Unsupervised and supervised machine learning for performance improvement of NFT optical transmission
Autor: | Morteza Kamalian, O. V. Kotlyar, Anastasiia Vasylchenkova, Maryna Pankratova, Sergei K. Turitsyn, Jaroslaw E. Prilepsky |
---|---|
Rok vydání: | 2018 |
Předmět: |
Computer science
Orthogonal frequency-division multiplexing business.industry k-means clustering Optical communication 02 engineering and technology Machine learning computer.software_genre 01 natural sciences Power (physics) Support vector machine ComputingMethodologies_PATTERNRECOGNITION 020210 optoelectronics & photonics Transmission (telecommunications) 0103 physical sciences 0202 electrical engineering electronic engineering information engineering Artificial intelligence Performance improvement 010306 general physics Cluster analysis business computer |
Zdroj: | 2018 IEEE British and Irish Conference on Optics and Photonics (BICOP) |
Popis: | We apply both the unsupervised and supervised machine learning (ML) methods, in particular, the k-means clustering and support vector machine (SVM) to improve the performance of the optical communication system based on the nonlinear Fourier transform (NFT). The NFT system employs the continuous NFT spectrum part to carry data up to 1000 km using the 16-QAM OFDM modulation. We classify the performance of the system in terms of BER versus signal power dependence. We show that the NFT system performance can be improved considerably by means of the ML techniques and that the more advanced SVM method typically outperforms the k-means clustering. |
Databáze: | OpenAIRE |
Externí odkaz: |