动态修正下的神经网络盲均衡算法

doi:10.3969/j.issn.1006-2475.2015.05.018

计算机与现代化 ›› 2015, Vol. 0 ›› Issue (5): 85-89.doi: 10.3969/j.issn.1006-2475.2015.05.018

动态修正下的神经网络盲均衡算法

（中山大学新华学院信息科学系，广东广州 510520）

收稿日期:2015-01-29 出版日期:2015-05-18 发布日期:2015-05-18
作者简介:赵慧青(1978-)，女，浙江杭州人，中山大学新华学院信息科学系助教，硕士，研究方向：计算机网络通信，多媒体信息处理。

Neural Network Blind Equalization Algorithm Under Dynamic Correction

(Department of Information Science, Xinhua College of Sun Yat-sen University, Guangzhou 510520, China)

Received:2015-01-29 Online:2015-05-18 Published:2015-05-18

摘要/Abstract

摘要： 针对现有的神经网络算法收敛速度慢以及精确度低的问题，通过对传统的神经网络盲均衡算法以及前馈神经网络进行研究，提出一种具有自动修正效果的前馈神经网络盲均衡算法。该算法通过对算法中的代价函数以及迭代步长因子进行改进，来提高算法的收敛速度；通过对所获得的目标信号进行修正处理，来对所获取的信息进行修正。实验结果表明，该算法的实验结果与预期效果基本相符，具有可靠性强、收敛速度快的优势。

关键词: 神经网络, 动态修正, 盲均衡, 前馈, 代价函数

Abstract: Existing neural network algorithms have the problems of slow convergence speed and low accuracy. In response to this phenomenon, we study traditional neural network blind equalization algorithms and feed forward neural networks, and present a feed forward neural network blind equalization algorithm with the effect of automatic correction. The convergence speed of the algorithm is improved by improving the cost function and iterative step factor. The acquired information is corrected by correcting the acquired target signals. Experimental results show that they are basically consistent with the expected results, and it is of the advantages of high reliability and fast convergence speed.

Key words: neural network, dynamic correction, blind equalization, feed forward, cost function

中图分类号:

TN911.5

赵慧青. 动态修正下的神经网络盲均衡算法[J]. 计算机与现代化, 2015, 0(5): 85-89.

ZHAO Hui-qing. Neural Network Blind Equalization Algorithm Under Dynamic Correction[J]. Computer and Modernization, 2015, 0(5): 85-89.

参考文献

[1] Khuhawar F Y, Unar M A, Mahoto N A, et al. Blind channel equalization using Elman network[J]. Sindh University Research Journal (Science Series), 2014,46(3):335-343.

[2] Xiang Yong, Yang Liu, Peng Dezhong, et al. A second-order blind equalization method robust to ill-conditioned SIMO FIR channels[J]. Digital Signal Processing, 2014,32:57-66.

[3] Chang Yuxin, Hu Guijun, Yan Li, et al. Mode demultiplexing based on multimodulus blind equalization algorithm[J]. Optics Communications, 2014,324:311-317.

[4] Chan J C, Ma Hui, Saha T K. Automatic blind equalization and thresholding for partial discharge measurement in power transformer[J]. IEEE Transactions on Power Delivery, 2014,29(4):1927-1938.

[5] 杨大龙,任亚博,张健,等. 变速率部分更新盲均衡算法[J]. 电讯技术, 2014,54(7): 869-875.

[6] Xiao Ying, Yin Fuliang. Blind equalization based on RLS algorithm using adaptive forgetting factor for underwater acoustic channel[J]. China Ocean Engineering, 2014,28(3):401-408.

[7] 肖瑛,李振兴,董玉华. 线性修正下的神经网络盲均衡算法[J]. 声学技术, 2008,27(4):601-604.

[8] 贾燕玲. 一种变步长神经网络盲均衡算法[J]. 科技信息, 2008(34):83-84.

[9] 高敏,郭业才,刘振兴,等. 基于正交小波变换分数间隔的神经网络盲均衡算法[J]. 数据采集与处理, 2011,26(2):128-134.

[10] Sun Yunshan, Zhang Liyi, Zhang Jin, et al. Neural Network Blind Equalization Algorithm Applied in Medical CT Image Restoration[J/OL]. http://www.hindawi.com/journals/mpe/2013/743546/, 2013-02-08.

[11] 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.

[12] Li Guang, Na Jing, Stoten D P, et al. Adaptive neural network feedforward control for dynamically substructured systems[J]. IEEE Transactions on Control Systems Technology, 2014,22(3):944-954.

[13] Ramasamy M D, Gounder K S. Half of threshold algorithm: An enhanced linear adaptive skipping training algorithm or multilayer feedforward neural networks[J]. American Journal of Applied Sciences, 2014,11(1):38-46.

[14] 魏海,杨华舒,苏志敏,等. 前馈神经网络导数特性分析[J]. 计算机工程, 2014,40(7):197-201.

[15] Chen Ching-Han, Yao Tun-Kai, Kuo Chia-Ming, et al. Evolutionary design of constructive multilayer feedforward neural network[J]. Journal of Vibration and Control, 2013,19(16):2413-2420.

[16] An Ning, Zhao Weigang, Wang Jianzhou, et al. Using multi-output feedforward neural network with empirical mode decomposition based signal filtering for electricity demand forecasting[J]. Energy, 2013,49:279-288.

[17] Augasta M, Gethsiyal, Kathirvalavakumar T. A novel pruning algorithm for optimizing feedforward neural network of classification problems[J]. Neural Processing Letters, 2011,34(3):241-258.

[18] Calderon-Macias C, Sen M K, Stoffa P L. Automatic NMO correction and velocity estimation by a feedforward neural network[J]. Geophysics, 1998,63(5):1696-1707.

[19] Han S, Park S, Pedrycz W. Conditional fuzzy clustering for blind channel equalization[J]. Applied Soft Computing, 2011,11(2):2777-2786.

动态修正下的神经网络盲均衡算法

Neural Network Blind Equalization Algorithm Under Dynamic Correction

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	何思达, 陈平华. 基于意图的轻量级自注意力序列推荐模型[J]. 计算机与现代化, 2024, 0(12): 1-9.
[2]	张晓东1, 白广芝1, 李敏1, 李昊洋2. 基于经验小波变换的油气井产量预测模型 [J]. 计算机与现代化, 2024, 0(12): 53-58.
[3]	刘宝宝, 杨菁菁, 陶露, 王贺应. 基于注意力的DSMSC的遥感图像场景分类[J]. 计算机与现代化, 2024, 0(12): 72-77.
[4]	陈亮, 李诚, 易伟, 熊伟, 汪晓帆, 唐海东. 基于毫米波雷达与视觉融合的电力现场安全帽佩戴检测[J]. 计算机与现代化, 2024, 0(12): 100-107.
[5]	马钰, 杨勇, 任鸽, 帕力旦·吐尔逊. 基于GCN和微调BERT的作文自动评分方法[J]. 计算机与现代化, 2024, 0(09): 33-37.
[6]	陈雪松1, 李衡1, 王浩畅2. 结合注意力机制和Mengzi模型的短文本分类[J]. 计算机与现代化, 2024, 0(09): 101-106.
[7]	高帅鹏, 王怡凡. 基于图像的群体情绪识别综述[J]. 计算机与现代化, 2024, 0(08): 98-107.
[8]	来坤. 字符模糊的中文纸质发票文字识别方法[J]. 计算机与现代化, 2024, 0(08): 114-119.
[9]	周宪溪, 牟莉. 基于改进TF-IDF和AGLCNN的新闻长文本分类模型[J]. 计算机与现代化, 2024, 0(08): 120-126.
[10]	杨江1, 孙晓梅1, 许韬2. 基于业务内容构建股票关联关系的股价预测[J]. 计算机与现代化, 2024, 0(07): 21-25.
[11]	刘存莉1, 雷占占2, 郑澳2. 基于循环卷积神经网络的排水管网缺陷检测方法[J]. 计算机与现代化, 2024, 0(07): 26-35.
[12]	武军凯, 茅正冲. 基于CDKF-RBFPID的激光器恒流源控制器[J]. 计算机与现代化, 2024, 0(07): 100-105.
[13]	周超, 丛鑫, 訾玲玲, 肖谷平. 基于DNN与注意力机制的推荐算法模型[J]. 计算机与现代化, 2024, 0(06): 1-7.
[14]	李珊, 王林娜, 高丁佳, 宣海波. 基于图神经网络的多层银企网络融合研究[J]. 计算机与现代化, 2024, 0(05): 27-32.
[15]	钟海龙1, 2, 何月顺1, 何璘琳1, 陈杰1, 田鸣3, 郑瑞银4. 基于代价敏感卷积神经网络的加密流量分类#br# #br#[J]. 计算机与现代化, 2024, 0(05): 55-60.