Enhanced Performance of PAM7 MISO Underwater VLC System Utilizing Machine Learning Algorithm Based on DBSCAN

After visible light communication drawing increasing attention, underwater visible light communication (UVLC) has attracted more interest in the research community nowadays. As multiple input single output (MISO) is getting increasingly widely used to improve the transmission speed in UVLC system, t...

Full description

Saved in:
Bibliographic Details
Main Authors: Meng Shi, Yiheng Zhao, Weixiang Yu, Yuchong Chen, Nan Chi
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8764014/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849415938967863296
author Meng Shi
Yiheng Zhao
Weixiang Yu
Yuchong Chen
Nan Chi
author_facet Meng Shi
Yiheng Zhao
Weixiang Yu
Yuchong Chen
Nan Chi
author_sort Meng Shi
collection DOAJ
description After visible light communication drawing increasing attention, underwater visible light communication (UVLC) has attracted more interest in the research community nowadays. As multiple input single output (MISO) is getting increasingly widely used to improve the transmission speed in UVLC system, the unbalance between multiple transmitters&#x2019; power is still a common phenomenon, which leads to the unequal spacing between each adjacent level and damages the system performance. In this paper, we study and analyze the unbalance between the two transmitters. Compared to a traditional hard decision, a density-based spatial clustering of applications with noise (DBSCAN) of a machine learning method is employed to get the actual center of each cluster and distinguish each level of PAM7 signals. In this way, a new decision curve substitutes traditional standard straight line as a constellation discrimination method. The experimental results show that up to 1.22&#x00A0;Gb/s over 1.2 m underwater visible light transmission can be achieved by using DBSCAN for PAM7 MISO signals. The measured bit error rate is well under the hard decision-forward error correction threshold of 3.8 &#x00D7; 10<sup>&#x2212;3</sup>.
format Article
id doaj-art-7d1968783ac04c4f881b56e2d72f2ca4
institution Kabale University
issn 1943-0655
language English
publishDate 2019-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-7d1968783ac04c4f881b56e2d72f2ca42025-08-20T03:33:21ZengIEEEIEEE Photonics Journal1943-06552019-01-0111411310.1109/JPHOT.2019.29288278764014Enhanced Performance of PAM7 MISO Underwater VLC System Utilizing Machine Learning Algorithm Based on DBSCANMeng Shi0https://orcid.org/0000-0002-2824-6753Yiheng Zhao1Weixiang Yu2https://orcid.org/0000-0003-3851-3330Yuchong Chen3Nan Chi4https://orcid.org/0000-0003-4966-3844Key Laboratory for Information Science of Electromagnetic Waves (MoE), Shanghai Institute for Advanced Communication and Data Science, Fudan University, Shanghai, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Shanghai Institute for Advanced Communication and Data Science, Fudan University, Shanghai, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Shanghai Institute for Advanced Communication and Data Science, Fudan University, Shanghai, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Shanghai Institute for Advanced Communication and Data Science, Fudan University, Shanghai, ChinaKey Laboratory for Information Science of Electromagnetic Waves (MoE), Shanghai Institute for Advanced Communication and Data Science, Fudan University, Shanghai, ChinaAfter visible light communication drawing increasing attention, underwater visible light communication (UVLC) has attracted more interest in the research community nowadays. As multiple input single output (MISO) is getting increasingly widely used to improve the transmission speed in UVLC system, the unbalance between multiple transmitters&#x2019; power is still a common phenomenon, which leads to the unequal spacing between each adjacent level and damages the system performance. In this paper, we study and analyze the unbalance between the two transmitters. Compared to a traditional hard decision, a density-based spatial clustering of applications with noise (DBSCAN) of a machine learning method is employed to get the actual center of each cluster and distinguish each level of PAM7 signals. In this way, a new decision curve substitutes traditional standard straight line as a constellation discrimination method. The experimental results show that up to 1.22&#x00A0;Gb/s over 1.2 m underwater visible light transmission can be achieved by using DBSCAN for PAM7 MISO signals. The measured bit error rate is well under the hard decision-forward error correction threshold of 3.8 &#x00D7; 10<sup>&#x2212;3</sup>.https://ieeexplore.ieee.org/document/8764014/MISODBSCANunderwater visible light communication.
spellingShingle Meng Shi
Yiheng Zhao
Weixiang Yu
Yuchong Chen
Nan Chi
Enhanced Performance of PAM7 MISO Underwater VLC System Utilizing Machine Learning Algorithm Based on DBSCAN
IEEE Photonics Journal
MISO
DBSCAN
underwater visible light communication.
title Enhanced Performance of PAM7 MISO Underwater VLC System Utilizing Machine Learning Algorithm Based on DBSCAN
title_full Enhanced Performance of PAM7 MISO Underwater VLC System Utilizing Machine Learning Algorithm Based on DBSCAN
title_fullStr Enhanced Performance of PAM7 MISO Underwater VLC System Utilizing Machine Learning Algorithm Based on DBSCAN
title_full_unstemmed Enhanced Performance of PAM7 MISO Underwater VLC System Utilizing Machine Learning Algorithm Based on DBSCAN
title_short Enhanced Performance of PAM7 MISO Underwater VLC System Utilizing Machine Learning Algorithm Based on DBSCAN
title_sort enhanced performance of pam7 miso underwater vlc system utilizing machine learning algorithm based on dbscan
topic MISO
DBSCAN
underwater visible light communication.
url https://ieeexplore.ieee.org/document/8764014/
work_keys_str_mv AT mengshi enhancedperformanceofpam7misounderwatervlcsystemutilizingmachinelearningalgorithmbasedondbscan
AT yihengzhao enhancedperformanceofpam7misounderwatervlcsystemutilizingmachinelearningalgorithmbasedondbscan
AT weixiangyu enhancedperformanceofpam7misounderwatervlcsystemutilizingmachinelearningalgorithmbasedondbscan
AT yuchongchen enhancedperformanceofpam7misounderwatervlcsystemutilizingmachinelearningalgorithmbasedondbscan
AT nanchi enhancedperformanceofpam7misounderwatervlcsystemutilizingmachinelearningalgorithmbasedondbscan