Performance Comparison of Dense Frequency Identifications for Empirical Mode Decomposition

Abstract:

Empirical Mode Decomposition(EMD) suffers some difficulties in separating dense frequencies. The Wavelet Packet Transform (WPT) and Singular-Value Decomposition (SVD) as signal preprocessors were used to decompose a simulated signal with dense frequency components and the performances of two signal preprocess technologies were compared in this paper. The results show that Singular-Value Decomposition (SVD) as preprocessor was better in separating dense frequencies than Wavelet Packet Transform (WPT).

• Periodical: Advanced Materials Research (Volumes 378-379)
• Pages: 266-269
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.378-379.266
• Online since: October 2011
• Authors: Min Zheng, Fan Shen
• Keywords: Dense Frequency, Empirical Mode Decomposition (EMD), Signal Processing, Singular Value Decomposition (SVD)

References

[1] S.R. Qina, Y.M. Zhong: Mechanical Systems and Signal Processing Vol.20(2006), p.1941–1952.

[2] H.L. Li, L.H. Yang and D.R: Huang. Mathematics and Computers in Simulation Vol.70(2005), p.22–32.

[3] Z.K. Penga, P.W. Tseb and F.L. Chu: Journal of Sound and Vibration Vol.286(2005), pp.187-205.

[4] Zhaohua Wu, Norden E. Huang: Advances in Adaptive Data Analysis Vol.1(2009), pp.1-41.