Abstract
Support vector data description (SVDD) is a very attractive kernel method in many novelty detection problems. However, the decision function of SVDD is expressed in terms of the kernel expansion, which results in a run-time complexity linear in the number of support vectors (SVs). In this paper, an efficient SVDD (E-SVDD) is proposed to improve the prediction speed of SVDD. This proposed E-SVDD first finds some crucial feature vectors by the partitioning-entropy-based kernel fuzzy c-means (KFCM) cluster technique and then uses the images of the preimages of these feature vectors to reexpress the center of SVDD. Hence, the decision function of E-SVDD only contains some crucial kernel terms, and the complexity of E-SVDD is linear in the number of the clusters. The experimental results on several benchmark datasets indicate that E-SVDD not only obtains fast prediction speed but also shows better stable generalization than other methods.
Similar content being viewed by others
Notes
Available at: http://www.mathworks.co.
References
Markou M, Singh S (2003) Novelty detection: a review, part I: statistical approaches. Signal Process 83(12):2481–2497
Markou M, Singh S (2003) Novelty detection: a review, part II: neural network based approaches. Signal Process 83(12):2499–2521
Lee K, Kim D, Lee K, Lee D (2007) Density-induced support vector data desciption. IEEE Trans Neural Netw 18(1):284–289
Vapnik V (1995) The natural of statistical learning theory. Springer, New York
Vapnik V (1998) Statistical learning theory. Wiley, New York
Campbell C, Bennett K (2001) A linear programming approach to novelty detection. In: Advances in neural information processing systems, vol 13. MIT Press, Cambridge, MA
Tax D, Duin R (1999) Support vector domain description. Pattern Recogn Lett 20:1191–1199
Tax D, Duin R (2004) Support vector data description. Mach Learn 54:45–66
Roberts S, Tarassenko L (1994) A probabilistic resource allocation network for novelty detection. Neural Comput Appl 6:270–284
Crammer K, Chechik G (2004) A needle in a haystack: local one-class optimization. In: Proceedings of 21th international conference on machine learning, p 26
Hoffmann H (2007) Kernel PCA for novelty detection. Pattern Recogn Lett 40(3):863–874
Lanckriet G, Ghaoui L, Jordan M (2003) Robust novelty detection with single-class MPM. In: Advances in neural information processing systems, vol 15. MIT Press, Cambridge, MA, pp 92–936
Schölkopf B, Mika S, Burges C, Knirsch P, Müller K, Rätsch G, Smola A (1999) Input space vs. feature space in kernel-based methods. IEEE Trans Neural Netw 10(5):1000–1017
Schölkopf B, Smola A (2002) Learning with kernels. MIT Press, Cambridge
Scott C, Nowak R (2006) Learning minimum volume sets. J Mach Learn Res 7:665–704
Steinwart I, Hush D, Scovel C (2005) A classification framework for anomaly detection. J Mach Learn Res 6:211–232
Vert R, Vert J (2006) Consistency and convergence rates of one-class SVM and related algorithms. J Mach Learn Res 7:817–854
Liu Y, Lin S, Hsueh Y, M.L. L (2009) Automatic target defect identification for TFT-LCD array process inspection using kernel FCM-based fuzzy SVDD ensemble. Expert Syst Appl 36(2):1978–1998
Park J, Kang D, Kim J, Kwok J, Tsang I (2007) Svdd-baded pattern denoising. Neural Comput Appl 19(7):1919–1938
Nanni L (2006) Machine learning algorithms for T-cell epitopes prediction. Neurocomputing 69(7–9):866–868
Banerjee A, Burlina P, Diehl C (2006) A support vector method for anomaly detection in hyperspectral imagery. IEEE Trans Geosci Remote Sens 44(8):2282–2291
Burges C (1996) Simplified support vector decision rules. In: Proceedings of the 13th international conference on machine learning, pp 71–77
Thies T, Weber F (2004) Optimal reduced-set vectors for support vector machines with a quadratic kernel. Neural Comput Appl 16:1769–1777
Downs T, Gates K, Masters A (2002) Exact simplification of support vector solutions. J Mach Learn Res 2:293–297
Guo J, Takahashi N, Nishi T (2005) A learning algorithm for improving the classification speed of support vector machines. In: Proceedings of 2005 European conference on circuit theory and design
Jiao L, Bo L, Wang L (2007) Fast sparse approximation for least squares support vector machine. IEEE Trans Neural Netw 18:685–697
Suykens J, Lukas L, van Dooren P, De Moor B, Vandewalle J (1999) Least squares support vector machine classifiers: a large scale algorithm. In: Proceedings of European conference of circuit theory design, pp 839–842
Suykens J, Vandewalle J (1999) Least squares support vector machine classifiers. Neural Process Lett 9(3):293–300
Bo L, Wang L, Jiao L (2007) Selecting a reduced set for building sparse support vector regression in the primal. In: Advances in knowledge discovery and data mining, pp 35–46
Liang X, Chen R, Guo X (2008) Pruning support vector machines without altering performances. IEEE Trans Neural Netw 19(10):1792–1803
Li Q, Jiao L, Hao Y (2007) Adaptive simplification of solution for support vector machine. Pattern Recogn Lett 40:972–980
Joachims T, Yu C (2009) Sparse kernel SVMs via cutting-plane training. Mach Learn 76(2-3):179–193
Liu Y, Liu Y, Chen Y (2010) Fast support vector data description for novelty detection. IEEE Trans Neural Netw 21(8):1296–1313
Mercer J (1909) Functions of positive and negative type and the connection with the theory of integal equations. Philos Trans R Soc Lond Ser A 209:415–446
Bakir G, Weston J, Schölkopf B (2004) Learning to find pre-images. In: Thrun J, Saul L, Schölkopf B (eds) Advances in neural information processing systems. vol 16, MIT Press, Cambridge, MA, pp 449–456
Burges C, Schölkopf B (1997) Improving the accuracy and speed of support vector learning machines. In: Mozer M, Jordan M, Petsche T (eds) Advances in neural information processing systems. vol 9, MIT Press, Cambridge, MA, pp 375–381
Kwok J, Tsang I (2004) The pre-image problem in kernel methods. IEEE Trans Neural Netw 15(6):1517–1525
Mika S, Schölkopf B, Smola A, Müller K, Scholz M, Rätsch G (1998) Kernel pca and de-noising in feature space. In: Kearns M, Solla S, Cohn D (eds) Advances in neural information processing systems, vol 11. Morgan Kaufmann, San Mateo, CA
Bezdek J (1981) Pattern recognition with fuzzy objective function algorithms. Plenum Press, New York
Wu Z, Xie W (2003) Fuzzy c-means clustering algorithm based on kernel method. In: Proceedings of fifth international conference on computational intelligence and multimedia applications, pp 49–54
Lin C, Lee C (1996) Neural fuzzy systems: a neuro-fuzzy synergism to intelligent system. Prentice-Hall, Englewood Cliffs, NJ
Höppner F, Klawonn F, Kruse R, Runkler T (1999) Fuzzy cluster analysis: methods for classification, data analysis and image recognition. Wiley, New York
Huang H, Liu Y (2002) Fuzzy support vector machines for pattern recognition and data mining. Int J Fuzzy Syst 4:826–835
Meyer C (2000) Matrix analysis and applied linear algebra. SIAM, Philadelphia
Kubat M, Matwin S (1997) Addressing the curse of imbalanced training sets: one-sided selection. In: Proceedings of 14th international conference on machine learning
Wu G, Chang E (2003) Class-boundary alignment for imbalanced dataset learning. In: Proceedings of international conference on machine learning workshop learning from imbalanced datasets
Acknowledgments
Supported by the Innovative Project of Shanghai Municipal Education Commission (11YZ81), the Natural Science Foundation of SHNU (SK200937, SK201030), and the Shanghai Leading Academic Discipline Project (S30405).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Peng, X., Xu, D. Efficient support vector data descriptions for novelty detection. Neural Comput & Applic 21, 2023–2032 (2012). https://doi.org/10.1007/s00521-011-0625-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0625-3