光学学报, 2012, 32 (11): 1106001, 网络出版: 2012-08-08   

连续多阈值神经元反馈神经网络盲检测光基带信号

Blind Optical Baseband Signals Detection Using Recurrent Neural Network Based on Continuous Multi-Valued Neurons
阮秀凯 1,2,*张耀举 1,2
作者单位
1 温州大学物理与电子信息工程学院, 浙江 温州 325035
2 温州大学激光与光电子技术研究所, 浙江 温州 325035
摘要
空间分集接收可补偿信道衰落,提出了一种基于幅相联合激励法的连续多阈值神经元反馈神经网络(RNNCMVN)的光基带信号直接盲检测方法。针对多进制相移键控(MPSK)信号的特点,设计了两种连续相位多阈值激励函数形式,并简要讨论了该两类激励函数参数的选择;分别推演基于幅相联合激励法的RNNCMVN光基带信号盲检测方法工作于同步和异步两种模式下的新能量函数及其相关证明。同时针对正交调幅(QAM)信号的特点,分别设计出连续振幅和相位多阈值激励函数形式,最后通过仿真验证了该方法的有效性。
Abstract
Spatial diversity reception can be used over wireless optical links to resist channel fading. A novel blind optical baseband signals detection direct algorithm is proposed by using recurrent neural network based on continuous multi-valued neurons (RNNCMVN) with amplitude and phase continuous activation (APCA). Considering the characteristics of mary phase shift keying (MPSK) signals, two types of continuous multi-valued activation functions are designed and the method of selecting their parameters is illustrated briefly. The new energy functions of synchronous and asynchronous mode of the RNNCMVN are derived and proved, respectively. Considering the characteristics of quadrature amplitude modulation (QAM) signals, the new continuous amplitude and phase multi-valued activation functions are designed and discussed, respectively. Finally, simulation results demonstrate the effectiveness of the proposed method.
参考文献

[1] 王勇, 于蕾, 曹家年. 基于副载波相移键控强度调制和低密度奇偶校验码的光无线通信系统性能[J]. 光学学报, 2009, 29(12): 3295~3298

    Wang Yong, Yu Lei, Cao Jianian. Performance of optical wireless communication system basing on the sub-carrier PSK intensity modulation and LDPC code[J]. Acta Optica Sinica, 2009, 29(12): 3295~3298

[2] 张建昆, 杨宇, 陈弘达. 室内可见光通信调制方法分析[J]. 中国激光, 2011, 38(4): 0405003

    Zhang Jiankun, Yang Yu, Chen Hongda. Modulation scheme analysis of indoor visible light communications[J]. Chinese J. Lasers, 2011, 38(4): 0405003

[3] 张俊文, 邵宇丰, 方武良 等. 基于单边带调制单载波频域均衡技术的研究[J]. 光学学报, 2010, 30(7): 1971~1976

    Zhang Junwen, Shao Yufeng, Fang Wuliang et al.. Research of single carrier frequency domain equalization based on single-sideband modulation[J]. Acta Optica Sinica, 2010, 30(7): 1971~1976

[4] 文爱军, 刘姣姣, 李晓军. 高速光传输系统中八进制差分相位幅度键控性能分析[J]. 中国激光, 2009, 36(3): 614~619

    Wen Aijun, Liu Jiaojiao, Li Xiaojun. Analysis of the transmission performance of octal differential phase-amplitude-shift keying in high speed optical fiber communication system[J]. Chinese J. Lasers, 2009, 36(3): 614~619

[5] 吴鹏飞, 柯熙政, 梁薇. 无线光码分多址中一种改进的盲多用户检测算法[J]. 光学学报, 2012, 32(2): 0206005

    Wu Pengfei, Ke Xizheng, Liang Wei. A modified blind multi-user detection algorithm for wireless optical code division multiple access systems[J]. Acta Optica Sinica, 2012, 32(2): 0206005

[6] 宋艳梅, 许渤, 邱昆. 相干光通信中相位估计与信道均衡的联合使用[J]. 光通信研究, 2012, 169(1): 6~8

    Song Yanmei, Xu Bo, Qiu Kun. Combined use of phase estimation and channel equalization in coherent optical communications[J]. Study on Optical Communications, 2012, 169(1): 6~8

[7] 刘亮, 吴琳, 张帆 等. 差分相移键控和开光键控信号的混合传输实验[J]. 光学学报, 2010, 30(3): 676~680

    Liu Liang, Wu Lin, Zhang Fan et al.. Experimental study of the hybrid transmission of 42.8 Gb/s differential phase shift keying and 9.95 Gb/s on-off keying signal[J]. Acta Optica Sinica, 2010, 30(3): 676~680

[8] K. Burse, R. Yadav, S. Shrivastava. Channel equalization using neural network: a review[J]. IEEE Trans. Syst., Man. Cybern., Part C: Appl. Rev., 2010, 40(3): 352~357

[9] R. Pandey. Feedforward neural network for blind equalization with PSK signal[J]. Neural Comput. & Appl., 2005, 14(4): 290~298

[10] 阮秀凯, 张志涌. 一种复杂星座信号的盲均衡新方法[J]. 电子学报, 2011, 39(7): 1502~1507

    Ruan Xiukai, Zhang Zhiyong. A novel blind equalization method of complex constellation signals[J]. Acta Electronica Sinica, 2011, 39(7): 1502~1507

[11] Xiukai Ruan, Zhiyong Zhang. Blind nonlinear channel equalization using kernel processing[C]. IEEE Image and Signal Processing, 2009. 4406~4411

[12] S. Rajbhandari, Z. Ghassemlooy, M. Angelova. Effective denoising and adaptive equalization of indoor optical wireless channel with artificial light using the discrete wavelet transform and artificial neural network[J]. IEEE J. Lightwave Technol., 2009, 27(20): 4493~4500

[13] 阮秀凯, 张志涌. 基于连续Hopfiled型神经网络的QAM信号盲检测[J]. 电子与信息学报, 2011, 33(7): 1600~1605

    Ruan Xiukai, Zhang Zhiyong. Blind detection of QAM signals using continuous Hopfield-type neural network[J]. J. Electronics & Information Technology, 2011, 33(7): 1600~1605

[14] J. M. Zurada. Neural networks: binary monotonic and multiple-valued[C]. IEEE Internatioal Symposium on Multiple-Valued Logic, 2000. 67~74

[15] I. Aizenberg. Complex-valued neurons with phase-dependent activation functions[C]. International Conference on Artificial Intelligence and Soft Computing, 2010, 6114: 3~10

[16] Wei Zhou, J. M. Zurada. A class of discrete time recurrent neural networks with multi-valued neurons[J]. Neurocomputing, 2009, 72(16-18): 3782~3788

[17] Z. Ghassemlooy, R. J. Dickenson, S. Rajbhandari. Wavelet transform-artificial neural network receiver with adaptive equalization for a diffuse indoor optical wireless OOK link[J]. Mediterranean J. Computers & Networks, 2009, 5(1): 1~9

[18] C. Y. Chi, C. C. Feng, C. H. Chen et al.. Blind Equalization and System Identification[M]. London: Springer-Verlag, 2006. 67~125

[19] L. Marcelino, G. O. Jonathan. Blind equalization using the IRWLS formulation of the support vector machine[J]. Signal Processing, 2009, 89(7): 1436~1445

阮秀凯, 张耀举. 连续多阈值神经元反馈神经网络盲检测光基带信号[J]. 光学学报, 2012, 32(11): 1106001. Ruan Xiukai, Zhang Yaoju. Blind Optical Baseband Signals Detection Using Recurrent Neural Network Based on Continuous Multi-Valued Neurons[J]. Acta Optica Sinica, 2012, 32(11): 1106001.

本文已被 3 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!