Abstract
In modern manufacturing, hundreds of process variables are collected, and it is usually difficult to identify the most informative ones. Partial Least Square Regression provides an efficient way to evaluate each variable, but it cannot evaluate any variable subset as a whole. In the paper, a new framework of key process variable identification is proposed. It combines PLSR model and wrapper feature selection to firstly assess every variable individually and then the top variables in groups. Five datasets are tested, and the average classification accuracy is higher and the key process variables identified are less than the available approaches.
Supported by National Natural Science Foundation of China (No.70931004, 70802043).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aha DW, Kibler D, Albert MK (1991) Instance-based learning algorithms. Mach Learn 6:37–66
Anzanello MJ, Albin SL, Chaovalitwongse WA (2009) Selecting the best variables for classifying production batches into two quality levels. Chemom Intell Lab Syst 97:111–117
Anzanello MJ, Albin SL, Chaovalitwongse WA (2012) Multicriteria variable selection for classification of production batches. Eur J Oper Res 218:97–105
Gauchi J, Chagnon P (2001) Comparison of selection methods of explanatory variables in PLS regression with application to manufacturing process data. Chemom Intell Lab Syst 58:171–193
Gerladi P, Kowalski BR (1986) Partial least squares regression: a tutorial. Anal Chim Acta 185:1–17
Guyon I, Elisseeff A (2003) An introduction to variable and feature selection. J Mach Learn Res 3:1157–1182
Hall MA, Holmes G (2003) Benchmarking attribute selection techniques for discrete class data mining. IEEE Trans Knowl Data Eng 15(3):1437–1447
Hoskuldsson A (1988) PLS regression methods. J Chemom 2:211–228
Hua J, Tembe WD, Dougherty ER (2009) Performance of feature-selection methods in the classification of high-dimension data. Pattern Recognit 42:409–424
Inza I, Larranaga P, Blanco R, Cerrolaza AJ (2004) Filter versus wrapper gene selection approaches in DNA microarray domains. Artif Intell Med 31:91–103
Jong S (1993) SIMPLS: an alternative approach to partial least squares regression. Chemom Intell Lab Syst 18:251–263
Kettaneha N, Berglundb A, Wold S (2005) PCA and PLS with very large data sets. Comput Stat Data Anal 48:69–85
Kohavi R, John GH (1997) Wrappers for feature selection. Artif Intell 97:273–324
Pudil P, Novovicova J, Kittler J (1994) Floating search methods in feature selection. Pattern Recognit Lett 15:1119–1125
Su C, Chen L, Chiang T (2006) A neural network based information granulation approach to shorten the cellular phone test process. Comput Ind 57:412–423
Wold S, Sjostrom M, Eriksson L (2001) PLS-regression: a basic tool of chemometrics. Chemom Intell Lab Syst 58:109–130
Yu L, Liu H (2003) Feature selection for high-dimensional data: a fast correlation-based filter solution. In: Proceedings of the twentieth international conference on machine learning (ICML-2003), Washington, DC
Acknowledgment
We would like to express our gratitude to Prof. Jean-Pierre Gauchi for providing the datasets of ADPN, LATEX, OXY, and SPIRA; and to Prof. Svante Wold for providing the PAPER dataset and some helpful advice about PLSR model. We also thank Dr. Michel J. Anzanello and Prof. Susan L. Albin for their supportive advice and encouragement during the algorithm testing.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tian, Wm., He, Z., Yan, W. (2013). Key Process Variable Identification for Quality Classification Based on PLSR Model and Wrapper Feature Selection. In: Dou, R. (eds) Proceedings of 2012 3rd International Asia Conference on Industrial Engineering and Management Innovation (IEMI2012). Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33012-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-642-33012-4_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33011-7
Online ISBN: 978-3-642-33012-4
eBook Packages: Business and EconomicsBusiness and Management (R0)