Skip to main content
SpringerLink
Log in

On Metric Correction and Conditionality of Raw Featureless Data in Machine Learning

  • Proceedings of the 6th International Workshop
  • Published:
Pattern Recognition and Image Analysis Aims and scope Submit manuscript

Abstract

Recently, raw experimental data in machine learning often appear as direct comparisons between objects (featureless data). Different ways to evaluate difference or similarity of a pair of objects in image and data mining, image analysis, bioinformatics, etc., are usually used in practice. Nevertheless, such comparisons often are not distances or correlations (scalar products) like a correct function defined on a limited set of elements in machine learning. This problem is denoted as metric violations in ill-posed matrices. Therefore, it needs to recover violated metrics and provide optimal conditionality of corresponding matrices of pairwise comparisons for distances and similarities. This is the correct basis for using of modern machine learning algorithms.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. R. A. Horn and C. R. Johnson, Matrix Analysis, 2nd ed. (Cambridge University Press, Cambridge, 2013).

    Google Scholar 

  2. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification (Wiley, New York, 2001).

    MATH  Google Scholar 

  3. S. D. Dvoenko, “Clustering and separating of a set of members in terms of mutual distances and similarities,” Trans. Mach. Learn. Data Mining 2 (2), 80–99 (2009).

    Google Scholar 

  4. S. D. Dvoenko and D. O. Pshenichny, “A recovering of violated metric in machine learning”, in Proc. 7th Symposium on Information and Communication Technology (SoICT’16) (ACM, New York, 2016), pp. 15–21. DOI: https://doi.org/10.1145/3011077.3011084

    Google Scholar 

  5. R. L. Bishop and R. J. Crittenden, Geometry of Manifolds (Academic Press, New York, 1964).

    MATH  Google Scholar 

  6. E. Pekalska and R. P. W. Duin, The Dissimilarity Representation for Pattern Recognition. Foundations and Applications (World Scientific, Singapore, 2005).

    Book  MATH  Google Scholar 

  7. I. Dubchak, I. Muchnik, C. Mayor, I. Dralyuk, and S.–H. Kim, “Recognition of a protein fold in the context of the SCOP classification”, Proteins: Struct. Funct. Genetics 35, 401–407 (1999).

    Article  Google Scholar 

  8. A. A. Goshtasby, Image Registration: Principles, Tools and Methods (Springer, London 2012). DOI: 10.1007/978–1–4471–2458–0

    Book  MATH  Google Scholar 

  9. B. Schölkopf and A. J. Smola, Learning with Kernels (MIT Press, Cambridge, 2002).

    MATH  Google Scholar 

  10. Z.–H. Zhou, F. Roli, and J. Kittler (Eds.), Multiple Classifier Systems, tMCS 2013, Lecture Notes in Computer Science (Springer, Berlin, Heidelberg, 2013), Vol. 7872.

    Google Scholar 

  11. R. D. Luce, Individual Choice Behaviour (Wiley, New York, 1959).

    MATH  Google Scholar 

  12. D.S. Watkins, Fundamentals of Matrix Computations, 3rd ed. (Wiley, New York, 2010).

    MATH  Google Scholar 

  13. A. N. Tikhonov and V. Y. Arsenin, Solutions of Ill–Posed Problems (Winston, New York, 1977).

    MATH  Google Scholar 

  14. W. S. Torgerson, Theory and Methods of Scaling (Wiley, New York, 1958).

    Google Scholar 

  15. V. Mottl, S. Dvoenko, O. Seredin, C. Kulikowski, and I. Muchnik, “Featureless pattern recognition in an imaginary Hilbert space and its application to protein fold classification”, in Machine Learning and Data Mining in Pattern Recognition, Proc. MLDM 2001, Ed. by P. Perner, Lecture Notes in Computer Science (Springer, Berlin, Heidelberg, 2001), Vol. 2123, pp. 322–336.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Tula State University, Tula, Russia

    S. D. Dvoenko & D. O. Pshenichny

Authors
  1. S. D. Dvoenko
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. D. O. Pshenichny
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to S. D. Dvoenko.

Additional information

The article is published in the original.

Sergei Danilovich Dvoenko. Graduated from the postgraduate courses of the Institute of Control Science, Russian Academy of Sciences. Received candidate’s degree in 1992. He received the associated professor designation in 1998. Graduated from the doctoral courses of the Tula State University and received doctor’s degree in 2002 at the Dorodnitsyn Computing Centre, Russian Academy of Sciences. Professor at the Tula State University. Member of the Russian organization “Association for Pattern Recognition and Image Analysis.” His scientific interests include the following fields: machine learning and pattern recognition, cluster-analysis and data mining, image processing, hidden Markov models, and fields in applied problems.

Denis Olegovich Pshenichny. Born in 1991. PhD student at the Tula State University. His scientific interests include the following fields: machine learning and pattern recognition, intelligent data analysis based on matrices of pairwise comparisons.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dvoenko, S.D., Pshenichny, D.O. On Metric Correction and Conditionality of Raw Featureless Data in Machine Learning. Pattern Recognit. Image Anal. 28, 595–604 (2018). https://doi.org/10.1134/S1054661818040089

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1134/S1054661818040089

Keywords

Search

Navigation