Abstract
Prototype Selection (PS) is the preprocessing technique for K nearest neighbor classification that selects a subset of instances before classification takes place. The most accurate state-of-the-art PS method is Fuzzy Rough Prototype Selection (FRPS), which assesses the quality of the instances by means of the fuzzy rough positive region and automatically selects a good threshold to decide if instances should be retained in the prototype subset. In this paper we introduce a new PS method based on FRPS, called Multi Threshold FRPS (MT-FRPS) . Instead of determining one threshold against which the quality of every instance is compared, we consider one threshold for each class.
We evaluate MT-FRPS on 40 standard classification datasets and compare it against MT-FRPS and the state-of-the-art PS methods and show that MT-FRPS improves the accuracy of the state-of-the-art PS methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Transactions on Information Theory 13, 21–27 (1967)
GarcÃa, S., Derrac, J., Cano, J., Herrera, F.: Prototype selection for nearest neighbor classification: Taxonomy and empirical study. IEEE Transactions on Pattern Analysis and Machine Intelligence 34, 417–435 (2012)
Kuncheva, L.I., Jain, L.C.: Nearest neighbor classifier: Simultaneous editing and feature selection. Pattern Recognition Letters 20, 1149–1156 (1999)
Kuncheva, L.I.: Editing for the k-nearest neighbors rule by a genetic algorithm. Pattern Recognition Letters 16, 809–814 (1995)
GarcÃa, S., Cano, J.R., Herrera, F.: A memetic algorithm for evolutionary prototype selection: A scaling up approach. Pattern Recognition 41, 2693–2709 (2008)
Casillas, J., Cordón, O., del Jesus, M., Herrera, F.: Genetic feature selection in a fuzzy rule-based classification system learning process. Information Sciences 136, 135–157 (2001)
Verbiest, N., Cornelis, C., Herrera, F.: Frps: a fuzzy rough prototype selection method. Pattern Recognition 46, 2770–2782 (2013)
Verbiest, N., Cornelis, C., Herrera, F.: A prototype selection method based on ordered weighted average fuzzy rough set theory. In: Proceedings of the 14th International Conference on Rough Sets, Fuzzy Sets, Data Mining and Granular Computing, pp. 180–190 (2013)
Cornelis, C., De Cock, M., Radzikowska, A.M.: Fuzzy rough sets: from theory into practice. In: Pedrycz, W., Skowron, A., Kreinovich, V. (eds.) Handbook of Granular Computing, pp. 533–552 (2008)
Dubois, D., Prade, H.: Rough fuzzy sets and fuzzy rough sets. International Journal of General Systems 17, 191–209 (1990)
Dubois, D., Prade, H.: Putting fuzzy sets and rough sets together. In: Slowinskii, R. (ed.) Intelligent Decision Support- Handbook of Applications and Advances of the Rough Sets Theory, pp. 203–232 (1992)
Cornelis, C., Jensen, R., Hurtado Martın, G., Slezak, D.: Attribute selection with fuzzy decision reducts. Information Sciences 180, 209–224 (2010)
Yager, R.: On ordered weighted averaging aggregation operators in multicriteria decisionmaking. IEEE Transactions on Systems, Man and Cybernetics 18, 183–190 (1988)
Cornelis, C., Verbiest, N., Jensen, R.: Ordered weighted average based fuzzy rough sets. In: Yu, J., Greco, S., Lingras, P., Wang, G., Skowron, A. (eds.) RSKT 2010. LNCS, vol. 6401, pp. 78–85. Springer, Heidelberg (2010)
Bache, K., Lichman, M.: UCI machine learning repository (2013)
Alcalá, J., Fernandez, A., Luengo, J., Derrac, J., GarcÃa, S., Sánchez, L., Herrera, F.: Keel data-mining software tool: Data set repository, integration of algorithms and experimental analysis framework. Journal of Multiple-Valued Logic and Soft Computing 17, 255–287 (2011)
Ben-David, A.: Comparison of classification accuracy using cohen’s weighted kappa. Expert Systems with Applications 34, 825–832 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Verbiest, N. (2014). Multi Threshold FRPS: A New Approach to Fuzzy Rough Set Prototype Selection. In: Cornelis, C., Kryszkiewicz, M., Ślȩzak, D., Ruiz, E.M., Bello, R., Shang, L. (eds) Rough Sets and Current Trends in Computing. RSCTC 2014. Lecture Notes in Computer Science(), vol 8536. Springer, Cham. https://doi.org/10.1007/978-3-319-08644-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-319-08644-6_8
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-08643-9
Online ISBN: 978-3-319-08644-6
eBook Packages: Computer ScienceComputer Science (R0)