Applying the Mahalanobis–Taguchi System to. Improve Tablet PC Production Processes. Chi-Feng Peng 2,†, Li-Hsing Ho 3,†, Sang-Bing Tsai. The purpose of this paper is to present and analyze the current literature related to developing and improving the Mahalanobis-Taguchi system (MTS) and to. ABSTRACT. The Mahalanobis-Taguchi System is a diagnosis and predictive method for analyzing patterns in multivariate cases. The goal of this study is to.

Author: Branris Shakajin
Country: Equatorial Guinea
Language: English (Spanish)
Genre: Relationship
Published (Last): 25 April 2010
Pages: 213
PDF File Size: 7.40 Mb
ePub File Size: 15.74 Mb
ISBN: 175-2-30831-813-3
Downloads: 73663
Price: Free* [*Free Regsitration Required]
Uploader: Yoll

The constant current control applied a current stepper, one Ampere per weld, to compensate tagucho the increase in the electrode diameter or what is known as mushrooming effect.

Mathematically, where is a variable vector of size and is the class. Association rule mining is a syste, classification approach combining association mining and classification into one approach [ 20 — 22 ].

On the other hand, Sun et al. The author declares that there are no conflicts of interest regarding the publication of this paper. The problem with the algorithmic approach is that it needs an extensive knowledge of specific classifier i. Changing the threshold will change the point location on the curve i.

Finally, the aim of this research is to enhance the Mahalanobis Taguchi System MTS classifier performance through providing a scientific, rigorous, and systematic method of determining the binary classification threshold that discriminates between the two classes, which can be applied to the MTS and its variants i. Since many features are used to calculate the MD, so that the probability to have significant features for the multivariable dataset is high, Taguchi mahalxnobis array is used to screen these features.

Imbalance data systtem often in real life such as text classification [ 7 ]. The syatem work regarding SVMs was published by Cortes and Vapnik [ 42 ], continued by significant contributions from other researchers [ 43 ].

Even with such unrealistic assumption, Naive Bayes still found noticeable success stories comparable with other types of sophisticated classifiers, for example, NB used in text classification [ 47 ], medical diagnosis [ 48 ], and systems performance management [ 49 ]. View at Scopus P.


Step 3 testing stage. In the case of highly imbalanced data, one-class learning showed good classification results [ 28 ]. On the other hand, specificity can be understood tqguchi the accuracy of the negative observations: The ROC plot is an – plot in which 2 is plotted on the vertical axis and 3 is plotted on the horizontal axis.

Modified Mahalanobis Taguchi System for Imbalance Data Classification

All the datasets except for the welding dataset were obtained from the UCI machine learning repository [ 41 ]. Since more features mean a higher cost of monitoring and require more processing time, it is important to exclude the unnecessary features from having an efficient classifier.

The next step is to determine the threshold that will be used to discriminate the negative observations from the positive ones maalanobis on the MD magnitude, which means that the new observation can be classified into either a positive or negative observation according to the following criteria: Unfortunately, imbalance ratio is not the only reason that causes degradation in classifier performance.

The data consisted of 3, welds, from which 3, were normal welds, and the others were expulsion welds performed mahalanobls an alternating current AC constant current controller. Recently worldwide competition pushes automotive OEMs to improve their productivity, reduce nonvalue added activity, and reduce cost.

Computational Intelligence and Neuroscience

For the data approach, the main idea is to balance the class density randomly or informatively i. The Mahalanobis Taguchi System MTS is considered one of the most promising binary classification algorithms to handle imbalance data.

Section 5 presents a case study to demonstrate the applicability of the proposed research. In order to investigate the robustness performance of the studied classifiers related to the class imbalance criterion, fourteen different UCI [ 41 ] datasets and one data welding from El-Banna et al.

The adaptation of decision tree classifier to suit the imbalance data can be accomplished by adjusting the probabilistic estimate of the tree leaf or developing new trimming approaches [ 14 ].


In this paper, we investigated a wide range of IR, from 1. The scaled MD for the positive date set supposes to be different from MD for those for the negative dataset. Many published works [ 16195354 ] pointed out that SVMs classification performance drops significantly when dealing with the imbalance data; therefore, modified SVMs mahalanobiss have been suggested to overcome this issue tqguchi both data and algorithmic levels.

In order to determine if there is a significant difference among the classifiers performances i. A low value of -ratio means that observations are mixed together and overlapped regions are large, and therefore it is difficult to discriminate between these observations. The border that separates balance from imbalance data is vague; for example, imbalance ratio, which is the ratio between the major to minor class observations, is reported from small values of to 1 to An arbitrary threshold is assumed i.

Table of Contents Alerts. Finally, the problem in using the cost-sensitive learning approach is the assumption of previous knowledge for many errors types and imposing mahalanobbis higher cost to the minority class to improve the prediction accuracy.

Unfortunately, the examination of accuracy and error rates 14 and 15 reveals that these metrics are not sensitive to the data distribution [ 10 ].

The most appropriate hyperplane means the one with the largest width of the margin parallel to the hyperplane with no interior points. Step 2 optimization stage. To overcome mahalanobjs pitfalls of data and algorithmic approaches to solve the problem of imbalanced data classification, the classification algorithm needs to be capable of dealing with imbalance data directly without resampling and should have a systematic foundation for determining the cost matrices or the threshold.