Abstract
In our work we used the capability of one-class support vector machine (SVM) method to develop a novel one-class classification approach. Algorithm is designed and tested, aimed for fault detection in complex technological systems, such as aircraft. The main objective of this project was to create an algorithm responsible for collecting and analyzing the data since the launch of an aircraft engine. Data can be transferred from a variety of sensors that are responsible for the speed, oil temperature and etc. In order to provide high generalization level and sufficient learning data sets an incremental algorithm is considered. The proposed method analyzes both “positive”/“normal” and “negative”/ “abnormal” examples. However, overall model structure is based on one-class classification paradigm. Modified SVM-base outlier detection method is verified in comparison with several classifiers, including the traditional one-class SVM. This algorithm has been tested on real flight data from the Western European and Russia. The test results are presented in the final part of the article.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Vapnik, V., Golowich, S.E., Smola, A.J.: Support Vector Method for Function Approximation, Regression Estimation and Signal Processing. In: Paper presented at the meeting of the Advances in Neural Information Processing Systems 9 — Proceedings of the 1996 Neural Information Processing Systems Conference (NIPS 1996), Dever, CO, USA (1997)
TU-204-100 Aircraft Operations Manual / Tupolev ANTK (1998)
Angelov, P.: Anomalous System State Identification, GB1208542.9 (priority date May 15, 2012)
Koppel, M., Schler, J.: Authorship verification as a one-class classification problem. In: Proceedings of the Twenty-First International Conference on Machine Learning (ICML 2004), p. 62. ACM, New York (2004)
Gretton, A., Desobry, F.: On-Line One-Class Support Vector Machines. An Application to Signal Segmentation. In: IEEE ICASSP, vol. 2, pp. 709–712 (2003)
Gâlmeanu, H., Andonie, R.: Implementation Issues of an Incremental and Decremental SVM. In: Kůrková, V., Neruda, R., Koutník, J. (eds.) ICANN 2008, Part I. LNCS, vol. 5163, pp. 325–335. Springer, Heidelberg (2008)
Das, S., Oza, N.C.: Sparse Solutions for Single Class SVMs: A Bi-Criterion Approach. In: Proc. SDM, pp. 816–827. SIAM, Omnipress (2011)
Jensen, S.: An Introduction to Lagrange Multipliers, http://www.slimy.com/~steuard/teaching/tutorials/Lagrange.html
Gershwin, S.B.: KKT - Examples. MIT OpenCourseWare (2010)
Tax, D.M.J., Laskov, P.: Online SVM learning: from classification to data description and back. Journal of Machine Learning Research 7, 1909–1936 (2006)
Hill, S.I., Doucet, A.: Adapting Two-Class Support Vector Classification Methods to Many Class Problems. In: Proc. ICML 2005 Proc. 22nd Intern. Conf. on Machine Learning, pp. 313–320 (2005)
Scholkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high dimensional distribution. Neural Computation 13(7), 1443–1471 (2001)
Angelov, P.: Autonomous Learning Systems: From Data Streams to Knowledge in Real time. Willey (December 2012) ISBN: 978-1-1199-5152-0
Bishop, C.: Machine Learning and Pattern Classification, 2nd edn. Springer (2009)
Stibor, T., Timmis, J.I., Eckert, C.: A Comparative study of real-valued negative selection to statistical anomaly detection techniques. In: Jacob, C., Pilat, M.L., Bentley, P.J., Timmis, J.I. (eds.) ICARIS 2005. LNCS, vol. 3627, pp. 262–275. Springer, Heidelberg (2005)
TU-204-100 Aircraft Operations Manual / Tupolev ANTK (1998)
Analysis Ground Station (AGS), Sagem/SAFRAN, France, http://www.sagem-ds.com/spip.php?rubrique230 (accessed November 8, 2012)
Kolev, D., Zvikhachevskiy, D., Suvorov, M., Angelov, P.: Safety (and maintenance) improvement Through automated flight data analysis March 19, 2012, Scale Focused Research Project for project SVETLANA, Grant Agreement: ACPO-GA-2010-265940 (2012)
Angelov, P., Zhou, X.: Evolving Fuzzy-Rule-based Classifiers from Data Streams. IEEE Trans. on Fuzzy Systems 16(6), 1462–1475 (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Kolev, D., Suvorov, M., Morozov, E., Markarian, G., Angelov, P. (2015). Incremental Anomaly Identification in Flight Data Analysis by Adapted One-Class SVM Method. In: Koprinkova-Hristova, P., Mladenov, V., Kasabov, N. (eds) Artificial Neural Networks. Springer Series in Bio-/Neuroinformatics, vol 4. Springer, Cham. https://doi.org/10.1007/978-3-319-09903-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-09903-3_18
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09902-6
Online ISBN: 978-3-319-09903-3
eBook Packages: EngineeringEngineering (R0)