경험적 모드분해법에 기초한 계층적 평활방법

Abstract

A signal in real world usually composes of multiple signals having dierent scalesof frequencies. For example sun-spot data is uctuated over 11 year and 85 year.Economic data is supposed to be compound of seasonal component, cyclic componentand long-term trend. Decomposition of the signal is one of the main topics in time seriesanalysis. However when the signal is subject to nonstationarity, traditional time seriesanalysis such as spectral analysis is not suitable. Huang et. al(1998) proposed data-adaptive method called empirical mode decomposition (EMD). Due to its robustnessto nonstationarity, EMD has been applied to various elds. Huang et. al, however,