Eurofuse 2011 pp 375-387 | Cite as

Modelling Fish Habitat Preference with a Genetic Algorithm-Optimized Takagi-Sugeno Model Based on Pairwise Comparisons

  • Shinji Fukuda
  • Willem Waegeman
  • Ans Mouton
  • Bernard De Baets
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 107)

Abstract

Species-environment relationships are used for evaluating the current status of target species and the potential impact of natural or anthropogenic changes of their habitat. Recent researches reported that the results are strongly affected by the quality of a data set used. The present study attempted to apply pairwise comparisons to modelling fish habitat preference with Takagi-Sugeno-type fuzzy habitat preference models (FHPMs) optimized by a genetic algorithm (GA). The model was compared with the result obtained from the FHPM optimized based on mean squared error (MSE). Three independent data sets were used for training and testing of these models. The FHPMs based on pairwise comparison produced variable habitat preference curves from 20 different initial conditions in the GA. This could be partially ascribed to the optimization process and the regulations assigned. This case study demonstrates applicability and limitations of pairwise comparison-based optimization in an FHPM. Future research should focus on a more flexible learning process to make a good use of the advantages of pairwise comparisons.

Keywords

Pairwise Comparison Membership Function Mean Square Error Habitat Preference Habitat Variable 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Adriaenssens, V., De Baets, B., Goethals, P., De Pauw, N.: Fuzzy rule-based models for decision support in ecosystem management. Sci. Total Environ. 319, 1–12 (2004)CrossRefGoogle Scholar
  2. 2.
    Ahmadi-Nedushan, B., Hilaire, A.S., Bérubé, B., Robichaud, E., Thiémonge, N., Bobée, B.: A review of statistical methods for the evaluation of aquatic habitat suitability for instream flow assessment. River Res. Appl. 22, 503–523 (2006)CrossRefGoogle Scholar
  3. 3.
    Bovee, K.D., Lamb, B.L., Bartholow, J.M., Stalnaker, C.B., Taylor, J., Henriksen, J.: Stream habitat analysis using the instream flow incremental methodology. U.S. Geological Survey, Biological Resources Division Information and Technology Report. USGS/BRD-1998-0004 (1998)Google Scholar
  4. 4.
    Elith, J., Graham, C.H.: Do they? How do they? Why do they differ? On finding reasons for differing performances of species distribution models. Ecography 32, 66–77 (2009)CrossRefGoogle Scholar
  5. 5.
    Fielding, A.H., Bell, J.F.: A review of methods for the assessment of prediction errors in conservation presence/absence models. Environ. Conserv. 24(1), 38–39 (1997)CrossRefGoogle Scholar
  6. 6.
    Fukuda, S., De Baets, B., Mouton, A.M., Waegeman, W., Nakajima, J., Mukai, T., Hiramatsu, K., Onikura, N.: Effect of model formulation on the optimization of a genetic Takagi-Sugeno fuzzy system for fish habitat suitability evaluation. Ecol. Model 222, 1401–1413 (2011)CrossRefGoogle Scholar
  7. 7.
    Fürnkranz, J., Hüllermeier, E.: Preference Learning. Springer, Heidelberg (2010)MATHGoogle Scholar
  8. 8.
    Goldberg, D.: Genetic algorithms in search, optimization, and machine learning. Addison-Wesley, Reading (1989)MATHGoogle Scholar
  9. 9.
    Guisan, A., Zimmermann, N.E.: Predictive habitat distribution models in ecology. Ecol. Model 135, 147–186 (2000)CrossRefGoogle Scholar
  10. 10.
    Hiramatsu, K., Fukuda, S., Shikasho, S.: Mathematical modeling of habitat preference of Japanese medaka for instream water environment using fuzzy inference. Trans. JSIDRE 228, 65–72 (2003) (in Japanese with English abstract)Google Scholar
  11. 11.
    Hüllermeier, E., Fürnkranz, J., Cheng, W., Brinker, K.: Label ranking by learning pairwise preferences. Artif. Intell. 172, 1897–1916 (2008)MATHCrossRefGoogle Scholar
  12. 12.
    Lechowicz, M.J.: The sampling characteristics of electivity indices. Oecologia (Berl.) 52, 22–30 (1982)CrossRefGoogle Scholar
  13. 13.
    Mouton, A.M., De Baets, B., Goethals, P.L.M.: Ecological relevance of performance criteria for species distribution models. Ecol. Model. 221, 1995–2002 (2010)CrossRefGoogle Scholar
  14. 14.
    Pino-Mejías, R., Cubiles-de-la-Vega, M.D., Anaya-Romero, M., Pascual-Acosta, A., Jordn-Lpez, A., Bellinfante-Crocci, N.: Predicting the potential habitat of oaks with data mining models and the R system. Environ. Modell Softw. 25, 826–836 (2010)CrossRefGoogle Scholar
  15. 15.
    Takagi, T., Sugeno, M.: Fuzzy identification of systems and its appfications to modelling and comrol. IEEE Trans. Systems Man Cybernet 15, 116–132 (1985)MATHGoogle Scholar
  16. 16.
    Van Broekhoven, E., Adriaenssens, V., De Baets, B.: Interpretability-preserving genetic optimization of linguistic terms in fuzzy models for fuzzy ordered classification: An ecological case study. Int. J. Approx Reasoning 44, 65–90 (2007)MATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Shinji Fukuda
    • 1
  • Willem Waegeman
    • 2
  • Ans Mouton
    • 3
  • Bernard De Baets
    • 2
  1. 1.Kyushu UniversityFukuokaJapan
  2. 2.Ghent UniversityGhentBelgium
  3. 3.Research Institute for Nature and Forest (INBO)BrusselsBelgium

Personalised recommendations