CSDL Home IEEE Transactions on Pattern Analysis & Machine Intelligence 2010 vol.32 Issue No.12 - December

Subscribe

Issue No.12 - December (2010 vol.32)

pp: 2113-2127

Shen-Shyang Ho , Univesity of Maryland Institute for Advanced Computer Studies, College Park

Harry Wechsler , George Mason University, Fairfax

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2010.48

ABSTRACT

In a data streaming setting, data points are observed sequentially. The data generating model may change as the data are streaming. In this paper, we propose detecting this change in data streams by testing the exchangeability property of the observed data. Our martingale approach is an efficient, nonparametric, one-pass algorithm that is effective on the classification, cluster, and regression data generating models. Experimental results show the feasibility and effectiveness of the martingale methodology in detecting changes in the data generating model for time-varying data streams. Moreover, we also show that: 1) An adaptive support vector machine (SVM) utilizing the martingale methodology compares favorably against an adaptive SVM utilizing a sliding window, and 2) a multiple martingale video-shot change detector compares favorably against standard shot-change detection algorithms.

INDEX TERMS

Change detection, data stream, exchangeability, hypothesis testing, martingale, classification, regression, clustering, support vector machine.

CITATION

Shen-Shyang Ho, Harry Wechsler, "A Martingale Framework for Detecting Changes in Data Streams by Testing Exchangeability",

*IEEE Transactions on Pattern Analysis & Machine Intelligence*, vol.32, no. 12, pp. 2113-2127, December 2010, doi:10.1109/TPAMI.2010.48REFERENCES

- [1] S.-S. Ho, "A Martingale Framework for Concept Change Detection in Time-Varying Data Streams,"
Proc. 22nd Int'l Conf. Machine Learning, L.D. Raedt and S. Wrobel, eds., pp. 321-327, 2005.- [2] S.-S. Ho and H. Wechsler, "Detecting Changes in Unlabeled Data Streams Using Martingale,"
Proc. 20th Int'l Joint Conf. Artificial Intelligence, M. Veloso, ed., pp. 1912-1917, 2007.- [3] V.N. Vapnik,
The Nature of Statistical Learning Theory, second ed. Springer-Verlag, 2000.- [4] W.A. Shewhart, "The Application of Statistics as an Aid in Maintaining Quality of a Manufactured Products,"
J. Am. Statistician Assoc., vol. 20, pp. 546-548, 1925.- [5] W.A. Shewhart,
Economic Control of Quality of Manufactured Product. Am. Soc. for Quality Control, 1931.- [6] A. Wald,
Sequential Analysis. Wiley, 1947.- [7] E.S. Page, "On Problem in Which a Change in a Parameter Occurs at an Unknown Point,"
Biometrika, vol. 44, pp. 248-252, 1957.- [8] M.A. Girshik and H. Rubin, "A Bayes Approach to a Quality Control Model,"
Annal of Math. Statistics, vol. 23, no. 1, pp. 114-125, 1952.- [9] A.N. Shiryaev, "On Optimum Methods in Quickest Detection Problems,"
Theory of Probability and Applications, vol. 8, pp. 22-46, 1963.- [10] M. Basseville and I.V. Nikiforov,
Detection of Abrupt Changes: Theory and Application. Prentice Hall, 1993.- [11] F. Chu and C. Zaniolo, "Fast and Light Boosting for Adaptive Mining of Data Streams,"
Proc. Pacific-Asia Conf. Knowledge Discovery and Data Mining, H. Dai, R. Srikant, and C. Zhang, eds., pp. 282-292, 2004.- [12] R. Klinkenberg and T. Joachims, "Detecting Concept Drift with Support Vector Machines,"
Proc. 17th Int'l Conf. Machine Learning, P. Langley, ed., pp. 487-494, 2000.- [13] G. Widmer and M. Kubat, "Learning in the Presence of Concept Drift and Hidden Contexts,"
Machine Learning, vol. 23, no. 1, pp. 69-101, 1996.- [14] R. Klinkenberg, "Learning Drifting Concepts: Examples Selection vs Example Weighting,"
Intelligent Data Analysis, special issue on incremental learning systems capable of dealing with concept drift, vol. 8, no. 3, pp. 281-300, 2004.- [15] F. Chu, Y. Wang, and C. Zaniolo, "An Adaptive Learning Approach for Noisy Data Streams,"
Proc. Fourth IEEE Int'l Conf. Data Mining, pp. 351-354, 2004.- [16] J.Z. Kolter and M.A. Maloof, "Dynamic Weighted Majority: A New Ensemble Method for Tracking Concept Drift,"
Proc. Third IEEE Int'l Conf. Data Mining, pp. 123-130, 2003.- [17] H. Wang, W. Fan, P.S. Yu, and J. Han, "Mining Concept-Drifting Data Streams Using Ensemble Classifiers,"
Proc. ACM SIGKDD, L. Getoor, T.E. Senator, P. Domingos, and C. Faloutsos, eds., pp. 226-235, 2003.- [18] M. Scholz and R. Klinkenberg, "Boosting Classifiers for Drifting Concepts,"
Intelligent Data Analysis, vol. 11, no. 1, pp. 3-28, 2007.- [19] O. Bousquet and M. Warmuth, "Tracking a Small Set of Experts by Mixing Past Posteriors,"
J. Machine Learning Research, vol. 3, pp. 363-396, 2002.- [20] C.C. Aggarwal, "A Framework for Change Diagnosis of Data Streams,"
Proc. ACM SIGMOD, pp. 575-586, 2003.- [21] S. Hido, T. Ide, H. Kashima, H. Kubo, and H. Matsuzawa, "Unsupervised Change Analysis Using Supervised Learning,"
Proc. Pacific Asia Conf. Advances in Knowledge Discovery and Data Mining, pp. 148-159, 2008.- [22] D. Kifer, S. Ben-David, and J. Gehrke, "Detecting Change in Data Streams,"
Proc. 13th Int'l Conf. Very Large Data Bases, M.A. Nascimento, M.T. Özsu, D. Kossmann, R.J. Miller, J.A. Blakeley, and K.B. Schiefer, eds., pp. 180-191, 2004.- [23] B. Krishnamurthy, S. Sen, Y. Zhang, and Y. Chen, "Sketch-Based Change Detection: Methods, Evaluation, and Applications,"
Proc. Internet Measurement Conf., pp. 234-247, 2003.- [24] T. Idé and K. Inoue, "Knowledge Discovery from Heterogeneous Dynamic Systems Using Change-Point Correlations,"
Proc. SIAM Conf. Data Mining, pp. 571-576, 2005.- [25] B. Liu, W. Hsu, H.-S. Han, and Y. Xia, "Mining Changes for Real-Life Applications,"
Proc. Int'l Conf. Data Warehousing and Knowledge Discovery, Y. Kambayashi, M.K. Mohania, and A.M. Tjoa, eds., pp. 337-346, 2000.- [26] Y. Zhai and M. Shah, "A General Framework for Temporal Video Scene Segmentation,"
Proc. 10th Int'l Conf. Computer Vision, pp. 1111-1116, 2005.- [27] V. Vovk, I. Nouretdinov, and A. Gammerman, "Testing Exchangeability On-Line,"
Proc. 20th Int'l Conf. Machine Learning, T. Fawcett and N. Mishra, eds., pp. 768-775, 2003.- [28] K. Proedrou, I. Nouretdinov, V. Vovk, and A. Gammerman, "Transductive Confidence Machines for Pattern Recognition,"
Proc. 13th European Conf. Machine Learning, T. Elomaa, H. Mannila, and H. Toivonen, eds., pp. 381-390, 2002.- [29] C. Saunders, A. Gammerman, and V. Vovk, "Transduction with Confidence and Credibility,"
Proc. 16th Int'l Joint Conf. Artificial Intelligence, T. Dean, ed., pp. 722-726, 1999.- [30] H. Papadopoulos, K. Proedrou, V. Vovk, and A. Gammerman, "Inductive Confidence Machines for Regression,"
Proc. 13th European Conf. Machine Learning, pp. 345-356, 2002.- [31] S.-S. Ho and H. Wechsler, "Query by Transduction,"
IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 30, no. 9, pp. 1557-1571, Sept. 2008.- [32] V. Vovk, A. Gammerman, and G. Shafer,
Algorithmic Learning in a Random World. Springer, 2005.- [33] M. Steele,
Stochastic Calculus and Financial Applications. Springer-Verlag, 2001.- [34] E.L. Lehmann,
Testing Statistical Hypotheses, second ed. Springer-Verlag, 1997.- [35] G.B. Wetherill and K.D. Glazebrook,
Sequential Methods in Statistics, third ed. Chapman and Hall, 1986.- [36] G. Cauwenberghs and T. Poggio, "Incremental Support Vector Machine Learning,"
Advances in Neural Information Processing Systems, pp. 409-415, MIT Press, 2000.- [37] R. Collobert and S. Bengio, "Links between Perceptrons, MLPs, and SVMs,"
Proc. 21st Int'l Conf. Machine Learning, 2004.- [38] S. Muthukrishnan, E. van den Berg, and Y. Wu, "Sequential Change Detection on Data Streams,"
Proc. ICDM Workshop Data Stream Mining and Management, pp. 551-556, 2007.- [39] U. Gargi, R. Kasturi, and S.H. Strayer, "Performance Characterization of Video-Shot-Change Detection Methods,"
IEEE Trans. Circuits and Systems for Video Technology, vol. 10, no. 1, pp. 1-13, Feb. 2000.- [40] G. Hulten, L. Spencer, and P. Domingos, "Mining Time-Changing Data Streams,"
Proc. ACM SIGKDD, pp. 97-106, 2001.- [41] H. Drucker, C.J.C. Burges, L. Kaufman, C.J.C. Burges, L. Kaufman, A. Smola, and V. Vapnik, "Support Vector Regression Machines,"
Advances in Neural Information Processing Systems, MIT Press, 1996.- [42] D.R. Musicant, "Normally Distributed Clustered Datasets," Computer Sciences Dept., Univ. of Wisconsin, http://www.cs.wisc.edu/dmi/svmndc/, 1998.
- [43] L. Breiman, "Bias, Variance, and Arcing Classifiers," Technical Report 460, Statistics Dept., Univ. of California, http://citeseer. ist.psu.edubreiman96bias.html , 1996.
- [44] C. Blake and C. Merz, "UCI Repository of Machine Learning Databases," http://www.ics.uci.edu/~mlearnMLRepository. html , 1998.
- [45] Y. LeCun, B. Boser, J.S. Denker, D. Henderson, R.E. Howard, W. Hubbard, and L.J. Jackel, "Backpropagation Applied to Handwritten Zip Code Recognition,"
Neural Computation, vol. 1, pp. 541-551, 1989. |