数据采集与处理2011，Vol.26Issue(2)：128-134,7.
基于正交小波变换分数间隔的神经网络盲均衡算法
Blind Neural Network Equalization Algorithm Based on Orthogonal Wavelet Transform Fractionally Spaced Equalizer
摘要
Abstract
A new blind equalization algorithm of neural network based on orthognal wavelet transform fractionally spaced equalizer T/4-FSE-WT-FNN) is proposed to reduce the steadystate error and improve the convergence rate. Four sub-channels are used in the algorithm and neural network is adopted as the equalizer in each channel. Simultaneously, the equalizer input signal is carried out by the orthogonal wavelet transform and normalized. Compared with WTFNN, T/4-FSE-CMA and T/4-FSE-WT-CMA algorithms, the proposed algorithm has the characteristics of faster convergence, smaller steady-state error and lower root mean square error. The efficiency of the proposed algorithm is proved by simulation in underwater acoustic channels.关键词
正交小波变换/神经网络/分数间隔/盲均衡/水声信道分类
信息技术与安全科学引用本文复制引用
高敏,郭业才,刘振兴,赵雪清..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):128-134,7.基金项目
全国优秀博士学位论文作者专项资金(200753)资助项目 （200753）
江苏省高等学校自然科学基金(08KJB510010)资助项目 （08KJB510010）
江苏省"六大人才高峰"培养资助项目. （）
