基于SVM的广义空移键控可见光通信系统信号检测算法

商建东; 孙浩博; 王法松

doi:10.11999/JEIT200711

基于SVM的广义空移键控可见光通信系统信号检测算法

doi: 10.11999/JEIT200711

1.
郑州大学河南省超算中心郑州 450001
2.
郑州大学信息工程学院郑州 450001

基金项目: 国家自然科学基金(61401401)，河南省科技攻关项目(192102210088)

详细信息

作者简介:
商建东：男，1968年生，教授，博士生导师，研究方向为高性能计算、计算机网络与通信

孙浩博：男，1995年生，硕士生，研究方向为可见光通信

王法松：男，1979年生，教授，硕士生导师，研究方向为盲信号处理、可见光通信

通讯作者:
王法松　iefswang@zzu.edu.cn

中图分类号: TN929.12
计量
- 文章访问数: 999
- HTML全文浏览量: 319
- PDF下载量: 83
- 被引次数: 0
出版历程
- 收稿日期: 2020-08-11
- 修回日期: 2021-04-15
- 网络出版日期: 2021-07-14
- 刊出日期: 2021-10-18

SVM-aided Signal Detection in Generalized Space Shift Keying Visible Light Communication System

1.
Henan Supercomputing Center, Zhengzhou University, Zhengzhou 450001, China
2.
School of Information Engineering, Zhengzhou University, Zhengzhou 450001, China

Funds: The National Natural Science Foundation of China (61401401), The Science and Technology Research Project of Henan Province (192102210088)

摘要

摘要: 针对室内广义空移键控(GSSK)调制的可见光通信(VLC)系统，该文提出一种基于支持向量机(SVM)的机器学习信号检测算法。在一般的VLC系统中，极大似然(ML)检测是最优检测算法，但是ML检测算法具有很高的计算复杂度。为了解决此问题，该文利用机器学习中的SVM分类思想实现对系统接收端的信号检测，以在保证信号检测正确率的情况下，降低计算复杂度，提高GSSK-VLC系统的信号检测效率。仿真结果表明，该文提出的针对室内GSSK-VLC系统的SVM信号检测算法与ML检测算法相比，在具有接近ML的误比特率(BER)性能的同时，计算复杂度明显降低，有效提升了系统的检测性能。
- 可见光通信 /
- 信号检测 /
- 支持向量机 /
- 空移键控 /
- 广义空移键控
Abstract: Novel signal detection technique is conceived for Generalized Space Shift Keying (GSSK) modulated indoor Visible Light Communication (VLC) system, which is aided by one of popular machine learning approach termed as Support Vector Machine (SVM). For general classic VLC system, as the optimal detection algorithm, Maximum Likelihood (ML) detection has a high computational complexity. In order to alleviate this problem, classification idea in SVM is utilized to realize signal detection at the user’s receiving end by a particular trained learning model. As a result, a signal detection algorithm for the considered GSSK-VLC system based on SVM is designed with lower computational complexity and nearly optimal detection accuracy. Simulation results demonstrate that the proposed SVM-aided signal detection technique can have near optima ML Bit Error Rate (BER) performance while the computational complexity is significantly reduced in the considered indoor GSSK-VLC system
- Visible Light Communication (VLC) /
- Signal detection /
- Support Vector Machine (SVM) /
- Space Shift Keying (SSK) /
- Generalized Space Shift Keying (GSSK)

HTML全文

图 1 室内VLC系统概念图

下载: 全尺寸图片幻灯片

图 2 GSSK-VLC系统框图

下载: 全尺寸图片幻灯片

图 3 LoS传输的几何模型示意图

下载: 全尺寸图片幻灯片

图 4 针对SSK-VLC系统不同算法的BER性能分析

下载: 全尺寸图片幻灯片

图 5 针对GSSK-VLC系统的不同算法的BER性能分析

下载: 全尺寸图片幻灯片

表 1 GSSK-VLC系统标签

$n$	${l_n}$	${i_n}$	LED index
1	1	000	LED 1 & 2
2	2	001	LED 1 & 3
3	3	010	LED 1 & 4
4	4	011	LED 1 & 5
5	5	100	LED 2 & 3
6	6	101	LED 2 & 4
7	7	110	LED 2 & 5
8	8	111	LED 3 & 4

下载: 导出CSV

表 2 LED位置的空间分布坐标

4 LEDs		8 LEDs
LED	$({O_X},{O_Y},{O_Z})\;{ \rm{m} }$	1	(1.25, 0.35, 3)
1	(1.25, 1.25, 3)	2	(3.85, 0.35, 3)
2	(3.25, 1.25, 3)	3	(1.25, 1.85, 3)
3	(1.35, 3.25, 3)	4	(3.85, 1.85, 3)
4	(3.25, 3.25, 3)	5	(1.25, 3.25, 3)
		6	(3.85, 3.25, 3)
		7	(1.25, 4.25, 3)
		8	(3.85, 4.25, 3)

下载: 导出CSV

表 3 系统仿真参数设置

发射端 (LED)		接收端(PD)
LED数量$({N_{\rm{t} } })$	4, 8	PD数量$({N_r})$	4
距地面高度	3 m	距地面高度	0.85 m
半功率半角$({\phi _{1/2} })$	${60^ \circ }$	PD的物理面积$({A_{\rm{PD} }})$	$1 \;{{\rm{cm}} ^2}$
光学滤波器增益$({{T}_s}(\psi ))$	1.0	PD的FoV半角$({\varPsi _{\rm{FoV}}})$	${60^ \circ }$
光电转换效率$(\eta )$	813.6 μW/mA	折光率$(\beta )$	$1.5$
调制指数$(\alpha )$	$0.1$	PD响应度$(R)$	100 μA/mW

下载: 导出CSV

表 4 针对GSSK-VLC系统基于不同检测算法所需时间对比

检测算法	计算时间(s)
KMC	175.8836
KMC (20)	3517.6607
KMC (50)	8794.1735
IKMC	879.418
SVM	98.6687
ML	10904.7794

下载: 导出CSV

参考文献(19)

[1]	LIU Wenlong, ZHANG Ying, and JIN Minglu. Lagrangian detection for generalized space-shift keying MIMO systems[J]. IEEE Transactions on Vehicular Technology, 2017, 66(9): 8585–8589. doi: 10.1109/TVT.2017.2678528
[2]	ZHANG Xinhe, LIU Qian, and JIN Minglu. Detection of generalized space shift keying signal with sparse reconstruction[J]. IEEE Transactions on Vehicular Technology, 2017, 66(6): 5471–5475. doi: 10.1109/TVT.2016.2621160
[3]	JEGANATHAN J, GHRAYEB A, and SZCZECINSKI L. Generalized space shift keying modulation for MIMO channels[C]. 2008 IEEE 19th International Symposium on Personal, Indoor and Mobile Radio Communications, Cannes, France, 2008: 1–5. doi: 10.1109/PIMRC.2008.4699782.
[4]	吴楠, 王旭东, 姚凯莉, 等. 可见光通信中的无载波位相调制技术[J]. 电子与信息学报, 2017, 39(2): 360–366. doi: 10.11999/JEIT160343 WU Nan, WANG Xudong, YAO Kaili, et al. Carrier-less position/phase modulation for visible light communications[J]. Journal of Electronics &Information Technology, 2017, 39(2): 360–366. doi: 10.11999/JEIT160343
[5]	FATH T and HAAS H. Performance comparison of MIMO techniques for optical wireless communications in indoor environments[J]. IEEE Transactions on Communications, 2013, 61(2): 733–742. doi: 10.1109/TCOMM.2012.120512.110578
[6]	WANG T Q, SEKERCIOGLU Y A, and ARMSTRONG J. Analysis of an optical wireless receiver using a hemispherical lens with application in MIMO visible light communications[J]. Journal of Lightwave Technology, 2013, 31(11): 1744–1754. doi: 10.1109/JLT.2013.2257685
[7]	YING Kai, QIAN Hua, BAXLEY R J, et al. Joint optimization of precoder and equalizer in MIMO VLC systems[J]. IEEE Journal on Selected Areas in Communications, 2015, 33(9): 1949–1958. doi: 10.1109/JSAC.2015.2432515
[8]	MITCHELL T, BUCHANAN B, DEJONG G, et al. Machine learning[J]. Kluwer International, 2003, 4(1): 417–433. doi: 10.1007/978-1-4613-2279-5
[9]	佟鑫, 李莹, 陈岚. SVM算法在硬件木马旁路分析检测中的应用[J]. 电子与信息学报, 2020, 42(7): 1643–1651. doi: 10.11999/JEIT190532 TONG Xin, LI Ying, and CHEN Lan. Application of SVM machine learning to hardware trojan detection using side-channel analysis[J]. Journal of Electronics &Information Technology, 2020, 42(7): 1643–1651. doi: 10.11999/JEIT190532
[10]	LIANG Hanwen, CHUMG W H, and KUO S Y. Coding-aided K-means clustering blind transceiver for space shift keying MIMO systems[J]. IEEE Transactions on Wireless Communications, 2016, 15(1): 103–115. doi: 10.1109/TWC.2015.2467394
[11]	YOU Longfei, YANG Ping, XIAO Yue, et al. Blind detection for spatial modulation systems based on clustering[J]. IEEE Communications Letters, 2017, 21(11): 2392–2395. doi: 10.1109/LCOMM.2017.2734648
[12]	ZHANG Lijuan and JIN Minglu. A constrained clustering-based blind detector for spatial modulation[J]. IEEE Communications Letters, 2019, 23(7): 1170–1173. doi: 10.1109/LCOMM.2019.2915304
[13]	JIANG Rui, SUN Caiming, ZHANG Long, et al. Deep learning aided signal detection for SPAD-based underwater optical wireless communications[J]. IEEE Access, 2020, 8: 20363–20374. doi: 10.1109/ACCESS.2020.2967461
[14]	LEE H, LEE I, and LEE S H. Deep learning based transceiver design for multi-colored VLC systems[J]. Optics Express, 2018, 26(5): 6222–6238. doi: 10.1364/OE.26.006222
[15]	YUAN Youli, ZHANG Min, LUO Pengfei, et al. SVM-based detection in visible light communications[J]. Optik, 2017, 151: 55–64. doi: 10.1016/j.ijleo.2017.08.089
[16]	MOSTAFA A and LAMPE L. Physical-Layer security for MISO visible light communication channels[J]. IEEE Journal on Selected Areas in Communications, 2015, 33(9): 1806–1818. doi: 10.1109/JSAC.2015.2432513
[17]	MOSTAFA A and LAMPE L. Optimal and robust beamforming for secure transmission in MISO visible-light communication links[J]. IEEE Transactions on Signal Processing, 2016, 64(24): 6501–6516. doi: 10.1109/TSP.2016.2603964
[18]	WANG Fasong, LIU Chaowen, WANG Qi, et al. Secrecy analysis of generalized space-shift keying aided visible light communication[J]. IEEE Access, 2018, 6: 18310–18324. doi: 10.1109/ACCESS.2018.2799658
[19]	HANDTE T, MULLER A, and SPEIDEL J. BER analysis and optimization of generalized spatial modulation in correlated fading channels[C]. The 70th IEEE Vehicular Technology Conference Fall (VTC 2009-Fall), Anchorage, USA, 2009: 1–5. doi: 10.1109/VETECF.2009.5378677.