Nearest Neighbor Based Prototype Classification Preserving Class Regions
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
A prototype selection method chooses a small set of training points from a whole set of class data. As the datasize increases, the selected prototypes play a significant role in covering class regions and learning adiscriminate rule. This paper discusses the methods for selecting prototypes in a classification framework. Weformulate a prototype selection problem into a set covering optimization problem in which the sets arecomposed with distance metric and predefined classes. The formulation of our problem makes us drawattention only to prototypes per class, not considering the other class points. A training point becomes aprototype by checking the number of neighbors and whether it is preselected. In this setting, we propose agreedy algorithm which chooses the most relevant points for preserving the class dominant regions. Theproposed method is simple to implement, does not have parameters to adapt, and achieves better orcomparable results on both artificial and real-world problems.
Abstract
A prototype selection method chooses a small set of training points from a whole set of class data. As the datasize increases, the selected prototypes play a significant role in covering class regions and learning adiscriminate rule. This paper discusses the methods for selecting prototypes in a classification framework. Weformulate a prototype selection problem into a set covering optimization problem in which the sets arecomposed with distance metric and predefined classes. The formulation of our problem makes us drawattention only to prototypes per class, not considering the other class points. A training point becomes aprototype by checking the number of neighbors and whether it is preselected. In this setting, we propose agreedy algorithm which chooses the most relevant points for preserving the class dominant regions. Theproposed method is simple to implement, does not have parameters to adapt, and achieves better orcomparable results on both artificial and real-world problems.
참고문헌 (21)
- T. Hastie, "The Elements of Statistical Learning: Data Mining, Inference, and Prediction" (2001), Springer
- X. Wu, "The Top Ten Algorithms in Data Mining" (2009), CRC Press
- D. R. Wilson, "Reduction techniques for instance-based learning algorithms", Machine Learning, 38(3), pp.257~286 (2000)
- J. A. Olvera-Lopez, "A review of instance selection methods", Artificial Intelligence Review, 34(2), pp.133~143 (2010)
- S. Garcia, "Prototype selection for nearest neighbor classification : taxonomy and empirical study", IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(3), pp.417~435 (2012)
- J. Bien, "Prototype selection for interpretable classification", The Annals of Applied Statistics, 5(4), pp.2403~2424 (2011)
- H. A. Fayed, "Self-generating prototypes for pattern classification", Pattern Recognition, 40(5), pp.1498~1509 (2007)
- I. Triguero, "A taxonomy and experimental study on prototype generation for nearest neighbor classification", IEEE Transactions on Systems, Man, and Cybernetics Part C(Applications and Reviews), 42(1), pp.86~100 (2012)
- M. J. Hudak, "RCE classifiers : theory and practice", Cybernetics and Systems, 23(5), pp.483~515 (1992)
- Learning class regions by sphere covering, "J. Wang", Brown University, ~, pp.IBNS Technical Report 2006-02 (2006)
- I. Takigawa, "Convex sets as prototypes for classifying patterns", Engineering Applications of Artificial Intelligence, 22(1), pp.101~108 (2009)
- R. Younsi, "A randomized sphere cover classifier", Proceedings of the 11th International Conference on Intelligent Data Engineering and Automated Learning, pp.234~241 (2010)
- D. Marchette, "Class cover catch digraphs", Wiley Interdisciplinary Reviews : Computational Statistics, 2(2), pp.171~177 (2010)
- F. Angiulli, "Fast nearest neighbor condensation for large data sets classification", IEEE Transactions on Knowledge and Data Engineering, 19, pp.1450~1464 (2007)
- D. Hwang, "Near-boundary data selection for fast support vector machines", Malaysian Journal of Computer Science, 25(1), pp.23~37 (2013)
- M. Marchand, "The set covering machine", Journal of Machine Learning, 3, pp.723~746 (2003)
- A. H. Cannon, "Approximation algorithms for the class cover problem", Annals of Mathematics and Artificial Intelligence, 40(3-4), pp.215~223 (2004)
- V. V. Vazirani, "Approximation Algorithms" (2001), Springer
- "The GLU Linear Programming Kit Package"[URL]
- "UCI Machine Learning Repository"[URL]
- "KEEL-Dataset Repository"[URL]