• 품질경영학회지
• /
• 제52권1호
• /
• pp.77-93
• /
• 2024

Purpose: The purpose of this study is to examine machine learning use cases in manufacturing companies from a digital quality management (DQM) perspective and to analyze and present machine learning research patterns from a quality management perspective. Methods: This study was conducted based on systematic literature review methodology. A comprehensive and systematic review was conducted on manufacturing papers covering the overall quality management process from 2015 to 2022. A total of 3 research questions were established according to the goal of the study, and a total of 5 literature selection criteria were set, based on which approximately 110 research papers were selected. Based on the selected papers, machine learning research patterns according to quality management were analyzed. Results: The results of this study are as follows. Among quality management activities, it can be seen that research on the use of machine learning technology is being most actively conducted in relation to quality defect analysis. It suggests that research on the use of NN-based algorithms is taking place most actively compared to other machine learning methods across quality management activities. Lastly, this study suggests that the unique characteristics of each machine learning algorithm should be considered for efficient and effective quality management in the manufacturing industry. Conclusion: This study is significant in that it presents machine learning research trends from an industrial perspective from a digital quality management perspective and lays the foundation for presenting optimal machine learning algorithms in future quality management activities.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회/대한산업공학회 2005년도 춘계공동학술대회 발표논문
• /
• pp.599-606
• /
• 2005

Novelty detection involves identifying novel patterns. They are not usually available during training. Even if they are, the data quantity imbalance leads to a low classification accuracy when a supervised learning scheme is employed. Thus, an unsupervised learning scheme is often employed ignoring those few novel patterns. In this paper, we propose two ways to make use of the few available novel patterns. First, a scheme to determine local thresholds for the Self Organizing Map boundary is proposed. Second, a modification of the Learning Vector Quantization learning rule is proposed so that allows one to keep codebook vectors as far from novel patterns as possible. Experimental results are quite promising.

• 경영과학
• /
• 제21권1호
• /
• pp.39-55
• /
• 2004

Efficient crew scheduling for cockpit crew is important in airline industry due to operational safety and cost associated with the flight duty time. Because of complexity of regulations imposed to the cockpit crew. it is complicated to generate an efficient schedule. Schedule of cockpit crew can be generated through two steps; selecting of flight patterns. and scheduling of them to the specific time horizon. Heuristic method is developed and applied with massive data in a limited time of computation. A set of flight patterns is selected from all possible flight patterns. which are generated by composing the flight leg based on regulations. by using the set partitioning problem with objective function of oversea stay cost. The selected set of flight patterns found at the first step is allocated to 4 week crew schedule to minimize the variance of total fight time assigned to each crew. The crew schedules obtained are evaluated and compared with the ones currently used in one of major airline company.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2005년도 추계학술대회 및 정기총회
• /
• pp.409-413
• /
• 2005

The logical analysis of data(LAD) is an effective Boolean-logic based data mining tool. A critical step in analyzing data by LAD is the pattern generation stage where useful knowledge and hidden structural information in data is discovered in the form of patterns. A conventional method for pattern generation in LAD is based on term enumeration that renders the generation of higher degree patterns practically impossible. In this paper, we present a new optimization-based pattern generation methodology and propose two mathematical programming medels, a mixed 0-1 integer and linear programming(MILP) formulation and a well-studied set covering problem(SCP) formulation for the generation of optimal and heuristic patterns, respectively. With benchmark datasets, we demonstrate the effectiveness of our models by automatically generating with much ease patterns of high complexity that cannot be generated with the conventional approach.

• 한국조경학회지
• /
• 제51권2호
• /
• pp.68-80
• /
• 2023

최근 사회의 변화와 새로운 기술 등의 도입으로 공원 이용행태가 다양해지면서 공원 관리의 복잡성이 증가하고 있으며, 이에 따른 유연하고 다양한 공원관리가 요구되고 있다. 그러나 이러한 새로운 요구에 대한 현황이 어떠한지, 도시공원 운영관리 정책이 이러한 수요에 대응가능한지에 대한 논의는 미흡한 실정으로, 공원 이용행태가 어떻게 다변화되고 있는지 실증적인 연구가 필요한 시점이다. 이에 본 연구는 다양한 사람들이 개인의 경험을 작성한 블로그 데이터를 활용하여 의미네트워크 분석과 토픽분석을 통해 공간 소비 양상을 고찰하고, 이러한 공간 소비 양상이 체험경제이론에 따른 경험적 소비 특성을 보이는지 살펴보았다. 연구 결과 피크닉 세트 대여, 식음료 배달 등 소비행위가 두드러지며, 감성적 경험을 추구하는 것으로 나타났다. 또한 이는 체험경제이론에 따른 경험적 소비 특성과도 부합하였다. 이는 다변화되고 있는 공원이용 수요에 맞춰 계획 및 유지관리 방법이 보다 더 유연해지고 다양해질 필요가 있다는 것을 시사한다.

• 무역상무연구
• /
• 제49권
• /
• pp.461-490
• /
• 2011

The purpose of this study is to examine which factors are encouraging SMEs to participate in uTradeHub(focused on the uTrade search service) in terms of product characteristics and sourcing patterns. The three factors encouraging Trade e-Marketplaces are identified in this study. First, internal factors include the support of top management, mature of IT infrastructure. Second, external factors include the pressure of industry, industry competition, dependence of trading partners. Third perception factors are perceived Usefulness, perceived easy of use. The empirical analysis had the following results. First, it reveals that support of top management, mature of IT infrastructure, industry competition have significant influence upon uTrade Search Services. On the other hand, pressure of industry, dependence of trading partners, Perceived relative benefits are not significant variable of the participation in uTrade Search Services. Second, the factors affecting the participation in uTrade Search Services are differentiated in terms of product characteristics and sourcing patterns. And the support of top management, mature of IT infrastructure, Perceived relative benefits are emphasized very important factors affecting the participation of uTrade Search Services in SMEs. The industry competition is recognized as more important factor in horizontal market in which Spot sourcing just like Operating products is trading. On the other hands, the dependence of trading partners are significant factor in vertical market in which Systemic sourcing just like Manufacturing products is trading.

• 보건행정학회지
• /
• 제22권4호
• /
• pp.579-596
• /
• 2012

The purpose of the study is to examine the use of medication among adults by comparing the pattern of outpatient prescription drug use with the pattern of long term taking lifestyle drug use. Furthermore, the study investigates factors associated with the use of medication, particularity focusing on socioeconomic factors. Korea Health Panel data of 2008 was used to conduct the study analysis. By performing four different logistic regression models, the study noticed different patterns of the medication use between prescription drugs and lifestyle drugs. More specifically, the study showed that adults with lower education level tend to more frequently receive prescriptions while adults with higher education as well as income level tend to more use lifestyle drugs than their counterparts. Furthermore, other control factors such as age and gender were statistically significant for the use of both prescription and lifestyle drugs in different patterns. The study findings expect that reimbursement structure of drugs may be significantly associated with the different patterns and accordingly the accessability of medicine in particularly vulnerable population. Therefore, these policy factors should be considered in future study to more comprehensively understand about the diverse patterns in the medication use.

• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.559-563
• /
• 2015

Identification of energy use patterns in buildings has a great opportunity for energy saving. To find what energy use patterns exist, clustering analysis has been commonly used such as K-means and hierarchical clustering method. In case of high dimensional data such as energy use time-series, data reduction should be considered to avoid the curse of dimensionality. Principle Component Analysis, Autocorrelation Function, Discrete Fourier Transform and Discrete Wavelet Transform have been widely used to map the original data into the lower dimensional spaces. However, there still remains an ongoing issue since the performance of clustering analysis is dependent on data type, purpose and application. Therefore, we need to understand which data reduction techniques are suitable for energy use management. This research aims find the best clustering method using energy use data obtained from Seoul National University campus. The results of this research show that most experiments with data reduction techniques have a better performance. Also, the results obtained helps facility managers optimally control energy systems such as HVAC to reduce energy use in buildings.

• 한국관광식음료학회지:관광식음료경영연구
• /
• 제13권1호
• /
• pp.111-118
• /
• 2002

The purpose of this study was to investigate the stress levels and the dietary patterns of 390 male and female University students in Seoul and to analyze the correlation between the two. Informations of the subjects were obtained by questionnaire. As a result of this research study, male students had such bad dietary patterns as their stress increased(P<.05). Female students were more affected in dietary patterns by stress level and both male and female students exhibited a tendency to be in a higher state of intake as their stress level increased.

• 가정과삶의질연구
• /
• 제14권3호
• /
• pp.91-108
• /
• 1996

The major purpose of this study was to find the influencing factors in explaining search patterns of product attributes in formation and to find if significant differences exist in search outcomes by search patterns. The data for this study were collected in a survey and the final sample consisted of 327 respondents purchased refrigerator 340 purchased bed. The important findings of this study are as follows: First the variables related to search cost-benefit play an important role in identifying search patterns for each of product attributers. The findings of this study provide some implications regarding consumer education programs and consumer information providing policies.