This paper uses a data mining methodologies to improve and predict cause of defect process variables in manufacturing process. Traditional statistical process control (SPC) techniques of control charting are not applicable in many process industries because it is difficult to analyze the cause of many process variables. The paper suggests that data mining methodologies useful when sequence rule, SVM (classification) methods are find out cause of defect process variables and SVM (prediction) methods used to predict process variables in manufacturing process. Therefore, it is allowing improved control in manufacturing process.

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.

With development of the database, there are too many data on process variables and the manufacturing process for the traditional statistical process control methods to identify the process variables related with assignable causes. Data mining is useful in

This paper uses a data mining methodologies to improve and predict cause of defect process variables in manufacturing process. Traditional statistical process control (SPC) techniques of control charting are not applicable in many process industries because it is difficult to analyze the cause of many process variables. The paper suggests that data mining methodologies useful when sequence rule, SVM (classification) methods are find out cause of defect process variables and SVM (prediction) methods used to predict process variables in manufacturing process. Therefore, it is allowing improved control in manufacturing process.

This paper presents a data-mining aided heuristic algorithm development. The developed algorithm includes three steps. The steps are a uniform coverage selection, development of feature functions and clustering, and a decision tree making. The developed algorithm is employed in designing an optimal multi-station fixture layout. The objective is to minimize the sensitivity function subject to geometric constraints. Its benefit is presented by a comparison with currently available optimization methods.

효과적으로 공정을 관리하기위하여 제품의 품질특성치에 영향을 주는 데이터를 수집하고 공정을 해석하여한다. 이를 위해서 데이터 마이닝(Data Mining)이 많이 수행되어지고 있다. 본 연구에서는 공정으로부터 수집된 대량의 정보 데이터를 신경망(Neural Network)기법을 통하여 공정의 불량률을 예측하고 불량률이 높게 나타난 데이터를 통해 연관규칙(Association Rule)을 적용하여 불량에 영향을 주는 공정의 패턴을 파악 공정을 개선하고자 한다.

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

In general, data mining has iterative processes with the following five steps: Data Selection, Cleansing, Transformation, Mining, Interpretation. Among these steps, steps of data selection and cleansing are performed to classify data. There are two types of data, continuous data and discrete data. Discrete data has a classified structure and it is easy to obtain rules from data. However, there are no general rules for classified method of data in continuous data. So, the result of data analysis will be differed from the classified method of data in continuous data. This research presents a methodology that can obtain the rules from data and classify data according to situations in DBMS (Data Base Management Systems).

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.

In this paper, we address a mining association rules with weighted items and multiple minimum support. We generalize this to the case where items are given weights to reflect their importance to the user. And to find rules that involve both frequent and rare items, we specify multiple minimum supports to reflect the frequency of the items. In rule mining, different rules may need to satisfy different minimum supports depending on what items are in the rules.

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.

Due to recent changes of computer & networks, the IDS(Intrusion Detection System) need to be developed for new intrusion patterns. The current IDS have limited on recognition and correspond to new intrusion patterns on detection speed for multi packet which dealing on the network. Therefore, new technology need to increasing efficiency and speed of detection speed requested. The aim of this research is the development of standard and systematic method on intrusion detection. The core idea is using data mining method to find bundle of patterns on networking program and user behavior patterns as well as apply the feature systems to calculate the classifiers which could recognize the well known or irregular intrusions. In this paper, we will recommend following steps to develop the intrusion detection system: First, we will learn the detection applying technique for multi intrusion cases. Second, we will use data mining technique which fast recognize the current intrusion patterns and new patterns. Third, to recognize intrusion patterns, information of packet on the network and recorded data on the host sessions have studied. Fourth, we will create regulations between intrusion and normal behavior by practical use of logged file abstraction programs. Fifth, we will analysis intrusion detection pattern based on the created regulations and study results.

Today''s database system needs to collect huge amount of questionnaire that results from development of the information technology by the internet, so it has to be administrable. However, there are many difficulties concerned with finding analytic data or

Every port is competing for attracting loyal customers from other ports to achieve more profits stably. This paper proposes a data-mining scheme to facilitate this process. For resolving the problem, the OD (Origination-Destination) data are gathered from the AIS (Automatic Identification System) data. The OD data are clustered according to the arrival dates and ports. The FP-growth algorithm is applied to mine the frequent patterns of ships arriving at ports. Maintaining a loyal customer list for port updates and accuracy is critical in establishing its usefulness. These lists are critical as they can be used to provide suggestions for new products and services to loyal customers. Finally, based on the frequent patterns of the ships and the mode of arrival times, a formula proposed in this paper to derive shipping companies’ loyalty to ports was applied. The case of Kaohsiung port was shown as an example of our algorithm, and the OD data of ships in 2017-2018 were processed. Using the results of our algorithm, other rival ports, such as Shanghai or Busan, may attract customers no longer loyal to Kaohsiung ports in the last two years and attract them as new loyal customers.

최근 들어 VR 산업의 성장을 위한 양질의 VR 콘텐츠에 대한 필요성이 꾸준히 제기되고 있다. 이에 본 연구는 VR 콘텐츠 중에서 가장 큰 주목을 받고 있는 VR 게임의 사용자의 관심요소에 대해 연구하였다. 연구 수행을 위해 스팀(STEAM)의 사용자 리뷰 데이터를 활용하였고 리뷰 데이터에 텍스트마이닝과 네트워크 분석을 적용한 결과 VR 게임 사용자의 관심요소는 '현존감', '1인칭 시점 게임', '청각적 요소', '상호작용' 으로 확인되었다. 본 연구는 양질의 VR 게임 개발을 위한 사용자 관점의 연구를 수행하고 사용자 관점의 연구를 리뷰을 통해 시도한 초기 연구라는 것에 대해 그 의의가 있다.

본 연구에서는 국내 하천에서 실측한 유사량 자료를 기초로 데이터 마이닝의 Model Tree 기법을 통해 유사량 산정 공식들을 도출하였으며, 이를 활용하여 내성천에서의 안정하도 단면을 평가하였다. 본 연구에서 도출한 유사량 공식은 국내 모래하상 전체를 대상으로 한 경우, 하폭, 유속, 수심, 경사, 하상토 중앙입경을 선택하였을때 적합도가 가장 높은 것으로 나타났다. 또한 내성천으로 자료의 범위를 한정한 경우에는 경사를 제외한 하폭, 유속, 수심, 하상토 중앙입경을 선택한 유사량 공식의 적합도가 가장 높게 나타났다. 각각의 Model Tree 공식들은 내성천 영주댐 하류 용혈 지점에서의 안정하도 단면 평가를 수행하는데 적용되었으며, 현재 내성천의 단면과 비교했을 때 향후 안정하도 단면으로의 변화를 위해 하상의 침식이 발생할 것으로 예측되었다. 또한 현재 하상보다 완만한 경사가 유지될 경우 장기적으로 평형상태에 도달할 것으로 예측되었다.

본 연구의 목적은 수학에 대한 자기효능감과 내재적 동기에 영향을 미치는 주요 요인을 추 출하고, 이 요인들 사이의 연관성 정도를 알아보는데 있다. 이를 위해 국가 수준에서 수집된 한국교육종단연구(2005) 자료를 데이터 마이닝 기법을 이용하여 분석한 결과, 수학교과에 대한 자기효능감에 영향을 미치는 주요 요인은 내재적 동기, 통제 기대, 초인지이고, 내재적 동기에 영향을 미치는 주요 요인은 자기효능감, 노력과 끈기, 숙달 접근인 것으로 나타났다. 그리고 자 기효능감과 내재적 동기는 수학 이해도에 영향을 미치는 것으로 나타났다.