基于遗传神经网络自适应噪声抵消技术的研究  

Research of adaptive noise cancellation technology based on genetic neural network

作　　者：马莉[1] 韩应征[1] 

机构地区：[1]太原理工大学信息工程学院,山西太原030024

出　　处：《电子设计工程》2011年第10期56-58,共3页Electronic Design Engineering

摘　　要：自适应噪声抵消技术是减除背景噪声影响的有效处理方式。概述了自适应噪声抵消原理、BP算法及遗传算法等基本理论,结合各自的优点,提出一种基于BP神经网络和遗传算法相结合的自适应噪声抵消系统。该系统中采用遗传算法优化网络权值方式构造遗传神经网络,用遗传神经网络替代传统的自适应滤波器,以此达到更好的噪声抵消效果。使用MATLAB仿真实例,发现其消噪效果显著同时信噪比得到提高。The technology of the adaptive noise canceller is on signal processing,which can clear off background noise effect better.By outlining the basic theory on the principle of adaptive noise cancellation,BP algorithm and genetic algorithm,the paper proposed a kind of new algorithm that a designed method to the adaptive noise canceller based on back propagation network optimization with genetic algorithms,which combines the advantages of two algorithms makes the effect more perfect.Through simulate single by using MATLAB,we find the mixed algorithms can save a large amount of learning and calculation time,and improve SNR,which used the genetic algorithm to optimize neural network weights.

关 键 词：自适应噪声抵消器 神经网络 BP算法 遗传算法 信噪比 

分 类 号：TN911.5[电子电信—通信与信息系统]