A New Fuzzy Clustering Method Based on FN-DBSCAN to Determine the Optimal Input Parameters

  • Sihem JebariEmail author
  • Abir Smiti
  • Aymen Louati
Conference paper
Part of the Learning and Analytics in Intelligent Systems book series (LAIS, volume 7)


In recent years, data analysis has become important with increasing data volume.

Clustering which groups objects according to their similarity, has an important role in data analysis. FN-DBSCAN is one of the most effective fuzzy density-based clustering algorithms and has been successfully implemented in medical field.

However, it is a challenging task to determine its user-given input parameter values \(\epsilon 1\) and \(\epsilon 2\), which represent respectively the minimal threshold of neighborhood membership degrees and the minimal set cardinality. Both parameters have a significant influence on the clustering results.

In this paper, we propose AF-DBSCAN algorithm which includes a new method to avoid the manual intervention and so permits to determine the \(\epsilon 1\) and \(\epsilon 2\) values automatically. In such way, the whole clustering process can be fully automated.

Simulative experiments, carried out on real medical data sets, highlighted the AF-DBSCAN effectiveness even for high-dimension data sets, and showed that the proposed method outperformed the classical method since it can determine the two parameters more reasonably.


Density-based clustering DBSCAN Automatic fuzzy clustering FN-DBSCAN 


  1. 1.
    Smiti, A.: COID: clustering, outliers and internal detection approach for case base maintenance. Master’s thesis, Institut Supérieur de Gestion de Tunis (2010)Google Scholar
  2. 2.
    Esmaelnejad, J., Habibi, J., Yeganeh, S.H.: A novel method to find appropriate \(\epsilon \) for DBSCAN. In: Nguyen, N.T., Le, M.T., Swiatek, J. (eds.) ACIIDS 2010, pp. 93–102 (2010)Google Scholar
  3. 3.
    Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial data sets with noise. In: Proceeding 2nd International Conference on Knowledge Discovery and Data Mining, pp. 226–231 (1996)Google Scholar
  4. 4.
    Gaonkar, M.N., Sawant, K.: AutoEpsDBSCAN: DBSCAN with EPS automatic for large dataset. ISSN (Print) 2(2), 2319–2526 (2013)Google Scholar
  5. 5.
    Gorawski, M., Malczok, R.: AEC algorithm: a heuristic approach to calculating density-based clustering EPS parameter. In: Proceedings of the 4th international conference on Advances in Information Systems, ADVIS 2006, pp. 90–99 (2006)CrossRefGoogle Scholar
  6. 6.
    Han, Y., Shi, P.: An improved ant colony algorithm for fuzzy clustering in image segmentation. Neurocomputing 70, 665–671 (2007)CrossRefGoogle Scholar
  7. 7.
    Hancer, E., Ozturk, C., Karaboga, D.: Artificial bee colony based image clustering method. In: IEEE Congress on Evolutionary Computation (CEC), pp. 1–5 (2012)Google Scholar
  8. 8.
    Lin, L., Suhua, L.: Wheat cultivar classifications based on tabu search and fuzzy c-means clustering algorithm. In: 4th International Conference on Computational and Information Sciences (ICCIS), pp. 493–496 (2012)Google Scholar
  9. 9.
    Marinakis, Y., Marinaki, M., Matsatsinis, N.: A hybrid discrete artificial bee colony - grasp algorithm for clustering. In: International Conference on Computers Industrial Engineering (CIE), pp. 548–553 (2009)Google Scholar
  10. 10.
    Nasibov, E.N., Ulutagay, G.: Robustness of density-based clustering methods with various neighborhood relations. Fuzzy Sets Syst. 160(24), 3601–3615 (2009) MathSciNetCrossRefGoogle Scholar
  11. 11.
    Sharma, L., Ramya, K.: An efficient DBSCAN using genetic algorithm based clustering. Int. J. Sci. Eng. Res. 5, 1820–1826 (2014)Google Scholar
  12. 12.
    Smiti, A., Elouedi, Z.: DBSCAN-GM: an improved clustering method based on Gaussian means and DBSCAN techniques. In: 16th International Conference on Intelligent Engineering Systems (INES), pp. 573 – 578 (2012)Google Scholar
  13. 13.
    Tiwari, K.K., Jain, A.: An genetic based fuzzy approach for density based clustering by using k-means. Int. J. Sci. Res. Eng. Trends 2, 114–120 (2016)Google Scholar
  14. 14.
    Xu, H.B., Wang, H.J., Li, C.G.: Fuzzy tabu search method for the clustering problem. In: Proceedings International Conference on Machine Learning and Cybernetics, pp. 876–880 (2002)Google Scholar
  15. 15.
    Zhao, B., Zhu, Z., Mao, E., Song, Z.: Image segmentation based on ant colony optimization and k-means clustering. In: IEEE International Conference on Automation and Logistics, pp. 459–463 (2007)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Institut Superieur Informatique du KefEl KefTunisia
  2. 2.LARODEC, Institut Superieur de Gestion de TunistunisTunisia

Personalised recommendations