An Output Grouping Based Approach to Multiclass Classification Using Support Vector Machines

  • Xuan ZhaoEmail author
  • Steven Guan
  • Ka Lok Man
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 393)


Support Vector Machine (SVM) classifiers are binary classifiers in nature, which have to be coupled/assembled to solve multi-class problems. One-Versus-Rest (1-v-r) is a fast and accurate method for SVM multiclass classification. This paper investigates the effect of output grouping on multiclass classification with SVM and offers an even faster version of 1-v-r based on our output grouping algorithm.


Multiclass classification Support vector machine Decomposition method Output grouping 


  1. 1.
    Chang C-C, Lin C-J (2011) Libsvm. ACM Trans Intell Syst Technol 2(3):1–27CrossRefGoogle Scholar
  2. 2. (2016). Available:
  3. 3.
    Hsu C-W, Lin C-J (2002) A comparison of methods for multi-class support vector machines. IEEE Trans Neural Networks 13(2):415–425CrossRefGoogle Scholar
  4. 4.
    Mehra N, Gupta S (2013) Survey on multiclass classification methods. Int J Comput Sci Inf Technol 4(4):572–576Google Scholar
  5. 5.
    Rifkin R (2008) Multiclass classification. Lect Slides. FebruaryGoogle Scholar
  6. 6.
    Tewari A, Bartlett PL (2007) On the Consistency of multiclass classification methods. J Mach Learn Res 8:1007–1025MathSciNetzbMATHGoogle Scholar
  7. 7.
    Guan S-U, Li S (2002) Parallel growing and training of neural networks using output parallelism. IEEE Trans Neural Netw 13(3):542–550CrossRefGoogle Scholar
  8. 8.
    Yang S, Guan S-U, Guo SJ, Zhao LF, Li WF, Xue HX (2013) Neural Network output partitioning based on correlation. J Clean Energy Technol 1(4):342–345CrossRefGoogle Scholar
  9. 9.
    Yang S, Guan SU, Li WF, Zhao LF (2013) Low-interference output partitioning for neural network training. J Clean Energy Technol 1(4)Google Scholar
  10. 10.
    LIBSVM data: classification, regression, and multi-label. Available Accessed on 03 Feb 2016
  11. 11.
    Dietterich TG, Bakiri G (1994) Solving multiclass learning problems via error-correcting output codes. J Artif Intell Res 2:263–286zbMATHGoogle Scholar
  12. 12. (2016). Available:
  13. 13.
    Guo SJ, Guan S-U, Yang S, Li WF, Zhao LF, Song JH (2013) Input partitioning based on correlation for neural network learning. J Clean Energy Technol 1(4):335–338CrossRefGoogle Scholar
  14. 14.
    Guo S, Guan S-U, Li W, Man KL, Liu F, Qin AK (2013) Input space partitioning for neural network learning. Int J Appl Evol Comput 4(2):56–66CrossRefGoogle Scholar
  15. 15.
    Guo S, Guan SU, Li W, Zhao L, Song J, Cao M (2012) Promotion-based input partitioning of neural network. In: International conference on computer, communication, automation and control 2012 (CCAC 2012)Google Scholar
  16. 16.
    Guo S, Guan SU, Li W, Zhao L, Song J, Cao M (2014) Promotion-based input partitioning of neural network. In: Proceedings of the 9th international symposium on linear drives for industry applications, vol 3, pp 179–186Google Scholar
  17. 17.
    Bordes A, Ertekin S, Weston J, Bottou L (2005) Fast kernel classifiers with online and active learning. J Mach Learn Res 6:1579–1619MathSciNetzbMATHGoogle Scholar

Copyright information

© Springer Science+Business Media Singapore 2016

Authors and Affiliations

  1. 1.Xi’an Jiaotong-Liverpool UniversitySuzhouChina

Personalised recommendations