Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Ognjen Jovanovic"'
Publikováno v:
Jovanovic, O, Yankov, M P, Da Ros, F & Zibar, D 2022, ' End-to-end Learning of a Constellation Shape Robust to Channel Condition Uncertainties ', Journal of Lightwave Technology, vol. 40, no. 10, pp. 3316-3324 . https://doi.org/10.1109/JLT.2022.3169993
Vendor interoperability is one of the desired future characteristics of optical networks. This means that the transmission system needs to support a variety of hardware with different components, leading to system uncertainties throughout the network
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c2b730163e21f79ab0911a8ebebc3b97
https://doi.org/10.1109/jlt.2022.3169993
https://doi.org/10.1109/jlt.2022.3169993
Autor:
Jasper Müller, Ognjen Jovanovic, Tobias Fehenberger, Gabriele Di Rosa, Joerg-Peter Elbers, Carmen Mas Machuca
Publikováno v:
Journal of Optical Communications and Networking.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::22cb3b3bad0803ded392ad90a1239c7a
https://doi.org/10.1364/jocn.483320
https://doi.org/10.1364/jocn.483320
Autor:
Polina Bayvel, Matthew Brand, Francesco Da Ros, Camille Delezoide, Qirui Fan, Marija Furdek, Christian Häger, Takeshi Hoshida, Luyao Huang, Memedhe Ibrahimi, Ognjen Jovanovic, Boris Karanov, Faisal Nadeem Khan, Toshiaki Koike-Akino, Keisuke Kojima, Alan Pak Tao Lau, Patricia Layec, Zhengxuan Li, Chao Lu, Carlos Natalino, Petros Ramantanis, Cristina Rottondi, Marc Ruiz, Laurent Schmalen, Behnam Shariati, Yingheng Tang, Takahito Tanimura, Massimo Tornatore, Alba P. Vela, Luis Velasco, Ye Wang, Wanting Xu, Yongxin Xu, Metodi Yankov, Lilin Yi, Shaoliang Zhang, Darko Zibar
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d4fd040b3b2aa2f85798415b0acef8ca
https://doi.org/10.1016/b978-0-32-385227-2.00006-1
https://doi.org/10.1016/b978-0-32-385227-2.00006-1
Publikováno v:
Yankov, M P, Jovanovic, O, Zibar, D & Da Ros, F 2022, Recent advances in constellation optimization for fiber-optic channels . in Proceedings of European Conference on Optical Communication 2022 . Optica Publishing Group, 2022 European Conference on Optical Communication, Basel, Switzerland, 18/09/2022 .
Technical University of Denmark Orbit
Technical University of Denmark Orbit
The autoencoder concept for geometric constellation shaping is discussed. Applications in coherent optical fiber communications are presented. Several popular training algorithms are compared. The quantization problem of finite precision DAC and ADC
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::2ce122b9cb2a3c734629d69fda602dfc
https://orbit.dtu.dk/en/publications/b6f7d08e-20fd-43cb-9261-7b504c1369c0
https://orbit.dtu.dk/en/publications/b6f7d08e-20fd-43cb-9261-7b504c1369c0
End-to-end learning has become a popular method to optimize a constellation shape of a communication system. When the channel model is differentiable, end-to-end learning can be applied with conventional backpropagation algorithm for optimization of
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::21fc7be0dee79c819589db819086e677
Publikováno v:
Da Ros, F, Gaiarin, S, Jones, R T, Jovanovic, O, Porto da Silva, E & Zibar, D 2020, Nonlinear Fourier Transform: Perpetual Research Topic or Future Game-Changer? in Signal Processing in Photonic Communications 2020 ., SpTu2I.1, Optical Society of America (OSA), Signal Processing in Photonic Communications 2020, Washington, District of Columbia, United States, 13/07/2020 . https://doi.org/10.1364/SPPCOM.2020.SpTu2I.1
OSA Advanced Photonics Congress (AP) 2020 (IPR, NP, NOMA, Networks, PVLED, PSC, SPPCom, SOF)
OSA Advanced Photonics Congress (AP) 2020 (IPR, NP, NOMA, Networks, PVLED, PSC, SPPCom, SOF)
The topic of nonlinear Fourier transform (NFT) will be discussed focusing on the results achieved so far, on current open challenges and on an outlook on future prospects, especially focusing on machine-learning aided NFT systems.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::273caf34dce5ca2f9b2bda340c244900
https://orbit.dtu.dk/en/publications/e338e129-30a9-4a71-94c7-ad0814f97dd0
https://orbit.dtu.dk/en/publications/e338e129-30a9-4a71-94c7-ad0814f97dd0
Autor:
Rasmus T. Jones, Darko Zibar, Ognjen Jovanovic, Simone Gaiarin, Metodi P. Yankov, Francesco Da Ros
Publikováno v:
2020 22nd International Conference on Transparent Optical Networks (ICTON)
ICTON
ICTON
One of the key limiting factors in fiber optic communication systems is the nonlinear transmission impairment, due to the Kerr nonlinearity of optical fibers. In order to deal with this impairment, end-to-end learning can be applied to the optical fi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::163e5899644c89c8fb69d3925957ab9a
Publikováno v:
Technical University of Denmark Orbit
ECOC
Jovanovic, O, Yankov, M P, Da Ros, F & Zibar, D 2021, End-to-end Learning of a Constellation Shape Robust to Variations in SNR and Laser Linewidth . in Proceedings of European Conference on Optical Communications 2021 . IEEE, European Conference on Optical Communications 2021, Bordeaux, France, 13/09/2021 .
ECOC
Jovanovic, O, Yankov, M P, Da Ros, F & Zibar, D 2021, End-to-end Learning of a Constellation Shape Robust to Variations in SNR and Laser Linewidth . in Proceedings of European Conference on Optical Communications 2021 . IEEE, European Conference on Optical Communications 2021, Bordeaux, France, 13/09/2021 .
We propose an autoencoder-based geometric shaping that learns a constellation robust to SNR and laser linewidth estimation errors. This constellation maintains shaping gain in mutual information (up to 0.3 bits/symbol) with respect to QAM over variou
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::91abee5be9b32f04163d7c29f22775f4
https://orbit.dtu.dk/en/publications/1e4bbedd-6396-47b3-8d1b-068c6761858e
https://orbit.dtu.dk/en/publications/1e4bbedd-6396-47b3-8d1b-068c6761858e