Adaptive One-Class Support Vector Machine for Damage Detection in Structural Health Monitoring

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10234)


Machine learning algorithms have been employed extensively in the area of structural health monitoring to compare new measurements with baselines to detect any structural change. One-class support vector machine (OCSVM) with Gaussian kernel function is a promising machine learning method which can learn only from one class data and then classify any new query samples. However, generalization performance of OCSVM is profoundly influenced by its Gaussian model parameter \(\sigma \). This paper proposes a new algorithm named Appropriate Distance to the Enclosing Surface (ADES) for tuning the Gaussian model parameter. The semantic idea of this algorithm is based on inspecting the spatial locations of the edge and interior samples, and their distances to the enclosing surface of OCSVM. The algorithm selects the optimal value of \(\sigma \) which generates a hyperplane that is maximally distant from the interior samples but close to the edge samples. The sets of interior and edge samples are identified using a hard margin linear support vector machine. The algorithm was successfully validated using sensing data collected from the Sydney Harbour Bridge, in addition to five public datasets. The designed ADES algorithm is an appropriate choice to identify the optimal value of \(\sigma \) for OCSVM especially in high dimensional datasets.


Machine learning Structural health monitoring One-class support vector machine Gaussian parameter selection Anomaly detection 


  1. 1.
    Bánhalmi, A., Kocsor, A., Busa-Fekete, R.: Counter-example generation-based one-class classification. In: Kok, J.N., Koronacki, J., Mantaras, R.L., Matwin, S., Mladenič, D., Skowron, A. (eds.) ECML 2007. LNCS (LNAI), vol. 4701, pp. 543–550. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-74958-5_51 CrossRefGoogle Scholar
  2. 2.
    Cortes, C., Vapnik, V.: Support vector machine. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  3. 3.
    Das, S., Srivastava, A.N., Chattopadhyay, A.: Classification of damage signatures in composite plates using one-class SVMs. In: Aerospace Conference, pp. 1–19. IEEE (2007)Google Scholar
  4. 4.
    Evangelista, P.F., Embrechts, M.J., Szymanski, B.K.: Some properties of the gaussian kernel for one class learning. In: Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds.) ICANN 2007. LNCS, vol. 4668, pp. 269–278. Springer, Heidelberg (2007). doi: 10.1007/978-3-540-74690-4_28 CrossRefGoogle Scholar
  5. 5.
    Farrar, C.R., Worden, K.: An introduction to structural health monitoring. Philos. Trans. R. Soc. Lond. A: Math. Phys. Eng. Sci. 365(1851), 303–315 (2007)CrossRefGoogle Scholar
  6. 6.
    Farrar, C.R., Worden, K.: Structural Health Monitoring: A Machine Learning Perspective. Wiley, Hoboken (2012)CrossRefGoogle Scholar
  7. 7.
    Khazai, S., Homayouni, S., Safari, A., Mojaradi, B.: Anomaly detection in hyperspectral images based on an adaptive support vector method. IEEE Geosci. Remote Sens. Lett. 8(4), 646–650 (2011)CrossRefGoogle Scholar
  8. 8.
    Khoa, N.L.D., Zhang, B., Wang, Y., Chen, F., Mustapha, S.: Robust dimensionality reduction and damage detection approaches in structural health monitoring. Struct. Health Monit. 13, 406–417 (2014)CrossRefGoogle Scholar
  9. 9.
    Khoa, N.L.D., Zhang, B., Wang, Y., Liu, W., Chen, F., Mustapha, S., Runcie, P.: On damage identification in civil structures using tensor analysis. In: Cao, T., Lim, E.-P., Zhou, Z.-H., Ho, T.-B., Cheung, D., Motoda, H. (eds.) PAKDD 2015. LNCS (LNAI), vol. 9077, pp. 459–471. Springer, Cham (2015). doi: 10.1007/978-3-319-18038-0_36 Google Scholar
  10. 10.
    Li, Y., Maguire, L.: Selecting critical patterns based on local geometrical and statistical information. IEEE Trans. Pattern Anal. Mach. Intell. 33(6), 1189–1201 (2011)CrossRefGoogle Scholar
  11. 11.
    Long, J., Buyukozturk, O.: Automated structural damage detection using one-class machine learning. In: Catbas, F.N. (ed.) Dynamics of Civil Structures, Volume 4. CPSEMS, pp. 117–128. Springer, Cham (2014). doi: 10.1007/978-3-319-04546-7_14 CrossRefGoogle Scholar
  12. 12.
    Alamdari, M.M., Samali, B., Li, J., Kalhori, H., Mustapha, S.: Spectral-based damage identification in structures under ambient vibration. J. Comput. Civ. Eng. 30, 04015062 (2015)CrossRefGoogle Scholar
  13. 13.
    Mustapha, S., Hu, Y., Nguyen, K., Alamdari, M.M., Runcie, P., Dackermann, U., Nguyen, V.V., Li, J., Ye, L.: Pattern recognition based on time series analysis using vibration data for structural health monitoring in civil structures (2015)Google Scholar
  14. 14.
    Runcie, P., Mustapha, S., Rakotoarivelo, T.: Advances in structural health monitoring system architecture. In: Proceedings of the the fourth International Symposium on Life-Cycle Civil Engineering, IALCCE, vol. 14 (2014)Google Scholar
  15. 15.
    Schölkopf, B., Platt, J.C., Shawe-Taylor, J., Smola, A.J., Williamson, R.C.: Estimating the support of a high-dimensional distribution. Neural Comput. 13(7), 1443–1471 (2001)CrossRefzbMATHGoogle Scholar
  16. 16.
    Tax, D.M.J., Duin, R.P.W.: Support vector data description. Mach. Learn. 54(1), 45–66 (2004)CrossRefzbMATHGoogle Scholar
  17. 17.
    Worden, K., Manson, G.: The application of machine learning to structural health monitoring. Philos. Trans. R. Soc. Lond. A: Math. Phys. Eng. Sci. 365(1851), 515–537 (2007)CrossRefGoogle Scholar
  18. 18.
    Xiao, Y., Wang, H., Wenli, X.: Parameter selection of gaussian kernel for one-class SVM. IEEE Trans. Cybern. 45(5), 941–953 (2015)CrossRefGoogle Scholar
  19. 19.
    Zeng, M., Yang, Y., Cheng, J.: A generalized Gilbert algorithm and an improved MIES for one-class support vector machine. Knowl.-Based Syst. 90, 211–223 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.Data61|CSIROEveleighAustralia
  2. 2.Department of Mechanical EngineeringAmerican University of Beirut BeirutLebanon
  3. 3.Faculty of Engineering and ITUniversity of Technology SydneySydneyAustralia

Personalised recommendations