Impact of Mahalanobis space construction on effectiveness of Mahalanobis-Taguchi system

被引：2
作者：
Wang, Ning [1 ]
Saygin, Can [2 ]
Sun, Shu-Dong [1 ]
机构：
[1] Department of Industrial Engineering, Northwestern Polytechnical University
[2] Department of Mechanical Engineering, University of Texas, San Antonio
来源：
International Journal of Industrial and Systems Engineering | 2013年 / 13卷 / 02期
关键词：
Diagnostics; Mahalanobis distance; Mahalanobis space; Mahalanobis-taguchi system; Multivariate analysis; Pattern recognition; Quality engineering;
D O I：
10.1504/IJISE.2013.051794
中图分类号：
学科分类号：
摘要：
Mahalanobis-Taguchi system (MTS) is a pattern recognition technique that aids in quantitative decisions by constructing a multivariate measurement scale using data analytic methods. In this paper, the importance of constructing the Mahalanobis space (MS) is demonstrated using the data from Soylemezoglu et al. (2010). The data collected from ten attributes for normal observations are treated using a control chart approach, similar to statistical process control models. Two MS models are constructed using the data inside the control limits of ±3σ and ±2σ for each variable and benchmarked in terms of accuracy, sensitivity, specificity and relative sensitivity. In addition, the impact of attribute selection is also demonstrated. This study shows that (1) a reliable MS is important for effective deployment of MTS; (2) the construction of MS, as well as selection of variables, should be driven by domain experts since understanding data in order to determine the normal observations require in-depth knowledge in the particular field of application and (3) for novice practitioners, filtering normal data using different control limits, applying MTS using alternative MS models, and investigating different combinations of significant features for the same application, and then determining the best MS model can be more effective. Copyright © 2013 Inderscience Enterprises Ltd.
引用
收藏
页码：233 / 249
页数：16
相关论文
共 33 条
  • [1] Asada M., Wafer yield prediction by the Mahalanobis-Taguchi system, The 6th IEEE International Workshop on Statistical Methodology, pp. 25-28, (2001)
  • [2] Cudney E.A., Drain D., Paryani K., Sharma N., A comparison of the Mahalanobis- Taguchi system to a standard statistical method for defect detection, Journal of Industrial and Systems Engineering, 2, 4, pp. 250-258, (2009)
  • [3] Cudney E.A., Hong J., Jugulum R., Paryani K., Ragsdell K.M., Taguchi G., An evaluation of Mahalanobis-Taguchi system and neural network for multivariate pattern recognition, Journal of Industrial and Systems Engineering, 1, 2, pp. 139-150, (2007)
  • [4] Cudney E.A., Jugulum R., Paryani K., Forecasting consumer satisfaction for vehicle ride using a multivariate measurement system, Int. J. Industrial and Systems Engineering, 4, 6, pp. 683-696, (2009)
  • [5] Cudney E.A., Paryani K., Ragsdell K.M., Applying the Mahalanobis-Taguchi system to vehicle ride, Journal of Industrial and Systems Engineering, 1, 3, pp. 251-259, (2007)
  • [6] Dasgupta T., Integrating the improvement and the control phase of six sigma for categorical responses through application of Mahalanobis-Taguchi system MTS, Int. J. Industrial and Systems Engineering, 4, 6, pp. 615-630, (2009)
  • [7] Das P., Mukherjee S., An unsupervised classification scheme for multi-class problems including feature selection based on MTS philosophy, Int. J. Industrial and Systems Engineering, 4, 6, pp. 665-682, (2009)
  • [8] Foster C.R., Jugulum R., Frey D.D., Evaluating an adaptive one-at - A -time search procedure within the Mahalanobis-Taguchi system, Int. J. Industrial and Systems Engineering, 4, 6, pp. 600-614, (2009)
  • [9] Hayashi S., Tanaka Y., Kodama E., A new manufacturing control system using Mahalanobis distance for maximizing productivity, IEEE Transactions on Semiconductor Manufacturing, 15, 4, pp. 442-446, (2001)
  • [10] Huang C.L., Hsu T.S., Liu C.M., The Mahalanobis-Taguchi system - neural network algorithm for data-mining in dynamic environments, Expert Systems with Applications, 36, 3, pp. 5475-5480, (2009)
1234