论文部分内容阅读
小波神经网络利用了小波变换的良好的时域和频域的分析能力以及神经网络的自学习能力,具有良好的容错能力和逼近能力。针对双模斯噪声,提出基于小波神经网络的双模噪声背景下信号的消噪算法,介绍了双模噪声的3种简化模型,阐述了小波神经网络的基本概念以及基于此方法的消噪算法。将小波神经网络用于此3种双模噪声背景下信号的消噪。实验结果表明,该方法能有效地消除已知信号中的双模噪声。
Wavelet neural network makes use of the good ability of wavelet transform in the analysis of time domain and frequency domain as well as the self-learning ability of neural network, and has good fault tolerance and approximation ability. According to the two-mode noise, the signal denoising algorithm based on wavelet neural network in dual-mode noise is proposed. Three simplified models of dual-mode noise are introduced. The basic concepts of wavelet neural network and the denoising algorithm based on this method . The wavelet neural network is used for signal de-noising in the three kinds of dual-mode noise background. Experimental results show that this method can effectively eliminate the dual-mode noise in the known signal.