Abstract
This paper proposes two new improvements of the k-modes algorithm under possibilistic and rough frameworks. These new versions of the k-modes deal with uncertainty in the values of attributes and in the belonging of objects to several clusters and handle rough clusters using possibility and rough set theories. In fact, both of the k-modes under possibilistic framework (KM-PF) and the k-modes using possibility and rough set theories (KM-PR) provide successful results when clustering categorical values of attributes under uncertain frameworks. However, they use a random selection of the initial modes which can have a bad impact on the final results. As a good selection of the initial modes can make better the clustering results, our aim through this paper is to propose new methods that improve the KM-PF and KM-PR methods through the selection of initial modes. Besides, we will study and analyze the impact of the good selection of the initial modes on both KM-PF and KM-PR. The test of the new methods that select the initial modes from the most dissimilar objects shows the improvement made in terms of accuracy, iteration number, and execution time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ammar, A., Elouedi, Z., Lingras, P.: The k-modes method using possibility and rough set theories. In: Proceedings of the IFSA World Congress and NAFIPS Annual Meeting, IFSA/NAFIPS. IEEE (2013)
Ammar, A., Elouedi, Z., Lingras, P.: The K-modes method under possibilistic framework. In: Zaïane, O.R., Zilles, S. (eds.) AI 2013. LNCS (LNAI), vol. 7884, pp. 211–217. Springer, Heidelberg (2013). doi:10.1007/978-3-642-38457-8_18
Dubois, D., Prade, H.: Possibility Theory: An Approach to Computerized Processing of Uncertainty. Plenium Press, New York (1988)
Jenhani, I., Ben Amor, N., Elouedi, Z., Benferhat, S., Mellouli, K.: Information affinity: a new similarity measure for possibilistic uncertain information. In: Mellouli, K. (ed.) ECSQARU 2007. LNCS (LNAI), vol. 4724, pp. 840–852. Springer, Heidelberg (2007). doi:10.1007/978-3-540-75256-1_73
Joshi, M., Lingras, P., Rao, C.R.: Correlating fuzzy and rough clustering. Fundamenta Informaticae 115, 233–246 (2012)
Lingras, P., Nimse, S., Darkunde, N., Muley, A.: Soft clustering from crisp clustering using granulation for mobile call mining. In: Proceedings of the GrC 2011: International Conference on Granular Computing, pp. 410–416 (2011)
Murphy, M.P., Aha, D.W.: UCI repository databases (1996) http://www.ics.uci.edu/mlearn
Huang, Z.: Extensions to the k-means algorithm for clustering large data sets with categorical values. Data Mining Knowl. Discov. 2, 283–304 (1998)
Huang, Z., Ng, M.K.: A note on k-modes clustering. J. Classif. 20, 257–261 (2003)
Pawlak, Z.: Rough sets. Int. J. Inf. Comput. Sci. 11, 341–356 (1982)
Pawlak, Z.: Rough Sets: Theoretical Aspects of Reasoning About Data. Kluwer Academic Publishers, Berlin (1992)
Tanaka, H., Guo, P.: Possibilistic Data Analysis for Operations Research. Physica-Verlag, Heidelberg (1999)
Viattchenin, D.A.: A Heuristic Approach to Possibilistic Clustering: Algorithms and Applications. Springer Publishing Company, Incorporated, Heidelberg (2013)
Zadeh, L.A.: Fuzzy sets as a basis for a theory of possibility. Fuzzy Sets Syst. 1, 3–28 (1978)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Ammar, A., Elouedi, Z. (2017). Selection of Initial Modes for Rough Possibilistic K-Modes Methods. In: Kryszkiewicz, M., Appice, A., Ślęzak, D., Rybinski, H., Skowron, A., Raś, Z. (eds) Foundations of Intelligent Systems. ISMIS 2017. Lecture Notes in Computer Science(), vol 10352. Springer, Cham. https://doi.org/10.1007/978-3-319-60438-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-60438-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-60437-4
Online ISBN: 978-3-319-60438-1
eBook Packages: Computer ScienceComputer Science (R0)