Optimized Decision Method Based on K-means-TKNN for Coherent Optical Communication Systems

Zixuan Liu, Qi Zhang*, Ran Gao, Xishuo Wang, Dong Guo, Xiangjun Xin, Qinghua Tian, Feng Tian, Huan Chang, Yongjun Wang, Xia Sheng

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We proposed a nonlinear equalization method based on K-means-Tailored K-Nearest Neighbors (K-means-TKNN) algorithm. The simulation results show that the computational complexity of K-means-TKNN can be reduced to 20.3% of that of the traditional KNN algorithm for the 64-QAM system.

Original languageEnglish
Title of host publication2021 19th International Conference on Optical Communications and Networks, ICOCN 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665424462
DOIs
Publication statusPublished - 2021
Event19th International Conference on Optical Communications and Networks, ICOCN 2021 - Qufu, China
Duration: 23 Aug 202127 Aug 2021

Publication series

Name2021 19th International Conference on Optical Communications and Networks, ICOCN 2021

Conference

Conference19th International Conference on Optical Communications and Networks, ICOCN 2021
Country/TerritoryChina
CityQufu
Period23/08/2127/08/21

Keywords

  • Coherent optical communication
  • Machine learning
  • Nonlinear equalization

Fingerprint

Dive into the research topics of 'Optimized Decision Method Based on K-means-TKNN for Coherent Optical Communication Systems'. Together they form a unique fingerprint.

Cite this

Liu, Z., Zhang, Q., Gao, R., Wang, X., Guo, D., Xin, X., Tian, Q., Tian, F., Chang, H., Wang, Y., & Sheng, X. (2021). Optimized Decision Method Based on K-means-TKNN for Coherent Optical Communication Systems. In 2021 19th International Conference on Optical Communications and Networks, ICOCN 2021 (2021 19th International Conference on Optical Communications and Networks, ICOCN 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICOCN53177.2021.9563704