations · Full text
Machine Learning Techniques in Optical Communication
Darko Zibar, Molly Piels, Rasmus T. Jones et al. · Journal of Lightwave Technology · 2015 · 230 citations