NDA Based Hierarchical Classification Scheme for Identifying the Contributors to a Multivariate Control Chart

Abstract:

Many multivariate control charts have been proposed for monitoring several related quality characteristics simultaneously. However, even when an out-of-control signal is detected, the employed multivariate control charts generally do not provide any interpretable information associated with that signal. That is, the contributors of the out-of-control event can not be identified by the charts. Hence, how to tackle this interpretation problem effectively is an important issue in multivariate process control. One rarely addressed but very crucial property of this interpretation problem is that the number of possible outcomes can be very large. According to this key property, a nonparametric discriminant analysis (NDA)-based hierarchical classification scheme is proposed in this paper. A simulation experiment including several popular classification methods was conducted for evaluating the performance of the proposed method. The result shows that our proposed scheme is very competitive when measured against these popular methods.

• Periodical: Key Engineering Materials (Volumes 467-469)
• Pages: 427-432
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.467-469.427
• Online since: February 2011
• Authors: H.Y. Huang, Jong Chih Chien
• Keywords: Hierarchical Classification, Multivariate Process Control, Nonparametric Discriminant Analysis (NDA), Support Vector Machine (SVM)

References

[1] A.B. Yeh, et. al: Multivariate Control Charts for Monitoring Covariance Matrix: A Review. Journal of Quality Technology and Quantitative Management, Vol. 3, No. 4 (1992), pp.415-436.

DOI: 10.1080/16843703.2006.11673124

[2] R.L. Mason, N.D. Tracy, J.C. Young: Decomposition of T² for multivariate control chart interpretation. Journal of Quality Technology, Vol. 27 (1995), pp.99-108.

DOI: 10.1080/00224065.1995.11979573

[3] G.C. Runger, F.B. Alt, D.C. Montgomery: Contributors to a multivariate SPC chart signal. Communications in Statistics - Theory and Methods, Vol. 25 (1996), pp.2203-2213.

DOI: 10.1080/03610929608831832

[4] J.E. Jackson: A user guide to principal components; John Wiley: New York (1991).

[5] T. Kourti, J.F. MacGregor: Multivariate SPC methods for process and product monitoring. Journal of Quality Technology, Vol. 28 (1996), pp.409-428.

DOI: 10.1080/00224065.1996.11979699

[6] F. Aparisi, J. Sanz: Interpreting the Out-of-Control Signals of Multivariate Control Charts Employing Neural Networks. World Academy of Science, Engineering and Technology, Vol. 61 (2010), pp.226-230.

[7] S. Kumar, J. Ghosh, and M. Crawford: Hierarchical Fusion of Multiple Classifiers for Hyperspectral Data Analysis, Pattern Analysis and Applications, Vol. 5, No. 2 (2002), p.210–220.

DOI: 10.1007/s100440200019

[8] B. Kim, D.A. Landgrebe: Hierarchical classifier design in high-dimensional numerous class cases. IEEE Trans. Geoscience and Remote Sensing, Vol. 29, No. 4 (1991), p.518–528.

DOI: 10.1109/36.135813

[9] Y. Chen, M.M. Crawford, J. Ghosh: Integrating Support Vector Machines in a Hierarchical Output Space Decomposition Framework, IEEE International Geoscience and Remote Sensing Symposium, Vol. 2 (2004), pp.949-952.

DOI: 10.1109/igarss.2004.1368565

[10] S. Kumar and J. Ghosh: GAMLS: A generalized framework for associative modular learning systems, Applications and Science of Computational Intelligence II (1999), p.24–34.

DOI: 10.1117/12.342865

[11] K. Fukunaga: Introduction to Statistical Pattern Recognition, San Diego, CA: Academic Publishers (1990).

[12] K. Fukunaga and M. Mantock: Nonparametric discriminant analysis, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. PAMI-5 (1983), p.671–678.

DOI: 10.1109/tpami.1983.4767461