• 산업경영시스템학회지
• /
• 제46권3호
• /
• pp.109-122
• /
• 2023

As platforms become primary decision making tools, platforms for decision have been introduced to improve quality of decision results. Because, decision platforms applied augmented decision-making process which uses experiences and feedback of users. This process creates a variety of alternatives tailored for users' abilities and characteristics. However, platform users choose alternatives before considering significant quality factors based on securing decision quality. In real world, platform managers use an algorithm that distorts appropriate alternatives for their commercial benefits. For improving quality of decision-making, preceding researches approach trying to increase rational decision -making ability based on experiences and feedback. In order to overcome bounded rationality, users interact with the machine to approach the optional situation. Differentiated from previous studies, our study focused more on characteristics of users while they use decision platforms. This study investigated the impact of quality factors on decision-making using platforms, the dimensions of systematic factors and user characteristics. Systematic factors such as platform reliability, data quality, and user characteristics such as user abilities and biases were selected, and measuring variables which trust, satisfaction, and loyalty of decision platforms were selected. Based on these quality factors, a structural equation research model was created. A survey was conducted with 391 participants using a 7-point Likert scale. The hypothesis that quality factors affect trust was proved to be valid through path analysis of the structural equation model. The key findings indicate that platform reliability, data quality, user abilities, and biases affect the trust, satisfaction and loyalty. Among the quality factors, group bias of users affects significantly trust of decision platforms. We suggest that quality factors of decision platform consist of experience-based and feedback-based decision-making with the platform's network effect. Through this study, the theories of decision-making are empirically tested and the academic scope of platform-based decision-making has been further developed.

• 품질경영학회지
• /
• 제27권2호
• /
• pp.237-250
• /
• 1999

Response surface analysis has been a popular tool conducted by engineers in many processes. In this paper, response surface function, named partial least squares response surface function is proposed. Partial least squares response surface function is a function of partial least squares components and the response surface modeling is used in either a first-order or a second-order model. Also, this approach will have the engineers be able to do the response surface modeling and the process optimization even when the number of experimental runs is less than the number of model parameters. This idea is applied to the nondesign data and an application of partial least squares response surface function to the process optimization is considered.

• 지식경영연구
• /
• 제3권1호
• /
• pp.1-18
• /
• 2002

Many organizations implement knowledge management initiates by developing knowledge management systems. This study aims at investigating knowledge sharing behaviors in a knowledge management system and identifying factors affecting such behaviors. To do this, we defined knowledge sharing behaviors in a knowledge management system as registration and view of knowledge at a system. Based on this definition, we established a research model by identifying seven factors affecting both behaviors as independent variables: Learning orientation, Pressure to share knowledge, Top management support, Reward for knowledge sharing, Level of experience in IT, System quality, and Knowledge quality. The 14 hypotheses derived from a research model were tested by a correlation analysis and a multiple regression analysis with data from 165 respondents of the 21 organizations which implemented knowledge management initiatives. As results, both of knowledge registration and knowledge review were strongly affected by the learning-orientedness of an organization. Finally, we discussed results and limitations of this study.

• 산업경영시스템학회지
• /
• 제45권4호
• /
• pp.86-98
• /
• 2022

Recently, many studies have been conducted to improve quality by applying machine learning models to semiconductor manufacturing process data. However, in the semiconductor manufacturing process, the ratio of good products is much higher than that of defective products, so the problem of data imbalance is serious in terms of machine learning. In addition, since the number of features of data used in machine learning is very large, it is very important to perform machine learning by extracting only important features from among them to increase accuracy and utilization. This study proposes an anomaly detection methodology that can learn excellently despite data imbalance and high-dimensional characteristics of semiconductor process data. The anomaly detection methodology applies the LIME algorithm after applying the SMOTE method and the RFECV method. The proposed methodology analyzes the classification result of the anomaly classification model, detects the cause of the anomaly, and derives a semiconductor process requiring action. The proposed methodology confirmed applicability and feasibility through application of cases.

• 품질경영학회지
• /
• 제26권1호
• /
• pp.48-60
• /
• 1998

This paper proposes a fourth generation index $C_{psk}$, constructed from $C_{psk}$, by introducing the factor｜$\mu$-T｜ in the numerator as an extra penalty for the departure of the process mean from the preassigned target value T. The motivation behind the introduction of $C_{psk}$ is that when $T\neqM$ process shifts away from target are evaluated without respect to direction. All indices that are now in use assume normally distributed data, and any use of the indices on non-normal data results in inaccurate capability measurements. In this paper, a new process capability index $C_{psk}$ is introduced for non-normal process. The Pearson curve and the Johnson curve are selected for capability index calculation and data modeling the normal-based index $C_{psk}$ is used as the model for non-normal process. A significant result of this research find that the ranking of the six indices, $C_{p}$, $C_{pk}$, $C_{pm}$, ${C^*}_{psk}$, $C_{pmk}$, $C_{psk}$in terms of sensitivity to departure of the process median from the target value from the most sensitive one up to the least sensitive are $C_{psk}$, $C_{pmk}$, ${C^*}_{psk}$,$C_{pm}$, $C_{pk}$, $C_{p}$.

• 한국정밀공학회지
• /
• 제13권12호
• /
• pp.63-69
• /
• 1996

As the significance of quality in the sense of customer satisfaction is growing, the management of quality becomes one of the main interests in the manufacturing systems research. This paper presents the concept of quality-driven CIM(Computer Integrated Manufacturing) system which is composed of a business process domain and a quality domain. In the business process domain, business functions are integrated by conventional design and manufacturing databases on the one hand, and an integrated quality system is interlinked to them via several quality modules on the other hand. Quality information model connects the business process domain with the quality domain where various types of quality data are stored in the form of quality database. This framework helps a manufacturing enterprise to implement the quality-driven CIM system to achieve its final objective "customer satisfaction".ion".uot;.

• 대한산업공학회지
• /
• 제40권4호
• /
• pp.404-414
• /
• 2014

Yield prediction is important to manage semiconductor quality. Many researches with machine learning algorithms such as SVM (support vector machine) are conducted to predict yield precisely. However, yield prediction using SVM is hard because extremely imbalanced and big data are generated by final test procedure in semiconductor manufacturing process. Using SVM algorithm with imbalanced data sometimes cause unnecessary support vectors from major class because of unselected support vectors from minor class. So, decision boundary at target class can be overwhelmed by effect of observations in major class. For this reason, we propose a under-sampling method with minor class based SVM (MCSVM) which overcomes the limitations of ordinary SVM algorithm. MCSVM constructs the model that fixes some of data from minor class as support vectors, and they can be good samples representing the nature of target class. Several experimental studies with using the data sets from UCI and real manufacturing process represent that our proposed method performs better than existing sampling methods.

• 한국건설관리학회논문집
• /
• 제14권5호
• /
• pp.131-143
• /
• 2013

BIM 지침을 통해 기본적인 모델링 기준을 제공하고 있지만, BIM 모델링 업무를 수행하는 참여자 별로 기준이 상이하고 BIM 모델의 활용목적에 따른 적용기준이 다르기 때문에 BIM 적용 지침에 대한 이행여부의 평가는 BIM 모델의 활용목적에 따른 품질을 만족시키기 위한 중요한 절차이다. 하지만 지침에 따라 작성된 BIM 모델의 검토항목 및 방법이 제시되지 않고 있다. 본 연구는 BIM 모델의 완성도를 높이기 위해 국내 BIM 지침의 BIM 기반 품질검토 항목을 도출하고 자동 품질검토 수행을 위한 룰 정의서를 제시한다. 먼저 국내 BIM 지침을 분석하여 품질검토 항목을 도출하고 플로우차트 및 의사코드를 활용한 구조화를 통해 룰 정의서를 작성한다. 작성된 룰 정의서를 기반으로 사례적용을 실시하여 자동 품질검토 과정을 수행한다. 본 연구는 3차원의 방대한 데이터를 포함한 BIM 모델의 설계품질과 완성도를 높이는데 기여할 것이다. 향후 활용목적에 따른 BIM 지침의 개발이 필수적으로 이루어져야 하며 BIM모델의 품질검토를 위한 구체적인 절차나 기준이 제공되어야 할 것이다.

• 품질경영학회지
• /
• 제50권3호
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2001년도 추계학술대회 논문집
• /
• pp.50-54
• /
• 2001

Information systems development entails planning, analysis, design and construction phases. The analysis phase identifying user requirements is the most important of these phases. Since unidentified defects in the early phase causes increased work and costs as development proceeds, the quality of analysis results affects the quality of the resultant system. Major tasks in the analysis phase are data modeling and process modeling. Research on building a knowledge-based system for data modeling have been conducted much, however, not sufficiently for process modeling. As a system environment with high user interaction increases, research on process modeling methods and knowledge- based systems considering such environment are required. In this research, a process modeling framework for information systems with high user interaction is suggested and a knowledge-based system for supporting the suggested framework is implemented. A proposed model consists of the following tasks: event analysis, process analysis, and event/process interaction analysis. Event analysis identifies business events and their responses. Process analysis break down the processes of an enterprise into progressively increasing details. Decomposition begins at the function level and ends when the elementary process level is reached. Event/process interaction analysis verifies the results of process analysis and event analysis. A knowledge-based system for supporting a proposed process modeling framework is implemented in a web-based environment.