Advertisement

Diagnosis Using Multiple Classifiers and Majority-Weighted Voting (WMV)

Chapter
  • 449 Downloads

Abstract

In this chapter, we integrate a meta-learning technique, namely weighted-majority voting (WMV) , in our diagnosis system. Multiple classifiers can be leveraged in a WMV-based diagnosis system to incorporate different sets of repair suggestions and form a single set of root-cause candidates. We review the usage of artificial neural networks (ANNs) . The advantage of ANNs is its interpretation of the relationship between the syndromes and corresponding faulty components. A trained ANN model associates the output to the weighted inputs, which derives an intuition on the contribution of each input to the output. In addition, the advantage of SVMs, as described in Chap.  2, is that the solution provided by SVMs is globally optimal and unique, while ANNs suffer from multiple local minima. Both of these two methods can be rapidly trained and they are scalable to large datasets. The proposed WMV-based system uses weights to combine the repair suggestions provided by each machine in order to identify a single set of recommended repair suggestions. The proposed WMV system can leverage results from both ANNs and SVMs.

Keywords

ANN Board-level Fault diagnosis Functional failures Machine learning Majority-weighted voting Neural networks Production Support-vector machines SVMs 

References

  1. 1.
    Zhang Z, Wang Z, Gu X, Chakrabarty K (2010) “Board-level fault diagnosis using Bayesian inference”. In: Proceedings of the IEEE VLSI test symposium (VTS), p 1–6Google Scholar
  2. 2.
    Zhang Z. Chakrabarty K, Wang Z, Wang Z, Gu X (2011) “Smart diagnosis: efficient board-level diagnosis and repair using artificial neural networks”. In: Proceedings of the IEEE international test conference (ITC), pp 1–10Google Scholar
  3. 3.
    Zhang Z, Gu X, Xie Y, Wang Z, Chakrabarty K (2012) “Diagnostic system based on support-vector machines for board-level functional diagnosis”. In: Proceedings of the IEEE European test symposium (ETS), p 1–6Google Scholar
  4. 4.
    Ye F, Zhang Z, Chakrabarty K, Gu X (2013) Board-level functional fault diagnosis using artificial neural networks, support-vector machines, and weighted-majority voting. IEEE Trans Comput-Aided Des Int Circuits Syst (TCAD) 32(5):723–736CrossRefGoogle Scholar
  5. 5.
    Ye F, Zhang Z, Chakrabarty K, Gu X (2013) “Board-level functional fault diagnosis using learning based on incremental support-vector machines”. In: Proceedings of the IEEE Asian test symposium (ATS), pp 208–213Google Scholar
  6. 6.
    Al-Jumah AA, Arslan T (1998) Artificial neural network based multiple fault diagnosis in digital circuits. Proceedings of the international symposium on circuits and systems (ISCAS), vol 2, pp 304–307Google Scholar
  7. 7.
    Totton K, Limb P (1991) “Experience in using neural networks for electronic diagnosis”. In: Proceedings of the ACM international conference on artificial neural networks, pp 115–118Google Scholar
  8. 8.
    Vapnik V (1995) The nature of statistical learning theory. Springer, HeidelbergCrossRefzbMATHGoogle Scholar
  9. 9.
    Haykin S (2008) Neural Networks and Learning Machines. Prentice Hall, New JerseyGoogle Scholar
  10. 10.
    Neural Network Toolbox (2012). http://www.mathworks.com/products/neuralnet/
  11. 11.
    Littlestone N, Warmuth M (1994) The weighted majority algorithm. J Inf Comput 108(2):212–261MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Rakotomamonjy A, Canu S (2008) SVM and Kernel Methods Matlab Toolbox. http://asi.insa-rouen.fr/enseignants/~arakoto/toolbox/index.html
  13. 13.
    Keerthi S, Lin C (2003) Asymptotic behaviors of support vector machines with Gaussian kernel. Neural Comput 15(7):1667–1689CrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2017

Authors and Affiliations

  1. 1.Huawei TechnologiesSanta ClaraUSA
  2. 2.Department of Electrical and Computer EngineeringDuke UniversityDurhamUSA

Personalised recommendations