Amplitude jitter compensation of PAM-8 VLC system employing time-amplitude two-dimensional re-estimation base on density clustering of machine learning. (21st March 2019)

• Record Type: Journal Article
• Authors: Lu, Xingyu; Zhou, Yingjun; Qiao, Liang; Yu, Weixiang; Liang, Shangyu; Zhao, Mingming; Zhao, Yiheng; Lu, Chao; Chi, Nan
• Is Part Of: Physica scripta. Volume 94:Number 5(2019)
• Publication Date: 2019-03-21
• Subjects: visible light communication -- light-emitting diodes -- channel estimation -- adaptive equalizer; Physics -- Periodicals; 530.05
• DOI: 10.1088/1402-4896/ab0a9f
• Languages: English
• ISSNs: 0031-8949

Abstract

Abstract: Amplitude jitter is a common phenomenon in pulse amplitude modulation (PAM) visible light communication (VLC) systems, which greatly affects the system performance. In this paper, we propose a novel time-amplitude two-dimensional re-estimation based on density-based spatial clustering of applications with noise (DBSCAN) algorithm of machine learning (2DDB) to distinguish different signal levels with jitter. The Q factor of a PAM-8 VLC system applying 2DDB is improved by 1.6–3.2 dB through experimental demonstration. In addition, we also investigate the influence of amplitude jitter with different levels on PAM-8 systems, and analyze the range of parameters and applications of a DBSCAN algorithm. To the best of our knowledge, this is the first time that DBSCAN of machine learning is successfully applied to PAM VLC systems.