Novel Inverse Sigmoid Fuzzy Approach for Water Quality Diatom Classification

Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 150)


The prediction accuracy of the fuzzy diatom models depends on both the manner of defining the fuzzy sets used (their number, shape and the parameters of the membership function (MF)) and the kind of the similarity metric used. In this paper, we define new similarity metric, which takes into the account the maximum number of diatoms’ abundance in specific environmental parameter range. The inverse sigmoid MF is used to shape each MF to describe this relationship, in order to produce more accurate models. This improvement of the ecological modelling is achieved through the process of evaluation results for interpretability; higher prediction accuracy and over fitting resistant. The evaluation results compared with classical classification algorithms have confirmed these findings. Based on these results, one model for each water-quality category class is presented and discussed. From ecological point of view, each model is verified with the existing diatom indicator references found in literature by the biological expert.


Inverse sigmoid distribution fuzzy membership function similarity metric water quality models 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Legendre, P., Birks, H.J.B.: Clustering and partitioning. In: Birks, H.J.B., Lotter, A.F., Juggins, S., Smol, J.P. (eds.) Tracking Environmental Change Using Lake Sediments, Data Handling and Numerical Techniques, vol. 5, Springer, Dordrecht (2011)Google Scholar
  2. 2.
    Deáth, G., Fabricus, K.E.: Classification and regression trees: a powerful yet simple technique for ecological data analysis. Ecology 81, 3178–3192 (2000)CrossRefGoogle Scholar
  3. 3.
    Fielding, A.H.: Cluster and Classification Techniques for the Biosciences. Cambridge University Press, Cambridge (2007)Google Scholar
  4. 4.
    Deáth, G.: Multivariate regression trees: a new technique for modeling species–environment relationships. Ecology 83, 1105–1117 (2002)Google Scholar
  5. 5.
    Deáth, G.: Boosted trees for ecological modelling and prediction. Ecology 88, 243–251 (2007)CrossRefGoogle Scholar
  6. 6.
    Prasad, A.M., Iverson, L.R., Liaw, A.: Newer classification and regression tree techniques: bagging and random forests for ecological predictions. Ecosystems 9, 181–199 (2006)CrossRefGoogle Scholar
  7. 7.
    Cutler, D.R., Edwards, T.C., Beard, K.H.: Random forests for classification in ecology. Ecology 88, 2783–2792 (2007)CrossRefGoogle Scholar
  8. 8.
    Elith, J., Leathwick, J.R., Hastie, T.: A working guide to boosted regression trees. Journal of Animal Ecology 77, 802–881 (2008)CrossRefGoogle Scholar
  9. 9.
    Stroemer, E.F., Smol, J.P.: The diatoms: Applications for the environmental and earth sciences, 2nd edn., pp. 23–47. Cambridge University Press (2010)Google Scholar
  10. 10.
    Naumoski, A., Kocev, D., Atanasova, N., Mitreski, K., Krstić, S., Džeroski, S.: Predicting chemical parameters of water quality form diatoms abundance in lake Prespa and its tributaries. In: Athanasiadis, I.N., Mitkas, P.A., Rizzoli, A.E., Gómez, J.M. (eds.) 4th International ICSC Symposium on Information Technologies in Environmental Engineering - ITEE 2009, pp. 264–277. Springer, Heidelberg (2009)Google Scholar
  11. 11.
    Kocev, D., Naumoski, A., Mitreski, K., Krstić, S., Džeroski, S.: Learning habitat models for the diatom community in Lake Prespa. Ecological Modelling 221(2), 330–337 (2010)CrossRefGoogle Scholar
  12. 12.
    Naumoski, A., Mitreski, K.: Classifying diatoms into trophic state index classes with novel classification algorithm. Procedia Environmental Sciences 2, 1124–1138 (2010)CrossRefGoogle Scholar
  13. 13.
    Naumoski, A., Mitreski, K.: Diatom Classification with Novel Bell Based Classification Algorithm. In: Gusev, M., Mitrevski, P. (eds.) ICT Innovations 2010. CCIS, vol. 83, pp. 245–254. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  14. 14.
    Van Dam, H., Mertens, A., Sinkeldam, J.: A coded checklist and ecological indicator values of freshwater diatoms from the Netherlands. Netherlands Journal of Aquatic Ecology 28(1), 117–133 (1994)CrossRefGoogle Scholar
  15. 15.
    Peter, K.E., Radko, M., Endre, P.: Triangular Norms, pp. 78–98. Kluwer, Dordrecht (2000)zbMATHGoogle Scholar
  16. 16.
    Torra, V., Narukawa, Y.: Modeling Decisions: Information Fusion and Aggregation Operators, pp. 147–175. Springer, Heidelberg (2007)Google Scholar
  17. 17.
    Levkov, Z., Krstić, S., Metzeltin, D., Nakov, T.: Diatoms of Lakes Prespa and Ohrid (Macedonia). Iconographia Diatomologica 16, 603 (2006)Google Scholar
  18. 18.
    Krstić. S.: Description of sampling sites. FP6-project TRABOREMA: Deliverable 2.2 (2005)Google Scholar
  19. 19.
    Krammer, K., Lange-Bertalot, H.: Die Ssswasserflora von Mitteleuropa 2: Bacillariophyceae. 1 Teil, p. 876. Gustav Fischer-Verlag, Stuttgart (1986)Google Scholar
  20. 20.
    Van Der Werff, A., Huls, H.: Diatomeanflora van Nederland. Abcoude - De Hoef (1974, 1957)Google Scholar
  21. 21.
    Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques, 2nd edn. Morgan Kaufmann (2005)Google Scholar
  22. 22.
    Blockeel, H., Struyf, J.: Efficient algorithms for decision tree cross-validation. Journal of Machine Learning Research 3, 621–650 (2002)zbMATHGoogle Scholar
  23. 23.
    Gold, C., Feurtet-Mazel, A., Coste, M., Boudou, A.: Field transfer of periphytic diatom communities to assess short term structural effects of metals (Cd, Zn) in rivers. Water Research 36, 3654–3664 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.Faculty of Electrical Engineering and Information TechnologiesSs. Cyril and Methodius UniversitySkopjeMacedonia
  2. 2.Faculty of Natural Sciences and Mathematics, Institute of BiologySs. Cyril and Methodius UniversitySkopjeMacedonia

Personalised recommendations