Neural network blind equalization optimized by parallel genetic algorithm with partial elitist strategy

Er-fu WANG; Yuan-shuo ZHENG; Xin-wu CHEN

doi:10.11959/j.issn.1000-436x.2016148

您当前的位置：

首页 >

文章列表页 >

Neural network blind equalization optimized by parallel genetic algorithm with partial elitist strategy

Academic communication | 更新时间：2024-06-05

- Neural network blind equalization optimized by parallel genetic algorithm with partial elitist strategy
- Journal of Communications Vol. 37, Issue 7, Pages: 193-200(2016)
- 作者机构：
  
  黑龙江大学电子工程学院，黑龙江哈尔滨 150080
- 作者简介：
- 基金信息：
  
  The National Natural Science Foundation of China(61571181);The National Natural Science Foundation of China(61302074)
- DOI：10.11959/j.issn.1000-436x.2016148
  CLC： TN911.5
- Online First：2016-07，
  
  Published：25 July 2016
- 稿件说明：
移动端阅览
Er-fu WANG, Yuan-shuo ZHENG, Xin-wu CHEN. Neural network blind equalization optimized by parallel genetic algorithm with partial elitist strategy[J]. Journal of Communications, 2016, 37(7): 193-200.
DOI：

Er-fu WANG, Yuan-shuo ZHENG, Xin-wu CHEN. Neural network blind equalization optimized by parallel genetic algorithm with partial elitist strategy[J]. Journal of Communications, 2016, 37(7): 193-200. DOI： 10.11959/j.issn.1000-436x.2016148.

摘要

针对高维非凸代价函数下神经网络盲均衡算法收敛速度慢、容易陷入局部极小值的缺点，提出了一种组群并行遗传优化神经网络的方法。根据神经网络拓扑结构进行个体编码，设置控制码和权重系数码以实现对网络拓扑结构和网络权重同时优化。优化迭代过程中根据适应度对个体排序分组，以融合不同遗传算子条件下遗传算法的优势。部分精英策略有效避免最优个体把持进化过程引发早熟的现象。非线性信道条件下的仿真结果证明方法具有更好的收敛性能。

Abstract

Owing to the disadvantage of slow convergence and easy to fall into local minimum of the neural network blind equalization algorithm under high dimensional and non-convex cost function

a parallel genetic algorithm (GA) with partial elitist strategy was proposed to optimize neural network training. According to the neural network topology

individual coding

the control code and the weights were set up to realize the network topology structure and the network weights simultaneously. The individual group was sorted according to the adaptation degree of the optimization iterative process

in order to integrate the advantages of genetic algorithm under the conditions of different genetic operators. Some elite strategies effectively avoid the phenomenon of premature phenomena caused by the optimal individual control in the process of evolution. The simulation results under the nonlinear channel condition show that the method has better convergence performance.

关键词

Keywords

references

PINCEMIN E , BROCHIER N , SELMI M , et al . Novel blind equalizer for coherent DP-BPSK transmission systems: theory and experiment [J ] . IEEE Photonics Technology Letters , 2013 , 25 ( 18 ): 1835 - 1838 .

郭业才，樊康，徐文才，等．基于混合遗传优化的正交小波变换盲均衡算法 [J ] ．数据采集与处理， 2011 , 26 ( 5 ): 503 - 507 .

GUO Y C , FAN K , XU W C , et al . Hybrid blind equalization algo-rithm based on genetic algorithm and wavelet transform [J ] . Journal of Electronics ＆ Information Technology , 2011 , 26 ( 5 ): 503 - 507 .

廖娟，郭业才，刘振兴，等．基于遗传优化的正交小波分数间隔盲均衡算法 [J ] ．兵工学报， 2011 , 32 ( 3 ): 268 - 273 .

LIAO J , GUO Y C , LIU Z X , et al . A fractionally spaced blind equali-zation algorithm based on orthogonal wavelet transform and genetic optimization [J ] . Acta Armamentarii , 2011 , 32 ( 3 ): 268 - 273 .

戴晓明，邹润民，冯瑞，等．混合并行遗传算法求解TSP问题 [J ] . 电子与信息学报， 2002 , 24 ( 10 ): 1424 - 1427 .

LIAO J , GUO Y C , LIU Z X , et al . A fractionally spaced blind equali-zation algorithm based on orthogonal wavelet transform and genetic optimization [J ] . Acta Armamentarii , 2002 , 24 ( 10 ): 1424 - 1427 .

NAFTA A , JOHANNISSON P , SHTAIF M . Blind equalization in optical communications using independent component analysis [J ] . Journal of Lightwave Technology , 2013 , 31 ( 12 ): 2043 - 2049 .

姜春艳．遗传优化神经网络算法在信道盲均衡中的应用 [J ] . 计算机仿真， 2011 , 28 ( 11 ): 145 - 147 .

JIANG C Y . Application of genetic neural network in blind equalization [J ] . Computer Simulation , 2011 , 28 ( 11 ): 145 - 147 .

郭业才，高敏，张艳萍．基于正交小波包变换的前馈神经网络盲均衡算法 [J ] ．电子测量与仪器学报， 2011 , 23 ( 11 ): 59 - 64 .

GUO Y C , GAO M , ZHANG Y P . Feedforward neural network blind equalization algorithm based on orthogonal wavelet packet trans-form [J ] . Journal of Electronic Measurement and Instrument , 2011 , 23 ( 11 ): 59 - 64 .

郭业才，王丽华．模糊神经网络控制的混合小波神经网络盲均衡算法 [J ] ．电子学报， 2011 , 39 ( 4 ): 975 - 980 .

GUO Y C , WANG L H . A hybrid wavelet neural network blind equa-lization algorithm based on fuzzy controlling [J ] . Acta Electronica Sinica , 2011 , 39 ( 4 ): 975 - 980 .

SUN Y S , ZHANG L Y , ZHANG J , et al . Neural network blind equalization algorithm applied in medical CT image restoration [J ] . Mathematical Problems in Engineering , 2013 ,( 2013 ): 1 - 10 .

XIAO Y , LI Z X . Wavelet neural network blind equalization with cascade filter based on RLS in underwater acoustic communication [J ] . Information Technology Journal , 2011 , 10 ( 2 ): 2440 - 2445 .

ABRAR S , ALI A , ZERGUINER A , et al . Tracking performance of two constant modulus equalizers [J ] . IEEE Communications Letters , 2013 , 17 ( 5 ): 830 - 833 .

ASHARIF F , TAMAKI S , ALSHARIF M R , et al . Performance im-provement of constant modulus algorithm blind equalizer for 16 QAM modulation [J ] . ICIC Express Letters , 2013 , 7 ( 4 ): 1377 - 1383 .

宋翀绂，王宝树．提高前馈神经网络学习效率的学习算法探讨 [J ] . 西安电子科技大学学报， 1999 , 26 ( 5 ): 545 - 548 .

SONG C F , WANG B S . Improvement on the efficiency of the learn-ing algorithm for multilayer feedforward neural networks [J ] . Journal of Xidian University , 1999 , 26 ( 5 ): 545 - 548 .

ZAOUCHE A , DAYOUB I , ROUVAEN J M . Baud-spaced constant modulus blind equalization via hybrid genetic algorithm and general-ized pattern search optimization [J ] . International Journal of Electronics and Communications , 2008 , 62 : 122 - 131 .

肖瑛，刘国枝，李振兴，等．遗传优化神经网络的水声信道盲均衡 [J ] ．应用声学， 2006 , 25 ( 6 ): 340 - 345 .

XIAO Y , LIU G Z , LI Z X , et al . Blind equalization for underwater acoustic communication by genetic algorithm optimizing neural net-work [J ] . Applied Acoustics , 2006 , 25 ( 6 ): 340 - 345 .

Views

461

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Research on scenario recognition for THz channels based on mRMR-GA

Low-power-consumption road side unit deployment strategy for urban 2-D 5G Internet of vehicles

Array-based neural network algorithm for multi-parameter joint estimation of underwater acoustic communication signals

Malicious DNS traffic detection based neural networks

Integrated communication and positioning system enabled by fusing visible light and RF

Related Author

HAO Xinyu

LIAO Xi

WANG Yang

LIN Feng

LUO Jiao

ZHANG Jie

YANG Xinjie

WANG Shuai

Related Institution

School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications

Faculty of Electrical Engineering and Computer Science, Ningbo University

School of Information and Communication Engineering, Beijing University of Posts and Telecommunications

School of Information Science and Technology, Southwest Jiaotong University

College of Meteorology and Oceanology, National University of Defense Technology

AI问答

⁰