Advertisement

A Robust Principal Component Analysis for Outlier Identification in Messy Microcalorimeter Data

  • J. W. FowlerEmail author
  • B. K. Alpert
  • Y.-I. Joe
  • G. C. O’Neil
  • D. S. Swetz
  • J. N. Ullom
Article
  • 15 Downloads

Abstract

A principal component analysis (PCA) of clean microcalorimeter pulse records can be a first step beyond statistically optimal linear filtering of pulses toward a fully nonlinear analysis. For PCA to be practical on spectrometers with hundreds of sensors, an automated identification of clean pulses is required. Robust forms of PCA are the subject of active research in machine learning. We examine a version known as coherence pursuit that is simple and fast and well matched to the automatic identification of outlier records, as needed for microcalorimeter pulse analysis.

Keywords

Microcalorimeters X-ray pulses Pulse analysis 

Notes

Acknowledgements

This work was supported by NIST’s Innovations in Measurement Science program and by NASA SAT NNG16PT18I, “Enabling & enhancing technologies for a demonstration model of the Athena X-IFU.” We thank Dan Becker and Malcolm Durkin for numerous discussions and earlier work on pulse outlier identification.

References

  1. 1.
    S.H. Moseley, J.C. Mather, D.J. McCammon, J. Appl. Phys. 56, 1257 (1984).  https://doi.org/10.1063/1.334129 ADSCrossRefGoogle Scholar
  2. 2.
    A.E. Szymkowiak, R.L. Kelley, S.H. Moseley, C.K. Stahle, J. Low Temp. Phys. 93, 281 (1993).  https://doi.org/10.1007/BF00693433 ADSCrossRefGoogle Scholar
  3. 3.
    B.K. Alpert, R.D. Horansky, D.A. Bennett et al., Rev. Sci. Instrum. 84, 6107 (2013).  https://doi.org/10.1063/1.4806802 CrossRefGoogle Scholar
  4. 4.
    S.R. Bandler, E. Figueroa-Feliciano, N. Iyomoto et al., Nucl. Instrum. Methods. Phys. Res. A 559, 817–819 (2006).  https://doi.org/10.1016/j.nima.2005.12.149 ADSCrossRefGoogle Scholar
  5. 5.
    P. Peille, M.T. Ceballos, B. Cobo, et al. SPIE Astronom. Telescopes + Instr., 9905, 99055W–1 (2016).  https://doi.org/10.1117/12.2232011
  6. 6.
    C. Pappas, J.W. Fowler, D.A. Bennet et al., J. Low Temp. Phys, J. Low Temp. Phys. 193, 249 (2018).  https://doi.org/10.1007/s10909-018-1999-8 ADSCrossRefGoogle Scholar
  7. 7.
    B. Shank, J.J. Yen, B. Cabrera et al., AIP Adv. 4, 117106 (2014).  https://doi.org/10.1063/1.4901291 ADSCrossRefGoogle Scholar
  8. 8.
    J.W. Fowler, B.K. Alpert, W.B. Doriese et al., IEEE Trans. Appl. Supercond. 27, 2500404 (2017).  https://doi.org/10.1109/TASC.2016.2637359 CrossRefGoogle Scholar
  9. 9.
    D.J. Fixsen, S.H. Moseley, T. Gerrits, A.E. Lita, S.W. Nam, J. Low Temp. Phys. 176, 16–26 (2014).  https://doi.org/10.1007/s10909-014-1149-x ADSCrossRefGoogle Scholar
  10. 10.
    J.W. Fowler, C.G. Pappas, B.K. Alpert et al., J. Low Temp. Phys. 193, 539 (2018).  https://doi.org/10.1007/s10909-018-1892-5 ADSCrossRefGoogle Scholar
  11. 11.
    S. Kempf, A. Fleischmann, L. Gastaldo, C. Enss, J. Low Temp. Phys. 193, 365 (2018).  https://doi.org/10.1007/s10909-018-1891-6 ADSCrossRefGoogle Scholar
  12. 12.
    S.E. Busch, J.S. Adams, S.R. Bandler et al., J. Low Temp. Phys. 184, 382–388 (2016).  https://doi.org/10.1007/s10909-015-1357-z ADSCrossRefGoogle Scholar
  13. 13.
    D. Yan, T. Cecil, L. Gades et al., J. Low Temp. Phys. 184, 397–404 (2016).  https://doi.org/10.1007/s10909-016-1480-5 ADSCrossRefGoogle Scholar
  14. 14.
    E.J. Candès, X. Li, Y. Ma, J. Wright, J. ACM 58, 11 (2011).  https://doi.org/10.1145/1970392.1970395 CrossRefGoogle Scholar
  15. 15.
    G.H. Golub, C.F. Van Loan, Matrix Computations, 4th edn. (Johns Hopkins, Baltimore, 2013)zbMATHGoogle Scholar
  16. 16.
    R.M. Larsen, Lanczos bidiagonalization with partial reorthogonalization. DAIMI Rep. Ser. 27, 537 (1998).  https://doi.org/10.7146/dpb.v27i537.7070 CrossRefGoogle Scholar
  17. 17.
  18. 18.
    N. Halko, P.G. Martinsson, J.A. Tropp, SIAM Rev. 53, 217 (2011).  https://doi.org/10.1137/090771806 MathSciNetCrossRefGoogle Scholar
  19. 19.
    T. Bouwmans, E.H. Zahzah, Comput. Vis. Image Underst. 122, 22 (2014).  https://doi.org/10.1016/j.cviu.2013.11.009 CrossRefGoogle Scholar
  20. 20.
    N. Vaswani, P. Narayanamurthy, Proc. IEEE 106, 1359 (2018).  https://doi.org/10.1109/JPROC.2018.2844126 CrossRefGoogle Scholar
  21. 21.
    G. Lerman, T. Maunu, Proc. IEEE 106, 1380 (2018).  https://doi.org/10.1109/JPROC.2018.2853141 CrossRefGoogle Scholar
  22. 22.
    N. Kwak, I.E.E.E. Trans, Pattern Anal. Mach. Intell. 30, 1672 (2008).  https://doi.org/10.1109/TPAMI.2008.114 CrossRefGoogle Scholar
  23. 23.
    F. Nie, H. Huang, C. Ding, D. Luo, H. Wang, in Proceedings of 22nd International Joint Conference on Artificial Intelligence (2011). https://bit.ly/2EVPGWu
  24. 24.
    Y.W. Park, D. Klabjan, in IEEE 16th International Conference on Data Mining (2016).  https://doi.org/10.1109/ICDM.2016.0054
  25. 25.
    P.P. Markopoulos, S. Kundu, S. Chamadia, D.A. Pados, I.E.E.E. Trans, Signal Process. 65, 4252 (2017).  https://doi.org/10.1109/TSP.2017.2708023 CrossRefGoogle Scholar
  26. 26.
    F. Nie, H. Huang, “Non-greedy L21-norm maximization for Principal Component Analysis” (2016). arxiv:1603.08293
  27. 27.
    H. Xu, C. Caramanis, IEEE Trans. Inf. Theory 58, 3047 (2012).  https://doi.org/10.1109/TIT.2011.2173156 CrossRefGoogle Scholar
  28. 28.
    M. Rahmani, G. Atia, I.E.E.E. Trans, Signal Process. 65, 6260 (2017).  https://doi.org/10.1109/TSP.2017.2749215 CrossRefGoogle Scholar
  29. 29.
    T. Cai, J. Fan, T. Jiang, J. Mach. Learn. Res. 14, 1837 (2013)MathSciNetGoogle Scholar
  30. 30.
    V. Menon, S. Kalyani, I.E.E.E. Trans, Signal Process. 67, 2439 (2019).  https://doi.org/10.1109/TSP.2019.2905826 CrossRefGoogle Scholar
  31. 31.
    J.W. Fowler, B.K. Alpert, D.A. Bennett et al., Metrologia 54, 494 (2017).  https://doi.org/10.1088/1681-7575/aa722f ADSCrossRefGoogle Scholar
  32. 32.
    K.D. Irwin, G.C. Hilton, Cryogenic Particle Detection (Springer, Heidelberg, 2005), pp. 63–150.  https://doi.org/10.1007/b12169 CrossRefGoogle Scholar
  33. 33.
    J.W. Fowler, B.K. Alpert, W.B. Doriese et al., Astrophys. J. Suppl. 219, 35 (2015).  https://doi.org/10.1088/0067-0049/219/2/35 ADSCrossRefGoogle Scholar
  34. 34.
    P.C. Mahalanobis, Proc. Natl. Inst. Sci. India 2, 49 (1936)Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Quantum Sensors GroupNational Institute of Standards and TechnologyBoulderUSA
  2. 2.Department of PhysicsUniversity of ColoradoBoulderUSA

Personalised recommendations