Adaptive Diagnosis Using Decision Trees (DT)



Functional fault diagnosis at board-level is desirable for high-volume production since it improves product yield. However, to ensure diagnosis accuracy and effective board repair, a large number of syndromes must be used. Therefore, the diagnosis cost can be prohibitively high due to the increase in diagnosis time and the complexity of syndrome collection/analysis. In this chapter, we apply decision trees to the problem of adaptive board-level functional fault diagnosis in high-volume manufacturing. The number of syndromes used for diagnosis is significantly less than the number of syndromes used for a priori training. Despite an order of magnitude or higher reduction in the number of syndromes compared to SVMs and ANNs, the diagnosis accuracy of the proposed method is comparable to that for the baseline methods and considerably higher for the same number of syndromes. Another advantage of using decision trees is that it can also be used to select an effective, but reduced, set of syndromes for use by ANNs or SVMs in a subsequent step. Moreover, to enable the reuse of knowledge from the test-design stage, we use an incremental version of decision trees so as to bridge the knowledge gap between test-design stage and volume production stage.


Adaptive diagnosis Board-level Decision tree Fault diagnosis Functional failures Incremental learning Production Machine learning 


  1. 1.
    Breiman L (1984) Classification and regression trees. Chapman & Hall/CRC, Boca RatonGoogle Scholar
  2. 2.
    Quinlan J (1986) Induction of decision trees. Mach Learn 1(1):81–106Google Scholar
  3. 3.
    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 IEEE International Test Conference (ITC), pp 1–10Google Scholar
  4. 4.
    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 IEEE European Test Symposium (ETS), pp 1–6Google Scholar
  5. 5.
    Vlahou A, Schorge JO, Gregory BW, Coleman RL (2003) Diagnosis of ovarian cancer using decision tree classification of mass spectral data. J Biomed Biotechnol 2003(5):308–314CrossRefGoogle Scholar
  6. 6.
    Abu-Hakima S (1992) Visualizing and understanding diagnoses. Can Artif Intell 30:1–10Google Scholar
  7. 7.
    McLachlan G, Do K, Ambroise C (2004) Analyzing microarray gene expression data, vol 422. Wiley, New YorkGoogle Scholar
  8. 8.
    Matlab Statistics Toolbox (2013)

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