改进小波阈值算法在信号处理中的研究  

Research on improved wavelet threshold algorithm in signal processing

作　　者：周进群 胡忠华 孙晓洁 ZHOU Jinqun;HU Zhonghua;SUN Xiaojie(Shennan Circuits Co.,Ltd.,Shenzhen 518117,Guangdong,China;Wuxi Shennan Circuits Co.,Ltd.,Wuxi 214028,Jiangsu,China)

机构地区：[1]深南电路股份有限公司,广东深圳518117 [2]无锡深南电路有限公司,江苏无锡214028

出　　处：《智能计算机与应用》2025年第2期91-95,共5页Intelligent Computer and Applications

摘　　要：采用小波阈值方法去噪虽然应用广泛,但传统的硬阈值和软阈值函数仍然存在截断、连续性及恒定误差等问题,导致信号去噪效果不佳。针对阈值函数局限性导致降噪不佳的问题,提出一种增加调节系数的改进小波阈值算法,通过控制系数可以灵活选择阈值函数满足信号去噪需求。仿真与实验测试表明,改进算法有效提高了信号的去噪效果,同时信噪比均方误差均有了明显改善,验证了改进算法的实际去噪效果和与原信号的接近程度,可以满足各种类型数字信号的去噪需求。Although the wavelet threshold method is widely used in denoising,the traditional hard threshold and soft threshold functions still have problems such as truncation,continuity and constant error,which leads to poor signal denoising effect.Aiming at the problem of poor noise reduction caused by the limitation of threshold function,an improved wavelet threshold algorithm with an adjustment coefficient is proposed.The threshold function can be flexibly selected to meet the demand of signal denoising by controlling the coefficient.The simulation and experimental results show that the improved algorithm effectively improves the denoising effect of the signal,and the mean square error of the signal-to-noise ratio has been significantly improved,which verifies the actual denoising effect of the improved algorithm and the closeness to the original signal,and can meet the denoising needs of various types of digital signals.

关 键 词：信号处理 小波阈值去噪 阈值函数 

分 类 号：TN911.4[电子电信—通信与信息系统]