Special Issue on Ensemble Learning and Applications; Guest Editors: Sidhi Kulkarni and Brijesh VermaNo Access

ONLINE CLASS IMBALANCE LEARNING AND ITS APPLICATIONS IN FAULT DETECTION

SHUO WANG

CERCIA, School of Computer Science, University of Birmingham, Birmingham, B15 2TT, UK

Search for more papers by this author

LEANDRO L. MINKU

CERCIA, School of Computer Science, University of Birmingham, Birmingham, B15 2TT, UK

Search for more papers by this author

, and

XIN YAO

CERCIA, School of Computer Science, University of Birmingham, Birmingham, B15 2TT, UK

Search for more papers by this author

https://doi.org/10.1142/S1469026813400014Cited by:52 (Source: Crossref)

Abstract

Although class imbalance learning and online learning have been extensively studied in the literature separately, online class imbalance learning that considers the challenges of both fields has not drawn much attention. It deals with data streams having very skewed class distributions, such as fault diagnosis of real-time control monitoring systems and intrusion detection in computer networks. To fill in this research gap and contribute to a wide range of real-world applications, this paper first formulates online class imbalance learning problems. Based on the problem formulation, a new online learning algorithm, sampling-based online bagging (SOB), is proposed to tackle class imbalance adaptively. Then, we study how SOB and other state-of-the-art methods can benefit a class of fault detection data under various scenarios and analyze their performance in depth. Through extensive experiments, we find that SOB can balance the performance between classes very well across different data domains and produce stable G-mean when learning constantly imbalanced data streams, but it is sensitive to sudden changes in class imbalance, in which case SOB's predecessor undersampling-based online bagging (UOB) is more robust.

Keywords:

Remember to check out the Most Cited Articles!
Check out these titles in artificial intelligence!

References

N. C. Oza, Online bagging and boosting, IEEE Int. Conf. Systems, Man and Cybernetics (Hawaii, USA, 2005) pp. 2340–2345. Google Scholar
C. E. Monteleoni, Online learning of non-stationary sequences, in AI Technical Report 2003-011, 2003 . Google Scholar
M. Ciaramita, V. Murdock and V. Plachouras, Online learning from click data for sponsored search, Int. World Wide Web Conf. (Beijing, China, 2008) pp. 227–236. Google Scholar
H. Wanget al., Mining concept-drifting data streams using ensemble classifiers, Proc. Ninth ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (Washington, DC, USA, 2003) pp. 226–235. Google Scholar
K. Nishidaet al., Detecting sudden concept drift with knowledge of human behavior, IEEE Int. Conf. Systems, Man and Cybernetics (Singapore, 2008) pp. 3261–3267. Google Scholar
S. J. Delanyet al., Knowl.-Based Syst. 18(5), 187 (2005), DOI: 10.1016/j.knosys.2004.10.002. Crossref, Google Scholar
H. He and E. A. Garcia, IEEE Trans. Knowl. Data Eng. 21(9), 1263 (2009). Google Scholar
S. Wang, L. L. Minku and X. Yao, A learning framework for online class imbalance learning, IEEE Symp. Computational Intelligence and Ensemble Learning (CIEL) (Singapore, 2013) pp. 36–45. Google Scholar
S. Wang et al. , Concept drift detection for online class imbalance learning , Int. Joint Conf. Neural Networks (IJCNN '13) ( 2013 ) . Google Scholar
H. M. Nguyen, E. W. Cooper and K. Kamei, Online learning from imbalanced data streams, Int. Conf. Soft Computing and Pattern Recognition (SoCPaR) (Dalian, China, 2011) pp. 347–352. Google Scholar
S. Wang and X. Yao, IEEE Trans. Reliab. 62(2), 434 (2012), DOI: 10.1109/TR.2013.2259203. Crossref, Google Scholar
G. M. Weiss, SIGKDD Explor. Newsl. 6(1), 7 (2004), DOI: 10.1145/1007730.1007734. Crossref, Google Scholar
S. Wang, Ensemble Diversity for Class Imbalance Learning, PhD thesis, School of Computer Science, The University of Birmingham, 2011 . Google Scholar
N. V Chawlaet al., J. Artif. Intell. Res. 16, 341 (2002). Google Scholar
M. Lin, K. Tang and X. Yao, IEEE Trans. Neural Netw. Learn. Syst. 24(4), 647 (2013), DOI: 10.1109/TNNLS.2012.2228231. Google Scholar
N. Japkowicz, C. Myers and M. A. Gluck, A novelty detection approach to classification, Proc. 14th Int. Joint Conf. Artificial Intelligence (Montreal, Quebec, Canada, 1995) pp. 518–523. Google Scholar
Z.-H. Zhou and X.-Y. Liu, IEEE Trans. Knowl. Data Eng. 18(1), 63 (2006). Crossref, Google Scholar
L. Rokach, Artif. Intell. Rev. 33(2), 1 (2010), DOI: 10.1007/s10462-009-9124-7. Crossref, Google Scholar
N. V. Chawlaet al., SMOTEBoost: Improving prediction of the minority class in boosting, Knowledge Discovery in Databases: PKDD 20032838 (2003) pp. 107–119. Google Scholar
S. Wang, H. Chen and X. Yao, Negative correlation learning for classification ensembles, Int. Joint Conf. Neural Networks, WCCI (IEEE Press, Barcelona, Spain, 2010) pp. 2893–2900. Google Scholar
S. Wang and X. Yao, The effectiveness of a new negative correlation learning algorithm for classification ensembles, IEEE Int. Conf. Data Mining Workshops (Sydney, Australia, 2010) pp. 1013–1020. Google Scholar
U. Bhowanet al., IEEE Trans. Evol. Comput. 17(3), 368 (2013), DOI: 10.1109/TEVC.2012.2199119. Crossref, Google Scholar
M. Kubat and S. Matwin, Addressing the curse of imbalanced training sets: One-sided selection, Proc. 14th Int. Conf. Machine Learning (Nashville, TN, USA, 1997) pp. 179–186. Google Scholar
J. Gaoet al., A general framework for mining concept-drifting data streams with skewed distributions, Proc. SIAM ICDM (Omaha, NE, USA, 2007) pp. 3–14. Google Scholar
J. Gaoet al., IEEE Internet Comput. 12(6), 37 (2008), DOI: 10.1109/MIC.2008.119. Crossref, Google Scholar
Y. Wang, Y. Zhang and Y. Wang, Stud. Comput. Intell. 214, 65 (2009), DOI: 10.1007/978-3-540-92814-0_11. Crossref, Google Scholar
S. Chen and H. He, Sera: Selectively recursive approach towards nonstationary imbalanced stream data mining, Int. Joint Conf. Neural Networks (Atlanta, Georgia, USA, 2009) pp. 522–529. Google Scholar
S. Chenet al., Musera: Multiple selectively recursive approach towards imbalanced stream data mining, Int. Joint Conf. Neural Networks (Barcelona, Spain, 2010) pp. 1–8. Google Scholar
S. Chen and H. He, Evolving Syst. 2(1), 35 (2010), DOI: 10.1007/s12530-010-9021-y. Crossref, Google Scholar
R. N. Lichtenwalter and N. V. Chawla, New Frontiers in Applied Data Mining, Lecture Notes in Computer Science 5669 (Springer-Verlag, Berlin, 2010) pp. 53–75. Crossref, Google Scholar
G. Ditzler and R. Polikar, IEEE Trans. Knowl. Data Eng. 25(10), 2283 (2012), DOI: 10.1109/TKDE.2012.136. Crossref, Google Scholar
L. L. Minku and X. Yao, IEEE Trans. Knowl. Data Eng. 24(4), 619 (2012), DOI: 10.1109/TKDE.2011.58. Crossref, Google Scholar
A. Ghazikhani, R. Monsefi and H. S. Yazdi, Evolving Syst. 4(2), 119 (2013), DOI: 10.1007/s12530-013-9076-7. Crossref, Google Scholar
B. Mirza, Z. Lin and K.-Z. Toh, Neural Processing Letters 38(3), 465 (2013), DOI: 10.1007/s11063-013-9286-9. Crossref, Google Scholar
M. P. Michaelideset al., Contaminant event monitoring in intelligent buildings using a multi-zone formulation, 8th IFAC Symp. on Fault Detection, Supervision and Safety of Technical Processes (SAFEPROCESS)8 (Mexico City, Mexico, 2012) pp. 492–497. Google Scholar
V. Reppa, M. M. Polycarpou and C. G. Panayiotou, IEEE Trans. Neural Netw. Learn. Syst. (2013), DOI: 10.1109/TNNLS.2013.2250301. Google Scholar
C. Catal, Expert Syst. Appl. 38(4), 4626 (2010), DOI: 10.1016/j.eswa.2010.10.024. Crossref, Google Scholar
T. Menzies, B. Caglayan, Z. He, E. Kocaguneli, J. Krall, F. Peters and B. Turhan, The promise repository of empirical software engineering data, June 2012, http://promisedata.googlecode.com . Google Scholar
J. McBain and M. Timusk, Pattern Recognit. Lett. 32(7), 1054 (2011), DOI: 10.1016/j.patrec.2011.01.019. Crossref, Google Scholar
C. Elkan, The foundations of cost-sensitive learning, Proc. Seventeenth Int. Joint Conf. Artificial Intelligence (IJCAI'01) (Seattle, Washington, USA, 2001) pp. 973–978. Google Scholar
C. Seiffertet al., Improving learner performance with data sampling and boosting, 20th IEEE Int. Conf. Tools with Artificial Intelligence (Dayton, Ohio, USA, 2008) pp. 452–459. Google Scholar
L. Breiman, Mach. Learn. 24(2), 123 (1996). Google Scholar
The Prognostics and Health Management Society (PHM Society), 2009 PHM Challenge Competition Data Set, http://www.phmsociety.org/references/datasets . Google Scholar
STMicroelectronics, iNemo: iNErtial MOdule V2 demonstration board, http://www.st.com/internet/evalboard/product/250367.jsp . Google Scholar
T. J. McCabe, IEEE Trans. Softw. Eng. 2(4), 308 (1976). Google Scholar
M. H. Halstead , Elements of Software Science ( Elsevier , 1977 ) . Google Scholar
G. Hulten, L. Spencer and P. Domingos, Mining time-changing data streams, Proc. Seventh ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining (San Francisco, CA, USA, 2001) pp. 97–106. Google Scholar
L. L. Minku, A. P. White and X. Yao, IEEE Trans. Knowl. Data Eng. 22(5), 730 (2010), DOI: 10.1109/TKDE.2009.156. Crossref, Google Scholar
H. Fuet al., Finding robust solutions to dynamic optimization problems, Proc. 16th European Conf. Applications of Evolutionary Computation7835, Lecture Notes in Computer Science (Springer, Berlin, 2013) pp. 616–625. Google Scholar