The metal bush assembling process is a process of inserting and compressing a metal bush that serves to reduce the occurrence of noise and stable compression in the rotating section. In the metal bush assembly process, the head diameter defect and placement defect of the metal bush occur due to metal bush omission, non-pressing, and poor press-fitting. Among these causes of defects, it is intended to prevent defects due to omission of the metal bush by using signals from sensors attached to the facility. In particular, a metal bush omission is predicted through various data mining techniques using left load cell value, right load cell value, current, and voltage as independent variables. In the case of metal bush omission defect, it is difficult to get defect data, resulting in data imbalance. Data imbalance refers to a case where there is a large difference in the number of data belonging to each class, which can be a problem when performing classification prediction. In order to solve the problem caused by data imbalance, oversampling and composite sampling techniques were applied in this study. In addition, simulated annealing was applied for optimization of parameters related to sampling and hyper-parameters of data mining techniques used for bush omission prediction. In this study, the metal bush omission was predicted using the actual data of M manufacturing company, and the classification performance was examined. All applied techniques showed excellent results, and in particular, the proposed methods, the method of mixing Random Forest and SA, and the method of mixing MLP and SA, showed better results.

Nowadays most colleges are confronting with a serious problem because many students have left their majors at the colleges. In order to make a countermeasure for reducing major separation rate, many universities are trying to find a proper solution. As a similar endeavor, the objective of this paper Is to find a predicting model of students leaving their majors. The sample for this study was chosen from a university in Kangwon-Do during seven years(2000.3.1 ~ 2006. 6.30). In this study, the ratio of training sample versus testing sample among partition data was controlled as 50% : 50% for a validation test of data division. Also, this study provides values about accuracy, sensitivity, specificity about three kinds of algorithms including CHAID, CART and C4.5. In addition, ROC chart and gains chart were used for classification of students leaving their majors. The analysis results were very informative since those enable us to know the most important factors such as semester taking a course, grade on cultural subjects, scholarship, grade on majors, and total completion of courses which can affect students leaving their majors.

The main objective of this study is to provide feature analysis of industrial accidents in manufacturing industries using CART algorithm, a data mining technique. In this study, data on 10,536 accidents were analyzed to create risk groups, including the risk of disease and accident. Also, this paper used the gains chart produced by the decision tree. According to the result, gains chart can be used for a risk analysis for industrial accidents management. The sample for this work chosen from data related to manufacturing industries during three years (2002～2004) in Korea. The resulting classification rules have been incorporated into development of a developed database tool to help quantify associated risks and act as an early warning system to individual industrial accident in manufacturing industries.

Many researches have been focused on the analysis of industry disasters in order to reduce them. As a similar endeavor, this paper provides a propensity analysis of injured people from various industries using classification and regression tree(CART), a data mining algorithm. The sample for this work was chosen from 25,157data related to various industries during one year ( 2003.2~2004.1 ) at Kangwon-Do in Korea. For the purpose of this paper, eight independent variables (injured date, injured time, injured month, type of Injured person, continuous service period, sex, company size, age)are taken from injured person group. According to the analysis result, it is found that five out of the eight factors that are predicted as significant have salient effects. Factors of season, time/hour, day of the week, or month which disasters happened do not show any significant effect. This paper provides common features of injured people. The provided analysis result will be helpful as a starting point for root cause analysis and reduction of industry disasters and also for development of a guideline of safety management.

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manuf

Data mining technique is the exploration and analysis, by automatic or semiautomatic means, of large quantities of data in order to discover meaningful patterns and rules. This paper uses a data mining technique for the prediction of defect types in manufacturing process. The purpose of this paper is to model the recognition of defect type patterns and prediction of each defect type before it occurs in manufacturing process. The proposed model consists of data handling, defect type analysis, and defect type prediction stages. The performance measurement shows that it is higher in prediction accuracy than logistic regression model.

We study data mining technique in an electronic commerce. Customers travel web pages in an shopping mall and they sometimes purchase products. It is important for a web master in a shopping mall to know customer's purchasing patterns. We discover both association rules among customer's purchasing products and customer's traversal paths. We propose three phase mining technique to explore it. In the first phase, it find large items from sales database. In the second phase, it add to traversal paths. In the third phase, it discover associations rules from large items.