首页 > 论文 > 激光与光电子学进展 > 55卷 > 6期(pp:60602--1)

基于模糊聚类与BP神经网络的无线光副载波调制识别

Modulation Recognition of Wireless Optical Subcarrier Based on Fuzzy Clustering and Back Propagation Neural Net

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

基于大气弱湍流信道模型, 设计了模糊聚类与改进反向传播(BP)神经网络相结合的星座图识别方法。采用模糊C均值(FCM)算法对无线光副载波多进制相移键控(MPSK)信号星座图进行聚类分析, 通过计算其硬趋势均值获得星座图特征, 然后将特征输入改进BP神经网络分类器进行调制识别。在对数振幅起伏方差σ2χ=0.1时, 总正确识别率达到100%, 随着起伏方差的增大, MPSK信号星座图聚敛性变差, 但总正确识别率也达到87.5%, 同时提高了16进制相移键控(16PSK)调制的识别率。

Abstract

Based on the atmospheric weak turbulence channel model, a constellation recognition method based on fuzzy clustering and improved back propagation (BP) neural network is designed. The fuzzy C mean (FCM) algorithm is used to get the cluster center of the wireless optical multiple phase shift keying (MPSK) subcarrier signals constellation. By calculating the hard tendency of the fuzzy classification, we obtain the feature of constellation. Finally, improved BP neural network as the classifier is designed and used to accomplish the modulation recognition. When the log-amplitude fluctuation variance σ2χ=0.1, the correct recognition rates of four different modulation styles are all up to 100%. With the increase of fluctuation variance, convergence of MPSK signal constellation diagram becomes worse, but the total correct recognition rate also gets to 87.5%, and the recognition rate of 16 phase shift keying (16PSK) is improved obviously.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TN929.1

DOI:10.3788/lop55.060602

所属栏目:光纤光学与光通信

基金项目:国家自然科学基金(61671375)、陕西省工业攻关科技计划项目(2016GY-802)、陕西省重点产业链创新项目(2017ZDCXL-GY-06-01)

收稿日期:2017-11-13

修改稿日期:2017-12-12

网络出版日期:--

作者单位    点击查看

陈丹:西安理工大学自动化与信息工程学院, 陕西 西安 710048
王晨昊:西安理工大学自动化与信息工程学院, 陕西 西安 710048
姚伯羽:西安理工大学自动化与信息工程学院, 陕西 西安 710048

联系人作者:陈丹(chdh@xaut.edu.cn)

备注:陈丹(1975-), 女, 博士, 副教授, 主要从事无线光通信、现代信号处理方面的研究。E-mail: chdh@xaut.edu.cn

【1】Lu Q, Liu Q C, Mitchell G S. Performance analysis for optical wireless communication systems using subcarrier PSK intensity modulation through turbulent atmospheric channel[C]∥IEEE Global Telecommunications Conference, Dallas, TX. [S. l.]: IEEE, 2004, 3: 1872-1875.

【2】Hassan M Z, Hossain M J, Cheng J L. Exact BER analysis of subcarrier QAM and PSK intensity modulations in strong turbulence[C]∥International Conference on Computing, Networking and Communications, Optical and Grid Networking Symposium, Honolulu, HI, USA. [S. l.]: IEEE, 2014: 478-483.

【3】Chen D, Ke X Z. Analysis on error rate of wireless optical communication using subcarrier modulation on turbo code[J]. Acta Optica Sinica, 2010, 30(10): 2859-2863.
陈丹, 柯熙政. 基于Turbo码的无线光通信副载波误码性能分析[J]. 光学学报, 2010, 30(10): 2859-2863.

【4】Samimi H. Performance of subcarrier intensity modulated FSO systems over gamma-gamma turbulence channels with pointing errors[J]. Wireless Personal Communications, 2016, 95(2): 1407-1416.

【5】Chen D, Ke X Z. Modulation recognition of wireless optical communication using subcarrier modulation over atmosphere weak turbulence channel[J]. Laser & Optoelectronics Progress, 2012, 49(7): 070601.
陈丹, 柯熙政. 大气弱湍流信道无线光副载波调制识别研究[J]. 激光与光电子学进展, 2012, 49(7): 070601.

【6】Wang J X, Song H. Digital modulation recognition based on constellation diagram[J]. Journal on Communications, 2004, 25(6): 166-173.
王建新, 宋辉. 基于星座图的数字调制方式识别[J]. 通信学报, 2004, 25(6): 166-173.

【7】Ali R, Offiah A, Ramlakhan S. Fuzzy C-Means clustering to analyze bone vibration as a method of screening fracture[C]∥International Symposium on Communication Systems, Networks and Digital Signal Processing, Prague, Czech Republic. [S. l.]: IEEE, 2016: 1-5.

【8】Guo Q, Nan P L, Wan J. Radar signal recognition based on ambiguity function features and cloud model similarity[C]∥International Conference on Ultrawideband and Ultrashort Impulse Signals, Odessa, Ukraine. [S. l.]: IEEE, 2016: 128-134.

【9】Gu M J. Signal recognition method based on fuzzy C-Means and support vector machine[J]. Computer & Digital Engineering, 2013, 41(3): 367-369.
顾敏剑. 基于模糊C均值聚类和支持向量机的信号识别方法[J]. 计算机与数字工程, 2013, 41(3): 367-369.

【10】Ghassemlooy Z, Popoola W, Rajbhandari S, et al. Optical wireless communication: system and channel modeling with Matlab[M]. Boca Raton: CRC Press, 2013: 131-137

【11】Wang Z F. Comparison of four kinds of fuzzy C-Means clustering methods[C]∥International Symposium on Information Processing, Qingdao, China. [S. l.]: IEEE, 2010: 563-566.

【12】Helmy M O, Zaki F W. Identification of linear bi-dimensional digital modulation schemes via clustering algorithms[C]∥International Conference on Computer Engineering & Systems, Cairo, Egypt. [S. l.]: IEEE, 2009: 385-390.

【13】Rivera F E, Zapata E L, Carazo J M. Cluster validity based on the hard tendency of the fuzzy classification[J]. Pattern Recognition Letters, 1990, 11(1): 7-12.

引用该论文

Chen Dan,Wang Chenhao,Yao Boyu. Modulation Recognition of Wireless Optical Subcarrier Based on Fuzzy Clustering and Back Propagation Neural Net[J]. Laser & Optoelectronics Progress, 2018, 55(6): 060602

陈丹,王晨昊,姚伯羽. 基于模糊聚类与BP神经网络的无线光副载波调制识别[J]. 激光与光电子学进展, 2018, 55(6): 060602

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF