非线性效应限制是高速可见光通信系统性能提升的一大瓶颈问题，为此提出将支持向量机（support vector machine，SVM）监督学习算法应用于几何整形可见光通信系统接收信号星座点的分类判决，将信号的同向分量和正交分量作为特征向量，建立最优分类界面，以降低非线性条件下星座点变形带来的符号误判，同时比较几种几何整形设计的性能.仿真分析和实验结果表明，SVM提升了非线性条件下系统的性能，在数据速率为1.2 Gbit/s的高速可见光通信传输中，圆-169几何整形16正交幅度调制（quadrature amplitude modulation，QAM）的符号误码性能最优.
Nonlinear effect has been becoming a major bottleneck in high speed visible light communication (VLC) system. In this paper, we propose a supervised learning algorithm, support vector machine (SVM) for improving constellation classification in geometrically shaping (GS) VLC system. By taking the in-phase and quadrature components of the signal as feature vectors, an optimal classification plane can be built, and the symbol error introduced by nonlinearity could be therefore reduced. The performances of several GS designs are conducted and compared. Simulation and experimental results show that SVM could significantly reduce the error rate, compared with conventional classification scheme based on Euclidean distance. Among all simulations with SVM, the system with the data rate of 1.2 Gbit/s, circle169 GS-16QAM performs the lowest symbol error rate.
[1] 迟楠,石蒙,哈依那尔,等. LiFi:可见光通信技术发展现状与展望[J]. 照明工程学报,2019, 30(1):1-9, 24. Chi N, Shi M, Ha Y, et al. LiFi:development status and prospects of visible light communication technology[J]. China Illuminating Engineering Journal, 2019, 30(1):1-9, 24. (in Chinese)
[2] Chi N, Haas H, Kavehrad M, et al. Visible light communications:demand factors, benefits and opportunities[J]. IEEE Wireless Communications, 2015, 22(2):5-7.
[3] Chi N, Shi M. Advanced modulation formats for underwater visible light communications[J]. Chinese Optics Letters, 2018, 16(12):120603.
[4] Hu F, Zou P, Li G, et al. Enhanced performance of CAP-modulated visible light communication system utilizing geometric shaping and rotation coding[J]. IEEE Photonics Journal, 2019, 11(5):1-2.
[5] Zhao J, Qin C, Zhang M, et al. Investigation on performance of special-shaped 8-quadrature amplitude modulation constellations applied in visible light communication[J]. Photonics Research, 2016, 4(6):249-256.
[6] 邹鹏,赵一衡,胡昉辰,等. 基于机器学习的可见光通信信号处理研究现状[J]. 激光与光电子学进展,2020, 57(1):9-21. Zou P, Zhao Y H, Hu F C, et al. Research status of machine learning based signal processing in visible light communication[J]. Laser & Optoelectronics Progress, 2020, 57(1):9-21. (in Chinese)
[7] Cui Y, Zhang M, Wang D, et al. Bit-based support vector machine nonlinear detector for millimeter-wave radio-over-fiber mobile fronthaul systems[J]. Optics Express, 2017, 25(21):26186-26197.
[8] Niu W, Ha Y, Chi N. Novel phase estimation scheme based on support vector machine for multiband-CAP visible light communication system[C]//2018 Asia Communications and Photonics Conference (ACP), 2018:1-3.
[9] Niu W, Ha Y, Chi N. Machine learning scheme for geometrically-shaped constellation classification utilizing support vector machine in multi-access internet of vehicle lighting[C]//2019 18th International Conference on Optical Communications and Networks (ICOCN), 2019:1-3.
[10] Pfau T, Liu X, Chandrasekhar S. Optimization of 16-ary quadrature amplitude modulation constellations for phase noise impaired channels[C]//2011 37th European Conference and Exhibition on Optical Communication, 2011:1-3.
[11] Qu Z, Djordjevic I B. Geometrically shaped 16QAM outperforming probabilistically shaped 16QAM[C]//2017 European Conference on Optical Communication (ECOC) 2017:1-3.
[12] Frank G. Pulse code communication:US 2632058[P]. 1953-03-17.
[13] Chi N, Chen H. Progress and prospect of high-speed visible light communication[J]. OptoElectronic Engineering, 2020, 47(3):190687.
[14] Ying K, Yu Z, Baxley R J, et al. Nonlinear distortion mitigation in visible light communications[J]. IEEE Wireless Communications, 2015, 22(2):36-45.
[15] Inan B, Lee S C J, Randel S, et al. Impact of LED nonlinearity on discrete multitone modulation[J]. Journal of Optical Communications and Networking, 2009, 1(5):439-451.
[16] Cortes C, Vapnik V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[17] Boser B E, Guyon I M, Vapnik V N. A training algorithm for optimal margin classifiers[C]//Proceedings of the Fifth Annual Workshop on Computational Learning Theory, 1992:144-152.
[18] Hsu C W, Lin C J. A comparison of methods for multiclass support vector machines[J]. IEEE Transactions on Neural Networks, 2002, 13(2):415-425.
[19] Burges C J. A tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2(2):121-167.
[20] Wu X, Chi N. The phase estimation of geometric shaping 8-QAM modulations based on k-means clustering in underwater visible light communication[J]. Optics Communications, 2019, 444:147-153.
[21] Nazeer K A, Sebastian M P. Improving the accuracy and efficiency of the k-means clustering algorithm[C]//Proceedings of the World Congress on Engineering. London:Association of Engineers, 2009, 1:1-3.
[22] Hu F, Zhao Y, Zou P, et al. Non-linear compensation based on polynomial function linked ANN in multi-band CAP VLC system[C]//2019 26th International Conference on Telecommunications (ICT), 2019:206-209.
[23] Graf H P, Cosatto E, Bottou L, et al. Parallel support vector machines:the cascade SVM[C]//Advances in Neural Information Processing Systems, 2005:521-52.
[24] Chi N, Zhao Y, Shi M, et al. Gaussian kernel-aided deep neural network equalizer utilized in underwater PAM8 visible light communication system[J]. Optics Express, 2018, 26(20):26700-26712.
