Advertisement

Missing Values in Dissimilarity-Based Classification of Multi-way Data

  • Diana Porro-Muñoz
  • Robert P. W. Duin
  • Isneri Talavera
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8258)

Abstract

Missing values can occur frequently in many real world situations. Such is the case of multi-way data applications, where objects are usually represented by arrays of 2 or more dimensions e.g. biomedical signals that can be represented as time-frequency matrices. This lack of attributes tends to influence the analysis of the data. In classification tasks for example, the performance of classifiers is usually deteriorated. Therefore, it is necessary to address this problem before classifiers are built. Although the absence of values is common in these types of data sets, there are just a few studies to tackle this problem for classification purposes. In this paper, we study two approaches to overcome the missing values problem in dissimilarity-based classification of multi-way data. Namely, imputation by factorization, and a modification of the previously proposed Continuous Multi-way Shape measure for comparing multi-way objects.

Keywords

missing values multi-way data dissimilarity representation 

References

  1. 1.
    Mortensen, P.P., Bro, R.: Real time monitoring and chemical profiling of a cultivation process. Chemometr. Intell. Lab. 84(1-2), 106–113 (2005)CrossRefGoogle Scholar
  2. 2.
    Møller, J., Parolari, G., Gabba, L., Christensen, J., Skibsted, L.: Evaluated surface autofluorescence spectroscopy in order to measure age-related quality index of parma ham during processing. J. Agr. Food Chem. 51, 1224–1230 (2003)CrossRefGoogle Scholar
  3. 3.
    Tomasi, G., Bro, R.: PARAFAC and missing values. Chemometr. Intell. Lab. 75, 163–180 (2005)CrossRefGoogle Scholar
  4. 4.
    Kroonenberg, P.M.: Applied Multiway Data Analysis. John Wiley & Sons (2008)Google Scholar
  5. 5.
    Acar, E., Dunlavy, D.M., Kolda, T.G., Mrup, M.: Scalable tensor factorizations for incomplete data. Chemometr. Intell. Lab. 106(1), 41–56 (2011)CrossRefGoogle Scholar
  6. 6.
    Walczak, B., Massart, D.: Dealing with missing data: Part I. Chemometr. Intell. Lab. 58, 15–27 (2001)CrossRefGoogle Scholar
  7. 7.
    Smilde, A.K., Bro, R., Geladi, P.: Multi-way Analysis. Applications in the chemical sciences. John Wiley & Sons, Inc. (2004)Google Scholar
  8. 8.
    Pekalska, E., Duin, R.P.W.: The Dissimilarity Representation For Pattern Recognition. Foundations and Applications. World Scientific (2005)Google Scholar
  9. 9.
    Porro-Muñoz, D., Duin, R.P.W., Talavera, I., Orozco-Alzate, M.: Classification of three-way data by the dissimilarity representation. Signal Processing 91(11), 2520–2529 (2011)CrossRefGoogle Scholar
  10. 10.
    Millán-Giraldo, M., Duin, R.P.W., Sánchez, J.S.: Dissimilarity-based classification of data with missing attributes. In: Proc. of CIP 2010, pp. 293–298 (2010)Google Scholar
  11. 11.
    Porro-Muñoz, D., Duin, R.P.W., Orozco-Alzate, M., Talavera Bustamante, I.: Continuous multi-way shape measure for dissimilarity representation. In: Alvarez, L., Mejail, M., Gomez, L., Jacobo, J. (eds.) CIARP 2012. LNCS, vol. 7441, pp. 430–437. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  12. 12.
    Lathauwer, L., De Moor, B.: From matrix to tensor: Multilinear algebra and signal processing. In: Proc. of the 4th International Conference on Mathematics in Signal Processing, Warwick, UK, vol. I, pp. 1–11 (1996)Google Scholar
  13. 13.
    Gonzalez, R.C., Woods, R.E.: Digital Image Processing, 3rd edn. Prentice-Hall, Inc., Upper Saddle River (2006)Google Scholar
  14. 14.
    Harshman, R.: Foundations of the Parafac procedure: models and conditions for an explanation multi-modal factor analysis. UCLA Working Papers in Phonetics, Los Angeles 16, 1–84 (1970)Google Scholar
  15. 15.
    Acar, E., Bro, R., Schmidt, B.: New exploratory clustering tool. Journal of Chemomometrics 22, 91–100 (2008)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Diana Porro-Muñoz
    • 2
  • Robert P. W. Duin
    • 2
  • Isneri Talavera
    • 1
  1. 1.Advanced Technologies Application Center (CENATAV)Cuba
  2. 2.Pattern Recognition LabTU DelftThe Netherlands

Personalised recommendations