Rough Mereology in Classification of Data: Voting by Means of Residual Rough Inclusions
In this work, we pursue the theme of applications of rough mereology, presenting a scheme for classifier construction by voting of training objects, exhaustive set of rules, and granules of training objects according to weights assigned by residual rough inclusions. The results show a high effectiveness of this approach as witnessed by the reported tests with some well–known data sets from UCI repository whose results are compared against the standard rough set exhaustive classifier.
Keywordsgranulation of knowledge rough inclusions residual implications granular decision systems
Unable to display preview. Download preview PDF.
- 3.Bazan, J.G.: A comparison of dynamic and non–dynamic rough set methods for extracting laws from decision tables. In: Polkowski, L., Skowron, A. (eds.) Rough Sets in Knowledge Discovery, vol. 1, pp. 321–365. Physica Verlag, Heidelberg (1998)Google Scholar
- 6.Polkowski, L.: The paradigm of granular rough computing. In: Zhang, D., Wang, Y., Kinsner, W. (eds.) ICCI 2007, pp. 145–163. IEEE Computer Society, Los Alamitos (2007)Google Scholar
- 7.Polkowski, L.: Formal granular calculi based on rough inclusions (a feature talk). In: Zhang, Y.-Q., Lin, T.Y. (eds.) IEEE GrC 2006, pp. 9–18. IEEE Press, Piscataway (2006)Google Scholar
- 8.Polkowski, L.: Formal granular calculi based on rough inclusions (a feature talk). In: Hu, X., Liu, Q., Skowron, A., Lin, T.Y., Yager, R.R., Zhang, B. (eds.) IEEE GrC 2005, pp. 57–62. IEEE Press, Piscataway (2005)Google Scholar
- 11.UCI Repository, http://www.ics.uci.edu/~mlearn/databases/