The Journal of Supercomputing

, Volume 73, Issue 7, pp 3002–3020 | Cite as

Principal component selection using interactive evolutionary computation

Article
  • 129 Downloads

Abstract

We propose a method to solve the selection problem of principal components in machine learning algorithms based on orthogonal transformation using interactive evolutionary computation. The orthogonal transformation presents a linear transformation method that preserves the inner product in the two coordinate systems, the one is before the transformation, and the other is after the transformation. One of the addressed subjects for machine learning algorithms based on orthogonal transformation is how to decide the number of principal components, and which of the principal components should be used to reconstruct the original data. In this work, we use the interactive differential evolution algorithm to study these subjects using real humans’ subjective evaluation in optimization process. An image compression problem using principal component analysis is introduced to study the proposed method. We do not only solve the selection problem of principal components for machine learning algorithms based on orthogonal transformation using interactive evolutionary computation, but also can analyse the human aesthetical characteristics on visual perception and feature selection arising from the designed method and experimental evaluation. We also discuss and analyse potential research subjects and some open topics, which are invited to further investigate.

Keywords

Interactive evolutionary computation Orthogonal transformation Aesthetical judgement Human computer interaction Visual perception Principal component analysis Principal component selection Interactive differential evolution Image compression 

References

  1. 1.
    Baudat G, Anouar F (2000) Generalized discriminant analysis using a kernel approach. Neural Comput 12(10):2385–2404CrossRefGoogle Scholar
  2. 2.
    Berger CEH, Koeijer JA, Glas W, Madhuizen HT (2006) Color separation in forensic image processing. J Forensic Sci 51(1):100–102CrossRefGoogle Scholar
  3. 3.
    Dawkins R (1986) Blind watchmaker. Alfred A Knopf, New YorkGoogle Scholar
  4. 4.
    Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Eugen 7(2):179–188CrossRefGoogle Scholar
  5. 5.
    Lehmann EL, Casella G (1998) Theory of point estimation, vol 31. Springer Science & Business Media, BerlinMATHGoogle Scholar
  6. 6.
    Li Y, Hu C, Minku LL, Zuo H (2013) Learning aesthetic judgements in evolutionary art systems. Genet Program Evolvable Mach 14(3):315–337CrossRefGoogle Scholar
  7. 7.
    Lim IS, Thalmann D (2000) Tournament selection for browsing temporal signals. In: Proceedings of the 2000 ACM Symposium on Applied Computing, vol 2. ACM, pp 570–573Google Scholar
  8. 8.
    Miller GA (1956) The magical number seven, plus or minus two: some limits on our capacity for processing information. Psychol Rev 63(2):81–97CrossRefGoogle Scholar
  9. 9.
    Ono S, Maeda H, Sakimoto K, Nakayama S (2014) User-system cooperative evolutionary computation for both quantitative and qualitative objective optimization in image processing filter design. Appl Soft Comput 15:203–218CrossRefGoogle Scholar
  10. 10.
    Papoulis A, Pillai SU (2002) Probability, random variables, and stochastic processes. Tata McGraw-Hill Education, New YorkGoogle Scholar
  11. 11.
    Pearson K (1901) Liii. on lines and planes of closest fit to systems of points in space. Lond Edinb Dublin Philos Mag J Science 2(11):559–572CrossRefMATHGoogle Scholar
  12. 12.
    Pei Y (2013) A chaotic ergodicity based evolutionary computation algorithm. In: 2013 Ninth International Conference on Natural Computation (ICNC2013). 23–25 Jul 2013 IEEE, pp 454–459Google Scholar
  13. 13.
    Pei Y (2014) Chaotic evolution: fusion of chaotic ergodicity and evolutionary iteration for optimization. Nat Comput 13(1):79–96MathSciNetCrossRefGoogle Scholar
  14. 14.
    Pei Y (2014) Study on efficient search in evolutionary computation. PhD thesis. Kyushu UniversityGoogle Scholar
  15. 15.
    Pei Y (2015) From determinism and probability to chaos: chaotic evolution towards philosophy and methodology of chaotic optimization. Sci World J 2015:14. doi:10.1155/2015/704587
  16. 16.
    Pei Y (2015) Linear principal component discriminant analysis. In: 2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC2015), IEEE, Oct, 9–12 2015, pp 2108–2113Google Scholar
  17. 17.
    Pei Y, Takagi H (2013) Triple and quadruple comparison-based interactive differential evolution and differential evolution. In: Foundations of Genetic Algorithms Workshop XII (FOGA2013), ACM, Jan, 16–20 2013, pp 173–182Google Scholar
  18. 18.
    Pei Y, Takagi H, (2015) Local information of fitness landscape obtained by paired comparison-based memetic search for interactive differential evolution. In: 2015 IEEE Congress on Evolutionary Computation (IEEE CEC2015), IEEE, May, 25–28 2015, pp 2215-2221Google Scholar
  19. 19.
    Price K, Storn RM, Lampinen JA (2006) Differential evolution: a practical approach to global optimization. Springer Science & Business Media, BerlinGoogle Scholar
  20. 20.
    Schölkopf B, Smola A, Müller K-R (1998) Nonlinear component analysis as a kernel eigenvalue problem. Neural Comput 10(5):1299–1319CrossRefGoogle Scholar
  21. 21.
    Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27(3):379–423MathSciNetCrossRefMATHGoogle Scholar
  22. 22.
    Storn R, Price K (1997) Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11(4):341–359MathSciNetCrossRefMATHGoogle Scholar
  23. 23.
    Takagi H (2001) Interactive evolutionary computation: fusion of the capabilities of ec optimization and human evaluation. Proc IEEE 89(9):1275–1296CrossRefGoogle Scholar
  24. 24.
    Takagi H, Pallez D (2009) Paired comparison-based interactive differential evolution. In: World Congress on Nature & Biologically Inspired Computing 2009 (NaBIC 2009). 9–11 Dec 2009 IEEE, pp 475–480Google Scholar
  25. 25.
    Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.Computer Science DivisionThe University of AizuAizuwakamatsuJapan

Personalised recommendations