Wavelet denoising method based on deep learning

• Main Authors: KANG WENWEN, LIN YUQING, DAI ERGANG, WANG KUN, LI SEN, LI FAN, XIE JUN, LI GUOLIANG, HAN FENG, ZHONG HAO, YANG FENGWEN, LIU YUJIAO, YAN CHONGYANG, XIE QING
• Format: Patent
• Language: Chinese; English
• Published: 21.07.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention discloses a wavelet denoising method based on deep learning, which adopts a neural network to realize a wavelet denoising function, and can automatically adjust network parameters according to the characteristics of signals to replace the selection process of a wavelet basis function when different signals are input, thereby improving the denoising processing efficiency and achieving a better denoising effect. And the method has wider applicability. 本发明公开了一种基于深度学习的小波去噪方法，本发明采用神经网络来实现小波去噪的功能，在输入不同信号时，能够根据信号的特点来自动调整网络参数以取代小波基函数的选取过程，提高去噪处理的效率，并且达到更好的去噪效果，具有更为广泛的适用性。