PriMera Scientific Engineering (ISSN: 2834-2550)

Research Article

Volume 8 Issue 2

Application of PCA in the Frequency Domain using the Covariance Spectrum

Rune Brincker*, Sandro Amador, Manuel Aenlle Lopez, Guangli Du, Umberto Alibrandi and Emmanouil Lydakis

February 03, 2026

DOI : 10.56831/PSEN-08-248

View PDF

Abstract

In this paper we will consider a re-interpretation of principal component analysis (PCA) for the case of time series of correlated data where the principal components are partly covered in noise, so that only in a part of the considered frequency band, the principal components are visible. In this case it might be useful to consider a representation of the spectral density matrix that is a real and one-sided function of frequency, in this paper denoted the covariance spectrum, which is directly representing the covariance matrix as a function of frequency. This means that if a principal component is dominating in a narrow frequency band, it might not be visible on the time domain, but be visible in the narrow band. The covariance spectrum can then be added in the considered band to represent the covariance matrix of the principal component, and classical PCA can be used to illustrate the properties of the principal component. Basic theory is introduced, and the principle is illustrated on a case with two harmonics in white noise acting on an arbitrary mechanical system.

References

  1. IT Jolliffe. Principal components analysis, Second Edition, Springer (2002).
  2. Terrence D Lagerlund, Frank W Sharbrough and Neil E Busacker. “Use of principal component analysis in the frequency domain for mapping electroencephalographic activities: comparison with phase-encoded Fourier spectral analysis”. Brain Topography 17.2 (2004): 73-84.
  3. Kyusoon Kim and Hee-Seok Oh. “Principal Component Analysis in the Graph Frequency Domain”. arXiv:2410.08422v1 [stat.ME] (2024).
  4. Alain Boudou and Sylvie Viguier-Pla. “On proximity between PCA in the frequency domain and usual PCA”. Statistics, A Journal of Theoretical and Applied Statistic. 40.5 (2004): 447-464.
  5. Chuncheng Liu., et al. “Application of principal component analysis for frequency-domain full waveform inversion”. SEG Las Vegas 2012 Annual Meeting (2012).
  6. Raanju R Sundararajan. “Principal Component Analysis using Frequency Components of Multivariate Time Series”. arXiv:2010.04515v1 [stat.ME] (2020).
  7. Yacine Aït-Sahaliaa and Dacheng Xiub. “Principal Component Analysis of High-Frequency Data”. Journal of the American Statistical Association 114.525 (2019): 287-303.
  8. R Brincker, L Zhang and P Andersen. “Modal identification from ambient responses using frequency domain decomposition”. Proc. of the International Modal Analysis Conference (IMAC), San Antonio, Texas, USA, (2000).
  9. Yi Liu, R Brincker and J MacDonald. “Consistent real-valued and one-sided spectral density functions”. Proc of 8th International Operational Modal Analysis Conference (IOMAC), Copenhagen (2019): 409-420.
  10. The ARTeMIS software for operational modal analysis”. https://www.svibs.com/  
  11. DE Newland. “An Introduction to Random Vibrations, Spectral & Wavelet Analysis”. Third Edition, Dover Publications (2005).