期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2014
卷号：62
期号：1
出版社：Journal of Theoretical and Applied
摘要：The core intention of this work is to investigate the wavelet function that is optimum in identifying and denoising the various biomedical signals. Using traditional methods it is difficult to recover the noises present in the signals. This paper presents a detail analysis of Discrete Wavelet Transform (DWT) denoising on various wavelet families and biomedical signals such as ECG, EMG and EEG. We have developed a trained network in order to optimally denoise the signals by using a back propagation algorithm in the neural network. Initially noise is added to the original signal, then the signal is decomposed using the Shift Invariant method. After decomposition, the proposed wavelet based method is used for noise removal. Then the signal is reconstructed by using wavelet reconstruction method. The denoised signals will be compressed by a hybrid wavelet shannon fano coding for reducing its storage size.
关键词：DWT; ECG; EEG; EMG; Neural network; Wavelet frequency thresholding
