Enhanced empirical mode decomposition using a novel sifting-based interpolation points detection

Yannis Kopsinis*, Stephen McLaughlin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

19 Citations (Scopus)

Abstract

Empirical mode decomposition (EMD) is a signal analysis method which has received much attention lately due its performance in a number of applications. The main disadvantage of EMD is that it is lacking a theoretical foundation and therefore, our understanding of it have come through intuition and experimental validation. This drawback has significantly limited the potential for improvements to the method itself. In other words, the version of EMD currently used by most researchers is roughly the same as that proposed 9 years ago. In this paper, a novel version of EMD is proposed which exhibits significantly improved decomposition performance. This new development exploits the results of a study on EMD concerning the optimized configuration of EMD with respect to criteria for selection of interpolation points.

Original languageEnglish
Title of host publication2007 IEEE/SP 14th Workshop on Statistical Signal Processing
PublisherIEEE
Pages725-729
Number of pages5
ISBN (Electronic)9781424411986
ISBN (Print)9781424411979
DOIs
Publication statusPublished - 2007
Event14th IEEE/SP WorkShoP on Statistical Signal Processing 2007 - Madison, United States
Duration: 26 Aug 200729 Aug 2007

Conference

Conference14th IEEE/SP WorkShoP on Statistical Signal Processing 2007
Abbreviated titleSSP 2007
Country/TerritoryUnited States
CityMadison
Period26/08/0729/08/07

Keywords

  • Signal analysis
  • Signal decomposition
  • Time - Frequency analysis

ASJC Scopus subject areas

  • Signal Processing

Fingerprint

Dive into the research topics of 'Enhanced empirical mode decomposition using a novel sifting-based interpolation points detection'. Together they form a unique fingerprint.

Cite this