Building Fuzzy Robust Regression Model Based on Granularity and Possibility Distribution

  • Yoshiyuki Yabuuchi
  • Junzo WatadaEmail author
Part of the Studies in Big Data book series (SBD, volume 8)


The characteristic of the fuzzy regression model is to enwrap all the given samples. The fuzzy regression model enables us to take the possibility interval for a granular instead of a single numerical value. This granular provides the wider treatment for us to human-centered understanding of the latent system. Such a granule or interval of fuzzy regression model is created by considering how far a sample is from the central values. That means when samples are widely scattered the size of a granular or an interval of the fuzzy model is widened. That is, the fuzziness of the fuzzy regression model is decided by the range of sample distribution. Therefore, outliers make the fuzzy regression model distorted. This chapter describes the model building of fuzzy robust regression from the perspective of granularity by removing improper data based on genetic algorithm. Moreover, let us build the fuzzy regression model that places the largest grade on the central point of scattering samples.


Fuzzy regression model Robustness Granularity Possibility distribution Human centered understanding Outliers Genetic algorithm 


  1. 1.
    Coppi, R., D’Urso, P., Giordani, P., Santoro, A.: Least squares estimation of a linear regression model with LR fuzzy response. Comput. Stat. Data Anal. 51(1), 267–286 (2006)CrossRefzbMATHMathSciNetGoogle Scholar
  2. 2.
    Diamond, P.: Least squares and maximum likelihood regression for fuzzy linear models. In: Kacprzyk, J., Fedrizzi, M. (eds.) Fuzzy Regression Analysis. Omnitech Press, Warsaw, pp. 137–151 (1992)Google Scholar
  3. 3.
    Diamond, P.: Fuzzy least squares. Inf. Sci. 46(3), 141–157 (1988)CrossRefzbMATHMathSciNetGoogle Scholar
  4. 4.
    D’Urso, P., Gastaldi, T.: A least-squares approach to fuzzy linear regression analysis. Comput. Stat. Data Anal. 34(4), 427–440 (2000)CrossRefzbMATHGoogle Scholar
  5. 5.
    Guo, P., Tanaka, H.: Fuzzy DEA: a perceptual evaluation method. Fuzzy Sets Syst. 119(1), 149–160 (2001)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Hasuike, T., Katagiri, H., Ishii, H.: Multiobjective random fuzzy linear programming problems based on the possibility maximization model. J.Adv. Comput. Intell. Intell. Inf. 13(4), 373–379 (2009)Google Scholar
  7. 7.
    Honda, A., Okazaki, Y.: Identification of fuzzy measures with distorted probability measures. J.Adv. Comput. Intell. Intell. Inf. 9(5), 467–476 (2005)Google Scholar
  8. 8.
    Hong, D.H., Hwang, C., Ahn, C.: Ridge estimation for regression models with crisp inputs and Gaussian fuzzy output. Fuzzy Sets Syst. 142(2), 307–319 (2004)CrossRefzbMATHMathSciNetGoogle Scholar
  9. 9.
    Inuiguchi, M., Tanino, T.: Interval linear regression methods based on minkowski difference: a bridge between traditional and interval linear regression models. Kybernetika 42(4), 423–440 (2006)zbMATHMathSciNetGoogle Scholar
  10. 10.
    Ishibuchi, H., Tanaka, H.: Several formulations of interval regression analysis. In: Proceedings of Sino–Japan Joint Meeting on Fuzzy Sets and Systems, Section B2-2 (1990)Google Scholar
  11. 11.
    Imoto, S., Yabuuchi, Y., Watada, J.: Fuzzy regression model of R&D project evaluation. Appl. Soft Comput. J. 8(3), 1266–1273, 2008 (Special Issue on Forging New Frontiers) Google Scholar
  12. 12.
    Modarres, M., Nasrabadi, E., Nasrabadi, M.M.: Fuzzy linear regression model with least square errors. Appl. Math. Comput. 163(2), 977–989 (2005)CrossRefzbMATHMathSciNetGoogle Scholar
  13. 13.
    Science and Technology Agency: Energy Consumption and the Global Environment in Asia (1992) (in Japanese)Google Scholar
  14. 14.
    Shibata, K., Watada, J., Yabuuchi, Y.: A fuzzy robust regression approach for evaluating electric and electronics corporations. J. Jpn. Ind. Manag. Assoc. 59(1), 58–67 (2008)Google Scholar
  15. 15.
    Tajima, H.: A proposal of fuzzy regression model. In: Proceedings of the Vietnam–Japan Bilateral Symposium Fuzzy Systems and Applications, pp. 383–389 (1998)Google Scholar
  16. 16.
    Tanaka, H., Watada, J., Asai, K.: Linear Regression Analysis by Possibilistic Models. In: Kacprzyk, J., Orlovsky, S. (eds.) pp. 186–199 (1987)Google Scholar
  17. 17.
    Tanaka, H., Watada, J.: Possibilistic linear systems and their application to the linear regression model. Fuzzy Sets Syst. 27(3), 275–289 (1988)CrossRefzbMATHMathSciNetGoogle Scholar
  18. 18.
    Tanaka, H., Ishibuchi, H., Yoshikawa, S.: Exponential possibility regression analysis. Fuzzy Sets Syst. 69(3), 305–318 (1995)CrossRefzbMATHMathSciNetGoogle Scholar
  19. 19.
    Tanaka, H., Guo, P.: Possibilistic Data Analysis for Operations Research. Phisica-Verlag, Heidelberg (1999)Google Scholar
  20. 20.
    Toyoura, Y., Watada, J., Yabuuchi, Y., Ikegame, H., Sato, S., Watanabe, K., Tohyama, M.: Fuzzy regression analysis of software bug structure. CEJOR 12(1), 13–23 (2004)zbMATHMathSciNetGoogle Scholar
  21. 21.
    Toyoura, Y., Watada, J., Khalid, M., Yusof, R.: Formulation of linguistic regression model based on natural words. Soft. Comput. 8(10), 681–688 (2004)CrossRefzbMATHGoogle Scholar
  22. 22.
    Watada, J.: Fuzzy time-series analysis and forecasting of sales volume. In: Kacprzyk, J., Fedrizzi, M. (eds.) Fuzzy Regression Analysis, pp. 211–227 (1992)Google Scholar
  23. 23.
    Watada, J., Yabuuchi, Y.: fuzzy robust regression analysis based on a hyperelliptic function. In: The Proceeding of Third IEEE International Conference on Fuzzy Systems, pp. 1841–1848 (1995)Google Scholar
  24. 24.
    Watada, J., Pedrycz, W.: Handbook of Granular Computing. In: Pedrycz, W., Skowron, A., Kreinovich, V. (eds.) pp. 719–740 (2008)Google Scholar
  25. 25.
    Water Handbook Editorial Committee.: Water Handbook, p. 95. Maruzen, Tokyo (2003) (in Japanese)Google Scholar
  26. 26.
    Yabuuchi, Y., Watada, J.: Fuzzy robust regression analysis based on a hyperelliptic function. In: Proceedings of the 4th IEEE International Conference on Fuzzy Systems, pp. 1841–1848 (1995)Google Scholar
  27. 27.
    Yabuuchi, Y., Watada, J.: Possibility robust regression analysis. In: Proceedings of the 20th International Conference on Computers and Industrial Engineering, pp. 9–12 (1997)Google Scholar
  28. 28.
    Yabuuchi, Y., Watada, J.: Model building based on central position for a fuzzy regression model. Proc. Czech–Jpn. Semin. 2006, 114–119 (2006)Google Scholar
  29. 29.
    Yabuuchi, Y., Watada, J.: Fuzzy regression model building through possibility maximization and its application. Innovative Comput. Inf. Control Express Lett. 4(2), 505–510 (2010)Google Scholar
  30. 30.
    Yabuuchi, Y., Watada, J.: Fuzzy robust regression model by possibility maximization. J.Adv. Comput. Intell. Intell. Inf. 15(4), 479–484 (2011)Google Scholar
  31. 31.
    Yabuuchi, Y., Watada, J.: Japanese economic analysis by possibilistic regression model which built through possibility maximization. J.Adv. Comput. Intell. Intell. Inf. 16(5), 576–580 (2012)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Faculty of EconomicsShimonoseki City UniversityShimonosekiJapan
  2. 2.Graduate School of Information, Production and SystemsWaseda UniversityKitakyushuJapan

Personalised recommendations