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: Nekus Mikakasa
Country: Egypt
Language: English (Spanish)
Genre: History
Published (Last): 20 March 2013
Pages: 14
PDF File Size: 15.1 Mb
ePub File Size: 5.43 Mb
ISBN: 844-1-20663-378-8
Downloads: 80203
Price: Free* [*Free Regsitration Required]
Uploader: Kagabar

All the datasets except for the welding dataset were obtained from the UCI machine learning repository [ 41 ]. While data and algorithmic approaches constitute the majority efforts in the area of imbalanced data, several other approaches have also been conducted, which will be reviewed in Literature Review.

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.

View at Scopus N. For example, let be the cost of wrongly classifying positive instant as a negative one, while is the cost of the contrary case. The ROC is beneficial because it provides a tool to show the advantages represented by true positives versus mahalahobis represented by false positives of the classifier relating to data density.

Computational Intelligence and Neuroscience

Association rule mining is a recent classification approach combining association mining and classification into one approach [ 20 — 22 ]. View at Google Scholar A. Jugulum, The Mahalanobis-Taguchi Strategy: View at Scopus P. The feature will be included if it has a positive gain; otherwise, it should be excluded.

In the case of highly imbalanced data, one-class learning showed good classification results [ 28 ]. The MTS approach starts with collecting considerable observations from the ssytem dataset, tailed by separating of the unhealthy dataset i.

Section 2 reviews the previous work of imbalance data classifications methods, the Mahalanobis Taguchi System, and its applications. The most common used metrics for the evaluation of the imbalance data classification performance are andwhere the last one uses weighted importance of the recall and precision controlled bythe default value of is 1which results in better assessment than accuracy metric, but still biased to one class [ 10 ].


In order to overcome the above problem, several metrics such as [ 51 ] 19raguchi area under a Receiver Operating Characteristic AUC-ROC curve [ 52 ], and [ 19 ] 20 are used to assess the imbalance data classifier performance.

In this stage, the optimum threshold and the associated features are determined from the previous stage and the Mahalanobis Mahzlanobis for the new observation is calculated based on those parameters. From the confusion matrix, Table 1the following can be defined: Each factor in the orthogonal array design can be calculated independently of all other factors since the design is balanced i.

Bayes theorem is the center of Naive Bayesian classifier NB in which class conditional independence is assumed. The scaled MD for the positive date set supposes to be different from MD for those for the negative dataset.

The proposed model, Algorithm 1provides an easy, reliable, and systematic way to determine the threshold for the Mahalanobis Taguchi System MTS and its variants i. Mathematically, this can be converted into the following optimization model.

Abstract The Mahalanobis Taguchi System MTS is considered one of the most promising binary classification algorithms to handle imbalance data. The organization of the paper is as follows: In order to assess the suggested algorithm, the MMTS has been benchmarked with several popular algorithms: Step 2 optimization stage.

Modified Mahalanobis Taguchi System for Imbalance Data Classification

In this context, it can be seen that accuracy and error rate metrics are biased towards one class on behalf of the other. To handle the imbalance data, determining many minimal supports for different classes to present their varied recurrence is required [ 23 ].

Finally, MMTS was the least performance among the classifiers for the car dataset. Mhaalanobis, imbalance ratio is not the only reason that causes degradation in classifier performance. On the other hand, one-class learning [ 2425 ] used the target class only to determine if the new observation belongs to this class or not.

For the genetic algorithm, the following parameters were used in the implementation: The experimental setup, the materials used, and all the other related information can be found in the same reference.

The problems reported in data approaches are as follows: It should be noted in this study that the imbalance ratio effect on the classification results should be explored. In order to determine if there is a significant difference among mahalanobiss classifiers performances i. To achieve this objective of using the optimum number mahalsnobis required welds that sustain the required strength of the structure, weld quality must be achieved.


Table 8 shows the values obtained from comparing the performances of the classifiers between any two classifiers using the Mann—Whitney test and the resulting classifiers rank.

MMTS showed a very robust classification performance across the range of the imbalance ratio; it also showed better classification performance results comparable with KBA, ACT i.

To overcome the 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.

MMTS and the benchmarked algorithms have been evaluated for each of the ten repetitions simultaneously. The idea of the SVMs classifier is based on establishing the most appropriate hyperplane that separates class observations from each other Figure 2. Assume there are two classes: In order to rank the classifiers, the pairwise Mann—Whitney test is used.

Using 1, the inverse of the correlation matrix, the mean, and the sample standard deviation of the featurefor the negative data, mahalanobs, the MD of the positive observations can be calculated.

View at Google Scholar. The ROC plot is mahhalanobis – plot in which 2 is plotted on the vertical axis and 3 is plotted on the horizontal axis. It has been noticed that the effect of the maximum Fishers Discriminant Ratio -ratio is dominated by the imbalance ratio IR effect i.

In this case, the training data was 1, observations i. The curve drawn in the figure represents the MTS classifier performance for different threshold values.

MTS is a multivariate supervised learning approach, which aims to classify new observation into one of the two classes i.