A Module to Enhance the Generalization Ability of End-to-End Deep Learning Systems in Optical Fiber CommunicationsShow others and affiliations
2025 (English)In: Journal of Lightwave Technology, ISSN 0733-8724, E-ISSN 1558-2213, Vol. 43, no 2, p. 596-601Article in journal (Refereed) Published
Abstract [en]
AnAdapter module is developed to increase the generalization capability of the end-to-end learning system for optical fiber communication systems. The Adapter has an interpretable structure and can be inserted and used without changing the original signal processing structure. The Adapter module can improve the system generalization capability and achieve the correct demapping within the transmission distance fluctuation range of $\pm$100 km and the power fluctuation range of $\pm$0.5 dBm. In addition, using an Adapter can improve the performance of optical communication by modifying the equalization algorithm without altering the structure of the existing transmission system.
Place, publisher, year, edition, pages
Institute of Electrical and Electronics Engineers (IEEE) , 2025. Vol. 43, no 2, p. 596-601
Keywords [en]
Vectors, Deep learning, Optical fiber dispersion, Signal processing algorithms, Optical fiber networks, Constellation diagram, Transceivers, End-to-end deep learning, fiber nonlinearity, generalization, geometric shaping, optical communication
National Category
Telecommunications
Identifiers
URN: urn:nbn:se:kth:diva-359537DOI: 10.1109/JLT.2024.3466977ISI: 001396074600013Scopus ID: 2-s2.0-85205143251OAI: oai:DiVA.org:kth-359537DiVA, id: diva2:1935222
Note
QC 20250206
2025-02-062025-02-062025-02-06Bibliographically approved