SVM detection for superposed pulse amplitude modulation in visible light communications

Youli Yuan; Min Zhang; Pengfei Luo; Zabih Ghassemlooy; Danshi Wang; Xiongyan Tang; Dahai Han

doi:10.1109/CSNDSP.2016.7573898

SVM detection for superposed pulse amplitude modulation in visible light communications

Youli Yuan, Min Zhang, Pengfei Luo, Zabih Ghassemlooy, Danshi Wang, Xiongyan Tang, Dahai Han

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

17 Citations (Scopus)

Abstract

A support vector machine (SVM)-based data detection for 8-superposed pulse amplitude modulation in visible light communication is proposed and experimentally demonstrated. In this work, the SVM detector contains three binary classifiers with different classification strategies. And the separating hyperplane of each SVM is constructed by training data. The experiment results show that the SVM detection offers 35% higher data rates when compared with the traditional direct decision method.

Original language	English
Title of host publication	Proceedings of the 2016 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP)
Place of Publication	Piscataway
Publisher	IEEE
Pages	1-5
ISBN (Print)	9781509025268
DOIs	https://doi.org/10.1109/CSNDSP.2016.7573898
Publication status	Published - 22 Sept 2016
Event	10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP 2016) - Prague Duration: 22 Sept 2016 → …

Conference

Conference	10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP 2016)
Period	22/09/16 → …

Keywords

direct decision
support vector machine
superposed pulse amplitude modulation
visible light communiction

Access to Document

10.1109/CSNDSP.2016.7573898

Cite this

@inbook{b735e45484fb4164b6368cd02cb9f9a5,

title = "SVM detection for superposed pulse amplitude modulation in visible light communications",

abstract = "A support vector machine (SVM)-based data detection for 8-superposed pulse amplitude modulation in visible light communication is proposed and experimentally demonstrated. In this work, the SVM detector contains three binary classifiers with different classification strategies. And the separating hyperplane of each SVM is constructed by training data. The experiment results show that the SVM detection offers 35\% higher data rates when compared with the traditional direct decision method.",

keywords = "direct decision, support vector machine, superposed pulse amplitude modulation, visible light communiction",

author = "Youli Yuan and Min Zhang and Pengfei Luo and Zabih Ghassemlooy and Danshi Wang and Xiongyan Tang and Dahai Han",

year = "2016",

month = sep,

day = "22",

doi = "10.1109/CSNDSP.2016.7573898",

language = "English",

isbn = "9781509025268",

pages = "1--5",

booktitle = "Proceedings of the 2016 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP)",

publisher = "IEEE",

address = "United States",

note = "10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP 2016) ; Conference date: 22-09-2016",

}

Yuan, Y, Zhang, M, Luo, P, Ghassemlooy, Z, Wang, D, Tang, X & Han, D 2016, SVM detection for superposed pulse amplitude modulation in visible light communications. in Proceedings of the 2016 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP). IEEE, Piscataway, pp. 1-5, 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP 2016), 22/09/16. https://doi.org/10.1109/CSNDSP.2016.7573898

SVM detection for superposed pulse amplitude modulation in visible light communications. / Yuan, Youli; Zhang, Min; Luo, Pengfei et al.
Proceedings of the 2016 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP). Piscataway: IEEE, 2016. p. 1-5.

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

TY - CHAP

T1 - SVM detection for superposed pulse amplitude modulation in visible light communications

AU - Yuan, Youli

AU - Zhang, Min

AU - Luo, Pengfei

AU - Ghassemlooy, Zabih

AU - Wang, Danshi

AU - Tang, Xiongyan

AU - Han, Dahai

PY - 2016/9/22

Y1 - 2016/9/22

N2 - A support vector machine (SVM)-based data detection for 8-superposed pulse amplitude modulation in visible light communication is proposed and experimentally demonstrated. In this work, the SVM detector contains three binary classifiers with different classification strategies. And the separating hyperplane of each SVM is constructed by training data. The experiment results show that the SVM detection offers 35% higher data rates when compared with the traditional direct decision method.

AB - A support vector machine (SVM)-based data detection for 8-superposed pulse amplitude modulation in visible light communication is proposed and experimentally demonstrated. In this work, the SVM detector contains three binary classifiers with different classification strategies. And the separating hyperplane of each SVM is constructed by training data. The experiment results show that the SVM detection offers 35% higher data rates when compared with the traditional direct decision method.

KW - direct decision

KW - support vector machine

KW - superposed pulse amplitude modulation

KW - visible light communiction

UR - https://www.scopus.com/pages/publications/84991738173

U2 - 10.1109/CSNDSP.2016.7573898

DO - 10.1109/CSNDSP.2016.7573898

M3 - Chapter

SN - 9781509025268

SP - 1

EP - 5

BT - Proceedings of the 2016 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP)

PB - IEEE

CY - Piscataway

T2 - 10th International Symposium on Communication Systems, Networks and Digital Signal Processing (CSNDSP 2016)

Y2 - 22 September 2016

ER -

SVM detection for superposed pulse amplitude modulation in visible light communications

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this