门控递归单元神经网络坐标变换盲均衡算法

魏海文; 郭业才

Chinese

您当前的位置：

首页 >

文章列表页 >

门控递归单元神经网络坐标变换盲均衡算法

更新时间：2026-09-04

- 门控递归单元神经网络坐标变换盲均衡算法
- Coordinate transformation blind equalization algorithm based on gated recurrent unit neural network
- 微电子学与计算机 2019年36卷第9期页码：89-93
- 作者机构：
  
  1. 南京信息工程大学机构江苏省气象探测与信息处理重点实验室,江苏,南京,211800
  2. 江苏省大气环境与装备技术协同创新中心,江苏,南京,211800
- 作者简介：
- 基金信息：
  
  国家自然科学基金 61673222江苏省高校自然科学研究重大项目 13KJA510001江苏省六大人才高峰项目 2008026
- DOI：
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
魏海文, 郭业才. 门控递归单元神经网络坐标变换盲均衡算法[J]. 微电子学与计算机, 2019, 36(9): 89-93, 98.

WEI Hai-wen, GUO Ye-cai. Coordinate transformation blind equalization algorithm based on gated recurrent unit neural network[J]. 2019, 36(9): 89-93.
魏海文, 郭业才. 门控递归单元神经网络坐标变换盲均衡算法[J]. 微电子学与计算机, 2019, 36(9): 89-93, 98. DOI：

WEI Hai-wen, GUO Ye-cai. Coordinate transformation blind equalization algorithm based on gated recurrent unit neural network[J]. 2019, 36(9): 89-93. DOI：

摘要

针对数字信号传输过程中的码间干扰问题

提出了门控递归单元神经网络坐标变换盲均衡算法(GRUNN-CT-CMA).首先

在递归神经网络基础上加入门控结构

使门控递归单元神经网络(GRUNN)对长时间跨度信息的感知能力更强、记忆力更持久.其次

在GRUNN中引入坐标变换得到的盲均衡算法

进一步降低了稳态误差、加快了代价函数收敛速度.结果表明

与常模盲均衡算法(CMA)和延迟单元递归神经网络盲均衡算法(BRNN-CMA)相比

GRUNN-CT-CMA在均衡高阶多模信号时

稳态误差最小、收敛速度最快、输出信号星座图最清晰.

Abstract

In order to solve the problem of inter symbol interference in the process of digital signal transmission

a coordinate transformation constant modulus blind equalization algorithm based on gated recurrent unit neural network (GRUNN-CT-CMA) is proposed. Firstly

based on the recurrent neural network

the gated recurrent unit neural network (GRUNN) with a gate structure was added

which has stronger perception and longer-lasting memory of long-span information. Secondly

the coordinate transformation blind equalization algorithm was introduced in GRUNN

which further reduced the residual error and corrected the phase offset. The simulation results show that comparing with the constant modulus blind equalization algorithm (CMA) and the bias-unit recurrent neural networkconstant modulus blind equalization algorithm (BRNN-CMA)

when GRUNN-CT-CMA equalizing high order multi-mode signals

the steady-state error is minimal

the speed of convergence is the fastest and the constellation of the output signal is the clearest.

关键词

Keywords

references

GIACOUMIDIS E, MATIN A, WEI JINLONG, et al. Blind nonlinearity equalization by machine learning based clustering for single- and multi-channel coherent optical OFDM[J]. Journal of Lightwave Technology, 2018, 36(3): 721-727. DOI: 721

RAVANELLI M, BRAKEL P, OMOLOGO M, et al. Light gated recurrent units for speech recognition[J]. IEEE Transactions on Emerging Topics in Computational Intelligence, 2018, 2(2): 92-102. DOI: 92

YU CHENGPU, XIELIHUA.On Recursive blind equalization in sensor networks[J].IEEE Transactions on Signal Processing, 2015, 63(3):662-672. DOI: 662

樊康, 郭业才.基于小生境遗传优化的正交小波变换盲均衡算法[J].微电子学与计算机, 2011, 28(7):50-53. DOI: 50

CASCIANELLI S, COSTANTE G, CIARFUGLIA T, et al. Full-GRU natural language video description for service robotics applications[J]. Robotics % Automation Letters, 2018, 3(2):841-848. DOI: 841

饶伟, 郭业才, 汪胜前, 等.基于坐标变换的常数模盲均衡新算法[J].电子学报, 2011, 39(1): 7-12. DOI: 7

GUOYE CAI, ZHAO XUEQING, LIU ZHENXING, et al. A modified T/2 fractionally spaced coordinate transformation blind equalization algorithm[J]. International Journal of Communications Network % System Sciences, 2010, 3(2): 183-189. DOI: 183

RAO WEI, YUAN KUNMING, GUO YECAI, et al. A simple constant modulus algorithm for blind equalization suitable for 16-QAM signal[C]// 2008 9th International Conference on Signal Processing. Beijing: IEEE, 2008: 1963-1966.

YING XIAO, DONG YUHUA, LI ZHENXING. Blind equalization in underwater acoustic communication by recurrent neural network with bias unit[C]// 2008 7th World Congress on Intelligent Control and Automation. Chongqing: IEEE, 2008: 25-27.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

低功耗设计的双链电源关断策略的实现与验证

一种基于特征上下文理解与切片分析的肺结核检测算法

基于MSS-YOLO-MPHands融合架构的装配手部动作识别研究

面向处理器分支预测单元的Spectre攻击轻量化防御方法

基于区块链的AI生成内容溯源框架设计研究