Efficient decision trees for multi-class support vector machines using entropy and generalization error estimation

• Autorzy: Kantavat P. , Kijsirikul B. , Songsiri P. , Fukui K. I. , Numao M.

Identyfikatory

DOI

10.2478/amcs-2018-0054

• Języki publikacji: EN

Abstrakty

EN

We propose new methods for support vector machines using a tree architecture for multi-class classification. In each node of the tree, we select an appropriate binary classifier, using entropy and generalization error estimation, then group the examples into positive and negative classes based on the selected classifier, and train a new classifier for use in the classification phase. The proposed methods can work in time complexity between O(log₂ N) and O(N), where N is the number of classes. We compare the performance of our methods with traditional techniques on the UCI machine learning repository using 10-fold cross-validation. The experimental results show that the methods are very useful for problems that need fast classification time or those with a large number of classes, since the proposed methods run much faster than the traditional techniques but still provide comparable accuracy.

Słowa kluczowe

EN

support vector machine; multi-class classification; generalization error; decision tree

PL

maszyna wektorów wsparcia; klasyfikacja wieloklasowa; błąd generalizacji; drzewo decyzyjne

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2018
• Tom: Vol. 28, no. 4
• Strony: 705--717
• Opis fizyczny: Bibliogr. 31 poz., rys., tab.

Twórcy

autor

Kantavat P.

• Department of Computer Engineering, Chulalongkorn University, Pathumwan, Bangkok 10330, Thailand

autor

Kijsirikul B.

• Department of Computer Engineering, Chulalongkorn University, Pathumwan, Bangkok 10330, Thailand

autor

Songsiri P.

• Department of Computer Engineering, Chulalongkorn University, Pathumwan, Bangkok 10330, Thailand

autor

Fukui K. I.

• Institute of Scientific and Industrial Research, Osaka University, Osaka 567-0047, Japan

autor

Numao M.

• Institute of Scientific and Industrial Research, Osaka University, Osaka 567-0047, Japan

Bibliografia

• [1] Bala, M. and Agrawal, R.K. (2011). Optimal decision tree based multi-class support vector machine, Informatica 35(2): 197–209.
• [2] Bartlett, P.L. and Shawe-Taylor, J. (1999). Generalization performance of support vector machines and other pattern classifiers, in B. Schölkopf et al. (Eds.), Advances in Kernel Methods, MIT Press, Cambridge, MA, pp. 43–54.
• [3] Blake, C.L. and Merz, C.J. (1998). UCI Repository of Machine Learning Databases, University of California, Irvine, CA, http://archive.ics.uci.edu/ml/.
• [4] Bredensteiner, E.J. and Bennett, K.P. (1999). Multicategory classification by support vector machines, Computational Optimization 12(1–3): 53–79.
• [5] Burges, C.J.C. (1998). A tutorial on support vector machines for pattern recognition, Data Mining and Knowledge Discovery 2(2): 121–167.
• [6] Chen, J., Wang, C. and Wang, R. (2009). Adaptive binary tree for fast SVM multiclass classification, Neurocomputing 72(13–15): 3370–3375.
• [7] Cheong, S., Hoon Oh, S. and Lee, S.-Y. (2004). Support vector machines with binary tree architecture for multi-class classification, Neural Information Processing Letters 2(3): 47–51.
• [8] Chmielnicki, W. and Stąpor, K. (2016). Using the one-versus-rest strategy with samples balancing to improve pairwise coupling classification, International Journal of Applied Mathematics and Computer Science 26(1): 191–201, DOI: 10.1515/amcs-2016-0013.
• [9] Crammer, K. and Singer, Y. (2002). On the learnability and design of output codes for multiclass problems, Machine Learning 47(2–3): 201–233.
• [10] Dong, C., Zhou, B. and Hu, J. (2015). A hierarchical SVMbased multiclass classification by using similarity clustering, International Joint Conference on Neural Networks, Killarney, Ireland, pp.1–6.
• [11] Fei, B. and Liu, J. (2006). Binary tree of SVM: A new fast multiclass training and classification algorithm, IEEE Transactions on Neural Networks 17(3): 696–704.
• [12] Friedman, J. (1996). Another approach to polychotomous classification, Technical report, Stanford University, Stanford, CA.
• [13] García, S., Fernández, A., Luengo, J. and Herrera, F. (2010). Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: Experimental analysis of power, Information Sciences 180(10): 2044–2064.
• [14] Hastie, T. and Tibshirani, R. (1998). Classification by pairwise coupling, Annals of Statistics 26(2): 451–471.
• [15] Hsu, C. and Lin, C. (2002). A comparison of methods for multiclass support vector machines, IEEE Transactions on Neural Networks 13(2): 415–425.
• [16] Joachims, T. (1999). Making large-scale SVM learning practical, in B. Schölkopf et al. (Eds.), Advances in Kernel Methods—Support Vector Learning, MIT Press, Cambridge, MA.
• [17] Kijsirikul, B., Ussivakulz, N. and Road, P. (2002). Multiclass support vector machines using adaptive directed acyclic graph, International Joint Conference on Neural Networks, Honolulu, HI, USA, pp. 980–985.
• [18] Knerr, S., Personnaz, L. and Dreyfus, G. (1990). Single-layer learning revisited: A stepwise procedure for building and training a neural network, Neurocomputing 68(68): 41–50.
• [19] Kumar, M.A. and Gopal, M. (2010). Fast multiclass SVM classification using decision tree based one-against-all method, Neural Processing Letters 32(3): 311–323.
• [20] Kumar, M.A. and Gopal, M. (2011). Reduced one-against-all method for multiclass svm classification, Expert Systems with Applications 38(11): 14238–14248.
• [21] Lei, H. and Govindaraju, V. (2005). Half-against-halfmulti-class support vector machines, in N.C. Oza et al. (Eds.), Multiple Classifier Systems, MCS 2005, Lecture Notes in Computer Science, Vol. 3541, Springer, Berlin/Heidelberg, pp. 156–164.
• [22] Liu, B., Cao, L., Yu, P.S. and Zhang, C. (2008). Multi-space-mapped SVMs for multi-class classification, Proceedings of 8th IEEE International Conference on Data Mining, Washington, DC, USA, Vol. 8, pp. 911–916.
• [23] Madzarov, G., Gjorgjevikj, D. and Chorbev, I. (2009). A multi-class SVM classifier utilizing binary decision tree support vector machines for pattern recognition, Electrical Engineering 33(1): 233–241.
• [24] Platt, J., Cristianini, N. and Shawe-Taylor, J. (2000). Large margin DAGs for multiclass classification, in S.A. Solla et al. (Eds.), Advances in Neural Information Processing Systems, MIT Press, Cambridge, MA, pp. 547–553.
• [25] Songsiri, P., Kijsirikul, B. and Phetkaew, T. (2008). Information-based dicrotomizer: A method for multiclass support vector machines, IEEE International Joint Conference on Neural Networks, Hong Kong, China, pp. 3284–3291.
• [26] Songsiri, P., Phetkaew, T. and Kijsirikul, B. (2015). Enhancement of multi-class support vector machine construction from binary learners using generalization performance, Neurocomputing 151(P1): 434–448.
• [27] Takahashi, F. and Abe, S. (2002). Decision-tree-based multiclass support vector machines, Proceedings of the 9th International Conference on Neural Information Processing, ICONIP’02, Singapore, Singapore, Vol. 3, pp. 1418–1488.
• [28] Vapnik, V.N. (1998). Statistical Learning Theory, John Wiley & Sons, New York, NY.
• [29] Vapnik, V.N. (1999). An overview of statistical learning theory, IEEE Transactions on Neural Networks 10(5): 988–99.
• [30] Vapnik V.N., C.A. (1974). Teoriya Raspoznavaniya Obrazov: Statisticheskie Problemy Obucheniya (Theory of Pattern Recognition: Statistical Problems of Learning), Nauka, Moscow.
• [31] Yang, X., Yu, Q., He, L. and Guo, T. (2013). The one-against-all partition based binary tree support vector machine algorithms for multi-class classification, Neurocomputing 113(3): 1–7.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2018).