Sun Jingyuan,Meng Qingfeng
(School of Mechanical Engineering,Xi'an Jiaotong University,Xi'an 710049,China)
Abstract: A nonparametric method for extracting waveforms of signal embedded in additive noise is presented,where the construction of the general basis functions described by some parameters is unnecessary. Using a template signal that contains a prior signal information, a set of nonparametric basis functions are obtained by means of a filter bank.The primary principle of the proposed method is to match the observed signal with the template signal in each frequency band.The choice of the template signal facilitates the method for a wide variety of applications.Simulated and experimental results show that the method is practical and effective,even if the noise frequency band coinsides with that of the signal.
Keywords: nonparametric;waveform extraction;template signal;filter bank