|
Activity Number:
|
16
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, August 2, 2009 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
| Abstract - #303795 |
|
Title:
|
Extension of Hilbert-Huang Transform to Statistical Problems
|
|
Author(s):
|
Hee-Seok Oh*+ and Donghoh Kim
|
|
Companies:
|
Seoul National University and Sejong University
|
|
Address:
|
Department of Statistics, Seoul, International, 151-747, Korea
|
|
Keywords:
|
empirical mode decomposition ; Hilbert spectrum ; Hilbert-Huang transform ; two-dimensional EMD
|
|
Abstract:
|
Hilbert-Huang transform (HHT) which consists of empirical mode decomposition (EMD) and its Hilbert spectrum has rapidly developed in many disciplines of sciences and engineering since Huang et al. (1988) invented it. In this paper, we briefly review HHT and then discuss some practical issues such as boundary problems for implementation of HHT effectively. In addition, we suggest a statistical EMD based on smoothing techniques and a two-dimensional EMD which can be applicable to various statistical problems including denoising, time series prediction and image processing. Furthermore, we provide theoretical interpretation of EMD that can be considered as only an empirical and data-driven algorithm.
|
