Blind Equalization Algorithms Based on Neural Network Optimized by Genetic Algorithm

李沅; 李凯; 路旭

您当前的位置：

首页 >

文章列表页 >

Blind Equalization Algorithms Based on Neural Network Optimized by Genetic Algorithm

更新时间：2026-09-14

- Blind Equalization Algorithms Based on Neural Network Optimized by Genetic Algorithm
- 基于遗传优化的神经网络盲均衡算法
- Vol. 30, Issue 2, Pages: 137-142(2009)
- 作者机构：
  
  1. 中北大学电子测试技术国家重点实验室
  2. 西安北方惠安化学工业有限公司
- 作者简介：
- 基金信息：
- DOI：
  CLC：
- Published：2009
- 稿件说明：
移动端阅览
李沅, 李凯, 路旭. Blind Equalization Algorithms Based on Neural Network Optimized by Genetic Algorithm[J]. 2009, 30(2): 137-142.
DOI：

李沅, 李凯, 路旭. Blind Equalization Algorithms Based on Neural Network Optimized by Genetic Algorithm[J]. 2009, 30(2): 137-142. DOI：

摘要

传统前馈神经网络盲均衡中神经网络的初始权重的确定缺乏理论依据

收敛速度慢

容易陷入局部极小值.为有效克服这些缺陷

提出了遗传优化神经网络的盲均衡算法.算法用遗传算法对前馈神经网络的网络权重进行优化

为神经网络提供一个全局较优的局部搜索空间;再利用传统神经网络在这个局部空间进行更精确地搜索

最终实现盲均衡.计算机仿真结果表明:与传统神经网络算法相比

新算法达到了更好的收敛特性和均衡效果

剩余稳态误差减少30%以上

收敛速度加快约20%

误码率也有明显降低.

Abstract

There are some disadvantages such as slow convergence

easy local minimum and no enough theoretical evidence for determining the initial weight of neural network by the traditional FNN blind equalization algorithm.Therefore a genetic algorithm optimizing neural network(GA-BP) is proposed to overcome these disadvantages.First

a preferable local solution space is offered to the neural network by using GA.Then

a precise searching is realized in the space with the conventional neural network algorithm to finish the blind equalization.Finally the comparisons between the traditional FNN algorithm and the GA-BP are carried out

and the simulating results show that the remainder steady-state error has decreased by more than 30%

the convergence rate has improved by 20% and the bit error rate(BER) has dropped obviously.

关键词

Keywords

references

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,2006,6(25):340-345.Xiao Ying,Liu Guozhi,Li Zhenxin,et al.Blind equalization for underwater acoustic communication by geneticalgorithm optimizing neural network[J].Applied Acoustics,2006,6(25):340-345.(in Chinese)

向长城,黄席樾,殷礼胜,等.基于遗传算法与可拓神经网络的故障诊断[J].计算机仿真,2008,25(4):249-252.Xiang Changcheng,Huang Xiyue,Yin Lishen,et al.Fault diagnosis based on genetic algorithm and extension neuralnetwork[J].Computer Simulation,2008,25(4):249-252.(in Chinese)

I.nan G,Hüseyin P,Ucman E.Combining neural network and genetic algorithm for prediction of lung sounds[J].Journal of Medical Systems,2005,29(3):217-231.

Yang Lei,Dai Yu,Zhang Bin,et al.A genetic algorithm optimized new structured neural network for multistagedecision-making problem[C].Sixth International Conference on Parallel and Distributed Computing Applications andTechnologies(PDCAT'05),2005:925-929.

鲁瑞.基于神经网络理论盲均衡算法的研究[D].太原:太原理工大学,2003.

张栋,蔡开元.基于遗传算法的神经网络两阶段学习方案[J].系统仿真学报,2003,15(18):1088-1090.Zhang Dong,Cai Kaiyuan.A genetic-algorithm-based two-stage learning scheme for neural networks[J].Journal ofSystem Simulation,2003,15(18):1088-1090.(in Chinese)

郭红梅.遗传算法在BP神经网络学习中的应用[J].辽宁大学学报(自然科学版),2007,34(2):151-152.Guo Hongmei.Application of genetic algorithm in BP neural network study[J].Journal of Liaoning University(Natural Sciences Edition),2007,34(2):151-152.(in Chinese)

张庆红,程国建.基于遗传算法的神经网络性能优化[J].计算机技术与发展,2007,17(12):125-127.Zhang Qinghong,Chen Guojian.Neural net work optimization based on genetic algorithms[J].Computer Technologyand Development,2007,17(12):125-127.(in Chinese)

Views

197

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Crankshaft Fatigue Life Prediction Based on Neural Network

Memory Enhancement Video Dehazing Algorithm Based on Physics⁃Prior Guidance

Modeling and Validation of Lithium Battery Aging-Electrochemical-Thermal Behavior Based on SEI Film Thickening

基于Optuna优化的遗传算法智能组卷模型

《中北大学学报(自然科学版》》征稿简则

Related Author

李战芬

韩意

刘彦臣

樊孝仁

张进秋

滕涛

黄大山

姚军

Related Institution

中北大学机电工程学院

中国人民解放军63961部队

太原工业学院网络与信息中心

装甲兵工程学院装备试用与培训大队

School of Computer Science and Technology， North University of China

⁰