Skip to main content
SpringerLink
Log in

Multiclass SVM active learning algorithm based on decision directed acyclic graph and one versus one

  • Published:
Cluster Computing Aims and scope Submit manuscript

Abstract

The classical training algorithms of support vector machines (SVM) are supervised learning algorithms which based on large-scale labeled samples, while these labeled samples are not easy to be acquired or labeled costly and class–unbalanced dataset, meanwhile these SVM algorithms are originally designed for the solution of two-class problems. To solve these problems of SVM, An Active learning algorithm based on decision directed acyclic graph (DDAG) for SVM is proposed in the paper, which train the multiclass SVMs using as few labeled instances as possible while maintaining the same SVM performance, or achieving the generalization performance of SVM classification as good as possible. The experimental results on the UCI data show that the proposed approach can achieve higher clasification accuracy, but using less labeled samples, while improving generalization performance and ruducing the marking costs of SVM training.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Vapnik, V.N.: Statistical learning theory. Wiley, New York (1998)

    MATH  Google Scholar 

  2. Kreßel, U.: Advances in kernel methods-support vector learning. In: Schölkopf, B., Burges, C.J.C., Smola, A.J. (eds.) Pairwise classification and support vector machines, pp. 255–268. MIT Press, Cambridge (1999)

    Google Scholar 

  3. Dietterich, T.G., Bakiri, G.: Solving multi-class learning problem via error correcting output codes. J. Artif. Intell. Res. 2, 263–286 (1995)

    Article  Google Scholar 

  4. Bennett, K. P., Blue, J. A.: A support vector machine approachto decision trees. In: Proceedings of the JCNN’98. Alaska: Anchorage, pp. 12396–24011, (1997)

  5. Platt, J., Cristianini, N., Shawe-Taylor, J.: Large margin DAGs for multiclass classification. In: Sollas, A., Leen, T.K., Mulle, K.R. (eds.) Advances in neural information processing systems 12, pp. 547–553. MIT Press, Cambridge (2000)

    Google Scholar 

  6. Tong, S.: Active learning: theory and applications. Stanford University, USA (2001)

    Google Scholar 

  7. Liu, W., Wang, T.: Active learning for online spam filtering. Asia Information Retrieval Symposium (AIRS). Springer, Berlin/Heidelberg, pp. 555–560, (2008)

  8. Brinker, K.: On multiclass active learning with support vector machines. In: Proceedings of the European Conference on Artificial Intelligence, pp. 969–970, (2004)

  9. Jain, P., Kapoor, A.: Active learning for large multi-class problems. In: Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Minmi, FL, USA., pp. 762–769, (2009)

  10. Yan, R., Yang, Y., Hauptmann, A.: Automatically labeling video data using multi-class active learning. In: Proceedings of the Ninth IEEE International Conference on Computer Vision (ICCV 2003). Washington: IEEE Computer Society, pp. 516–523, (2003)

  11. Yang, B., Sun, J., Wang, T. et al.: Effective multi-label active learning for text classification. In: Proceedings of the 15th ACM SIGKDD International Conference On Knowledge Discovery And Data Mining. ACM New York, NY, USA, pp 917–926, (2009)

  12. Yan, R., Hauptmann, A.: Multi-class active learning for video semantic feature extraction. In: Proceedings of the IEEE International Conference On Mutimedia and Expo(ICME), specela session On “Active Learning on Multimedia Retrieval”. Taipei, TaiWan, pp. 27–30, (2004)

  13. Alex Holub, Pietro Perona, Michael C. Burl.Entropy-based active learning for object recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Anchorage, AK, pp. 1–8, (2008)

  14. Qi, G.-J., Hua, X.-S., Rui, Y., et al.: Two-dimensional multilabel active learning with an efficient online adaptation model for image classification. IEEE Transact. Pattern Anal. Mach. Intell. 31(10), 1880–1897 (2008)

    Google Scholar 

  15. Joshi, A. J., Porikli, F., Papanikolopoulos, N.: Multi-class active learning for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)[C]. Minmi, FL, USA, pp. 2372–2379, (2009)

  16. Singh, M., Brew, A., Greene, D., et al.: Score normalization and aggregation for active learning in multi-label classification. UCD-CSI-2010-2. University College Dublin, Dublin (2010)

    Google Scholar 

  17. Vijayanarasimhan, S., Grauman, K.: What’s it going to cost you? predicting effort vs. informativeness for multi-label image annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Minmi, FL, USA., pp. 2262–2269, (2009)

  18. Hsu, C.W., Lin, C.J.: A comparison of methods for multi-class support vector machine. IEEE Transact. Neural. Netw. 13(2), 415–425 (2002)

    Article  Google Scholar 

  19. Takahashi, F., Shigeo, A.: Decision-tree-based multi-class support vector machines. In: Proceedings of the ICONIP Annual Conference of the Institute of Systems, Control and Information Engineers. Japan, pp. 483–484, (2002)

  20. LI, X.R., Zhao, G., Zhao, L.Y.: Design of decision-tree-based support vector machines multi-class classifier based on vector projection. Control Decis. 23(7), 745–750 (2008)

    MathSciNet  MATH  Google Scholar 

  21. Faraoun, K.M., Boukelif, A.: Genetic programming approach for multi-category pattern classification applied to network intrusions detection. Int. J. Comput. Intell. 3(1), 79–90 (2007)

    Google Scholar 

  22. Jing, H.U.: Machine learning and optimization design of neural network classifier. Hefei University of Technology, Hefei (2007)

    Google Scholar 

  23. Hu, J., GAO, J., Yang, J.: The approach to active leaning on fuzzy neural network classifier. J. Univ. Sci. Technol. China 38(3), 241–246 (2008)

    MATH  Google Scholar 

  24. Gong, X.: Research on bayesian learning theory and its application. Institute of Computing Technology Chinese Academy of Science, Beijing (2002)

    Google Scholar 

  25. Feng, C., Chen, Z., Huang, H.: Organization names recognition with active learning. Mini-micro Syst. 27(4), 710–714 (2006)

    Google Scholar 

  26. Baram, Y., Yaniv, R.E., Luz, L.: Online choice of active learning algorithms. J. Mach. Learn. Res. 5, 255–291 (2004)

    MathSciNet  Google Scholar 

  27. Lin, H.-T., Lin, C.-J., Weng, R.C.: A note on Platt’s probabilistic outputs for support vector machines. Mach. Learn. 68(3), 267–276 (2007)

    Article  Google Scholar 

  28. Xun, Y.U.A.N., Xiu-qing, W.U., Ri-chang, H.O.N.G., et al.: Video genre categorization using SVM classifiers with active learning. J. Univ. Sci. Technol. China 39(5), 474–478 (2009)

    Google Scholar 

  29. Ting-Fan, W., Lin, C.-J., Weng, R.C.: Probability estimates for multi-class classification by pairwise coupling. J. Mach. Learn. Res. 5, 975–1005 (2004)

    MathSciNet  MATH  Google Scholar 

  30. Hai-long, X.U., Xiao-feng, B.I.E., Hui, F.E.N.G., et al.: Active learning algorithm for SVM based on QBC. Syst. Eng. Electron. 38(12), 2865–2871 (2015)

    MATH  Google Scholar 

  31. Hai-long, X.U., Xiao-dan, W.A.N.G., Yong, L.I.A.O., et al.: Incremental training algorithm of SVM based on active learning. Control Decis. 25(2), 282–286 (2010)

    Google Scholar 

  32. Hai-long, X.U., Xiao-dan, W.A.N.G., Yong, L.I.A.O., et al.: New approach for optimizing model of RBF-SVM based on PSO. Control Decis. 25(3), 367–370 (2010)

    Google Scholar 

Download references

Acknowledgements

The authors wish to express their gratitude to the referees for their helpful comments and kind suggestions in revising this paper. This work is substantially supported by Grants from the China Postdoctoral Science Foundation (Nos.: 2017M613415).

Author information

Authors and Affiliations

  1. Air and Missile Defense College of Air Force Engineering University, Shaanxi Xi’an, 710051, China

    Hailong Xu, Xiaofeng Bie, Hui Feng & Ye Tian

Authors
  1. Hailong Xu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xiaofeng Bie
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hui Feng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ye Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hailong Xu.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, H., Bie, X., Feng, H. et al. Multiclass SVM active learning algorithm based on decision directed acyclic graph and one versus one. Cluster Comput 22 (Suppl 3), 6241–6251 (2019). https://doi.org/10.1007/s10586-018-1951-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10586-018-1951-3

Keywords

Search

Navigation