Machine-learning detector based on support vector machine for 122-Gbps multi-CAP optical communication system

In this work, we firstly apply support vector machine (SVM) detector in 122-Gbps Multi-CAP system. It can de-map the rotated constellations directly without any correction. The concrete simulations indicate such a machine-learning based detector provides considerable BER reduction for high-density C...

Full description

Saved in:
Bibliographic Details
Main Authors: Lin Sun, Jiangbing Du, Guoyao Chen, Zuyuan He, Xia Chen, Reed, Graham T.
Format: Conference Proceeding
Language:English
Subjects:
Adaptive optics
Detectors
Machine learning
Multi-CAP
Optical detectors
Optical distortion
Optical fiber communication
Optical filters
Support vector machines
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we firstly apply support vector machine (SVM) detector in 122-Gbps Multi-CAP system. It can de-map the rotated constellations directly without any correction. The concrete simulations indicate such a machine-learning based detector provides considerable BER reduction for high-density CAPs in low-frequency band, compared with hard decision.
ISSN:2166-8892
DOI:10.1109/OECC.2017.8114893