小波变换用于奇异性检测与小波类型选择的仿真  

Simulation on Detection of Singularity and Selection of Wavelet Type with Wavelet

作　　者：张德丰[1] 马莉[1] 梁忠宏[2] 

机构地区：[1]佛山科学技术学院计算机系,佛山528000 [2]哈尔滨工业大学航天学院,哈尔滨150001

出　　处：《系统仿真学报》2008年第24期6795-6798,共4页Journal of System Simulation

基　　金：佛山科学技术学院专项基金资助项目

摘　　要：小波变换具有空间局部性,它能聚焦于信号的局部结构,因此用小波变换确定信号的奇异性位置更加有效。提出了一种新的奇异性检测方法,它包含两点:寻找小波变换模极大值在细尺度的坐标以确定奇异性发生的时间;通过小波变换模极大值的衰减计算Lipschitz指数,从而判断奇异的性质。在仿真实验的基础上验证了方法的可行性。并在仿真实验结果的基础上,总结出了小波类型选择的规律。Wavelet transform has local space, and it can focus on local signal structure, therefore using wavelet transform to determine the position of signal singularity is more effectively. A new method was put forward, and its singular detection contains two： looking for wavelet modulus maxima in fine scales coordinates to determine the time of the singularity; through wavelet modulus maxima Lipschitz exponent, the attenuation calculation to judge the singularity. Based on the simulation experiment, the feasibility of the method was validated. And on the basis of the experimental results, the wavelet type selection of law was summed up.

关 键 词：小波变换 奇异性 仿真 傅立叶变换 多分辨分析 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]