Publication: Data-driven signal decomposition method
Issued Date
2005-12-01
Resource Type
Other identifier(s)
2-s2.0-33947190421
Rights
Mahidol University
Rights Holder(s)
SCOPUS
Bibliographic Citation
ICIA 2005 - Proceedings of 2005 International Conference on Information Acquisition. Vol.2005, (2005), 464-467
Suggested Citation
Pornchai Chanyagorn, Masud Cader, Harold H. Szu Data-driven signal decomposition method. ICIA 2005 - Proceedings of 2005 International Conference on Information Acquisition. Vol.2005, (2005), 464-467. Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/16503
Research Projects
Organizational Units
Authors
Journal Issue
Thesis
Title
Data-driven signal decomposition method
Author(s)
Other Contributor(s)
Abstract
This paper introduces the data-driven signal decomposition method based on the Empirical Mode Decomposition (EMD) technique. The decomposition process uses the data themselves to derive the base function in order to decompose the one-dimensional signal into a finite set of intrinsic mode signals. The novelty of EMD is that the decomposition does not use any artificial data windowing which implies fewer artifacts in the decomposed signals. The results show that the method can be effectively used in analyzing non-stationary signals. Furthermore, we applied this method to analyze closing equity prices of a financial stock. The result demonstrates the usefulness of the method in analyzing financial time series data, and some practical considerations in envelope estimation. © 2005 IEEE.