• 한국콘텐츠학회논문지
• /
• 제18권10호
• /
• pp.229-235
• /
• 2018

본 연구의 목적은 효율적이고 효과적인 정책 발굴 과정에서 빅데이터의 활용이 점차 중요해지는 현실에서 지방자치단체의 정책 이슈 발굴에 빅데이터 분석을 활용하는 방안을 제시하는 데 있다. 이를 위하여 본 연구에서는 수원시를 대상으로 지난 3년간의 수원시 약 18만 건의 기사를 분석하여 정책 이슈를 발굴하였으며, 이를 IPA분석을 통해 정책의 우선순위를 평가하였다. 본 연구의 분석 결과는 신문 기사를 통한 반정형 빅데이터의 분석으로 전국의 주요 이슈와는 차별화된 지방자치단체의 차별화된 정책 이슈를 도출하는데 효과적임을 보였으며, 특히 도출된 정책 이슈들이 대부분 그 우선순위가 높은 것으로 평가되었다. 이처럼 본 연구에서 제시한 빅데이터 분석을 통한 정책 이슈 발굴의 방법론은 지방자치단체가 효율적인 정책 이슈를 도출하고 민의를 효과적으로 파악할 수 있음을 의미한다. 또한, 본 연구에서 제시한 방법론은 지방자치단체의 온라인 민원 자료, 주민 SNS 등 다양한 반정형, 비정형 빅데이터의 분석을 통한 정책 이슈 발굴에 적용이 가능할 것으로 기대된다.

• 품질경영학회지
• /
• 제44권2호
• /
• pp.389-408
• /
• 2016

Purpose: This study was designed to analyze the behavioral change of knowledge structures and the trends of research topics in the quality management field. Methods: The network structure and knowledge structure of the words were visualized in map form using co-word analysis, cluster analysis and strategic diagram. Results: Summarizing the research results obtained in this study are as follows. First, the word network derived from co-occurrence matrix had 106 nodes and 5,314 links and its density was analyzed to 0.95. Average betweenness centrality of word network was 2.37. In addition, average closeness centrality and average eigenvector centrality of word network were 0.01. Second, by applying optimal criteria of cluster decision and K-means algorithm to word co-occurrence matrix, 106 words were grouped into seven clusters such as standard & efficiency, product design, reliability, control chart, quality model, 6 sigma, and service quality. Conclusion: According to the results of strategic diagram analysis over time, the traditional research topics of quality management field related to reliability, 6 sigma, control chart topics in the third quadrant were revealed to be declined for their study importance. Research topics related to product design and customer satisfaction were found to be an important research topic over analysis periods. Research topic related to management innovation was emerging state and the scope of research topics related to process model was extended to research topics with system performance. Research topic related to service quality located in the first quadrant was analyzed as the key research topic.

• 지능정보연구
• /
• 제21권1호
• /
• pp.119-142
• /
• 2015

사용자의 취향과 선호도를 고려하여 정보를 제공하는 추천 시스템의 중요성이 높아졌다. 이를 위해 다양한 기법들이 제안되었는데, 비교적 도메인의 제약이 적은 협업 필터링이 널리 사용되고 있다. 협업 필터링의 한 종류인 모델 기반 협업 필터링은 기계학습이나 데이터 마이닝 모델을 협업 필터링에 접목한 방법이다. 이는 희박성 문제와 확장성 문제 등의 협업 필터링의 근본적인 한계를 개선하지만, 모델 생성 비용이 높고 성능/확장성 트레이드오프가 발생한다는 한계점을 갖는다. 성능/확장성 트레이드오프는 희박성 문제의 일종인 적용범위 감소 문제를 발생시킨다. 또한, 높은 모델 생성 비용은 도메인 환경 변화의 누적으로 인한 성능 불안정의 원인이 된다. 본 연구에서는 이 문제를 해결하기 위해, 군집화 기반 협업 필터링에 마르코프 전이확률모델과 퍼지 군집화의 개념을 접목하여, 적용범위 감소 문제와 성능 불안정성 문제를 해결한 예측적 군집화 기반 협업 필터링 기법을 제안한다. 이 기법은 첫째, 사용자 기호(Preference)의 변화를 추적하여 정적인 모델과 동적인 사용자간의 괴리 해소를 통해 성능 불안정 문제를 개선한다. 둘째, 전이확률과 군집 소속 확률에 기반한 적용범위 확장으로 적용범위 감소 문제를 개선한다. 제안하는 기법의 검증은 각각 성능 불안정성 문제와 확장성/성능 트레이드오프 문제에 대한 강건성(robustness)시험을 통해 이뤄졌다. 제안하는 기법은 기존 기법들에 비해 성능의 향상 폭은 미미하다. 또한 데이터의 변동 정도를 나타내는 지표인 표준 편차의 측면에서도 의미 있는 개선을 보이지 못하였다. 하지만, 성능의 변동 폭을 나타내는 범위의 측면에서는 기존 기법들에 비해 개선을 보였다. 첫 번째 실험에서는 모델 생성 전후의 성능 변동폭에서 51.31%의 개선을, 두 번째 실험에서는 군집 수 변화에 따른 성능 변동폭에서 36.05%의 개선을 보였다. 이는 제안하는 기법이 성능의 향상을 보여주지는 못하지만, 성능 안정성의 측면에서는 기존의 기법들을 개선하고 있음을 의미한다.

• 콘크리트학회논문집
• /
• 제29권3호
• /
• pp.267-273
• /
• 2017

최근 콘크리트 구조물의 유지보수 문제가 대두되면서 구조물에 발생하는 균열을 스스로 치유하는 자기치유 기술이 활발히 연구되고 있다. 현재 자기치유 콘크리트의 치유 성능 평가에 투수시험이 널리 사용되지만, 이와 관련된 표준화된 방법이 없어 시험결과의 비교에 어려움이 있다. 또한 콘크리트의 자기치유 성능은 초기 균열폭에 큰 영향을 받는데, 콘크리트의 균열폭 측정을 위한 표준화된 방법도 없는 실정이다. 따라서 본 연구에서는 정수위 투수시험 장치를 이용하여 수두차와 균열폭이 유출수량에 미치는 영향을 분석하였다. 또한 투수 실험 결과의 회귀 분석을 통해 유출수량과 초기 균열폭의 상관관계식을 제안하였으며, 제안된 식을 이용하여 예측한 모르타르 시편의 균열폭이 광학현미경을 이용하여 측정한 실제 균열폭과 잘 일치하는 결과를 얻었다.

• 대한인간공학회지
• /
• 제29권3호
• /
• pp.365-373
• /
• 2010

Many studies on safety issues of human-machine interaction are being conducted, especially taking emergency situations into consideration. In light of this view, the importance of objective and reliable measurement of users' reactions under emergency situations is becoming more important than ever in reflecting such issues in the design of everyday things. However, despite the need to consider the human-machine interactions and human performances at the design stage, there were few studies which considered human performances and behaviors under emergency situations. This study is about an evaluation method and design guide to include such human performances under emergency situations during human-machine interactions. This is achieved through an experiment where operators are instructed to press the emergency button at an experimentally designed location under a random emergency situation. By analyzing the results in a human factors perspective, the response time and the accuracy of the operators' behaviors are explained. Analysis revealed that in designing the center fascia for automobiles, there is a tradeoff between response time and accuracy, and the optimal size of buttons differ in each part of the center fascia. This method is expected to be applicable to industrial situations to derive optimal position for emergency buttons.

• 한국IT서비스학회지
• /
• 제21권4호
• /
• pp.91-103
• /
• 2022

This study proposes a model for predicting contracted power using electric power data collected in real time from convenience stores nationwide. By optimizing the prediction model using machine learning, it will be possible to predict the contracted power required to renew the contract of the existing convenience store. Contracted power is predicted through the XGBoost regression model. For the learning of XGBoost model, the electric power data collected for 16 months through a real-time monitoring system for convenience stores nationwide were used. The hyperparameters of the XGBoost model were tuned using the GridesearchCV, and the main features of the prediction model were identified using the xgb.importance function. In addition, it was also confirmed whether the preprocessing method of missing values and outliers affects the prediction of reduced power. As a result of hyperparameter tuning, an optimal model with improved predictive performance was obtained. It was found that the features of power.2020.09, power.2021.02, area, and operating time had an effect on the prediction of contracted power. As a result of the analysis, it was found that the preprocessing policy of missing values and outliers did not affect the prediction result. The proposed XGBoost regression model showed high predictive performance for contract power. Even if the preprocessing method for missing values and outliers was changed, there was no significant difference in the prediction results through hyperparameters tuning.

• 한국콘텐츠학회논문지
• /
• 제16권10호
• /
• pp.664-675
• /
• 2016

본 연구의 목적은 간호대학생의 초등학교 현장실습에 관한 직무 및 과업을 DACUM 기법을 활용하여 분석하고자 하였다. J도에 소재한 일 간호대학의 보건교사교직과정을 이수하고, 초등학교 현장실습과정을 수행한 간호학과 4학년을 대상으로 DACUM 워크숍을 실시하여 임무, 과업, 과업별 중요도, 난이도, 빈도 등의 직무내용을 분석하였고, 직무에 요구되는 지식, 기술, 태도, 도구, 장래전망과 특성을 도출하였다. 도출된 직무분석 내용은 J시, I시, G시 등의 학교현장전문가 7인과 교육학전공 교수 2인으로부터 내용타당도를 검증받았고, 이를 토대로 본 연구자가 DACUM 차트를 개발하였다. DACUM 차트는 6개 임무와 24개 과업으로 구성되었고, 직무수행에 필요한 지식, 기술, 태도 등이 도출되었다. 연구의 결과로는 초등학교 학교현장실습의 임무 중 건강관리는 가장 중요도가 높은 과업으로 산출되었고, 교수학습능력과 문서작업능력이 실습을 위한 기본적인 기술로 제시되었다. 학교현장에서의 보건교사의 전문성과 역할에 대한 중요도는 증가되므로 보건교육 향상 프로그램 개발을 위한 교육기관의 제도적 노력과 교육환경 개선 등의 뒷받침이 필요할 것으로 사료된다.

• 농촌계획
• /
• 제22권1호
• /
• pp.101-111
• /
• 2016

The purpose of this study is to investigate the roadside agricultural product shops located in Miryang city, and to find out the current situation on how people rate the importance and satisfaction levels of various aspects through surveys on sellers and consumers. With this information, the main problems and possible solutions are analyzed with the Important Performance Analysis(IPA) method. First, building parking spaces for customers should be prioritized to improve safety. Because many roadside shops for agricultural products are located alongside two-lane roads, sufficient parking spaces are needed for the consumers' safety. Second, to enhance the rural landscape, consumers express that improving store quality and integrating more with the environment are important. Store owners should take more care in maintaining store quality so that customers do not experience inconvenience while shopping. Futhermore, institutional guidelines and standards must be implemented to allow for a more harmonious relationship between these shops and the environment. Third, both sellers and consumers think that taste, price, and freshness are important aspects of roadside agricultural product shops. However, while sellers and consumers both agree that the price is the most important factor, there is a discrepancy between these two groups regarding the satisfactory price level. The sellers do not agree that their products are being sold at the fair price. This can be interpreted as sellers believe that the prices are set too low. Because pricing is important aspect and also a very delicate issue, mid to long term consideration and study will be needed to improve roadside shops for agricultural products in the future.

• 수산경영론집
• /
• 제52권1호
• /
• pp.65-82
• /
• 2021

This study utilizes the IPA (Importance-Performance Analysis) method to assess the importance, possibility, and urgency of using blockchain technology for fisheries sectors and the related policies. Based on a field survey targeting experts and stakeholders in the fisheries and blockchain technology sectors, the following major results and corresponding implications are drawn. First of all, the respondents of our survey have an outlook that the introduction and utilization of blockchain will be required in four major parts. These parts include i) the seafood' information system managed by the government or public institutions, ii) traceability and certification process for domestic and foreign seafoods, iii) meeting the need of seafood safety from consumers, and iv) taking prompt actions to seafood safety related accidents. Next, the seafood information system managed by the government or public institutions has been limited in maintaining information consistency and continuity once the fisheries ministries and departments are integrated, closed or partially transferred. Thus, it is assessed that the technology will be able to improve consistency and continuity of the seafood information in case of applying blockchain to the seafood information management system. This result that blockchain is necessary for the seafood information system have a significant implication in Korea's seafood management which has been independently controlled until now. Lastly, the application of blockchain to seafood traceability and certification systems has the most well-known cases through international and domestic pilot projects, and the results of our survey reflect this reality. Our results contribute to showing an additonal characteristics of blockchain in the fisheries sector, resulting in the possiblity that blockchain can be used for taking swift steps in the event of seafood safety accidents and meeting the need of seafood consumers for safety.

• 품질경영학회지
• /
• 제50권1호
• /
• pp.77-89
• /
• 2022

Purpose: In order to improve the audit quality of a company, an in-depth analysis is required to categorize the audit report in the form of a text document containing the details of the external audit. This study introduces a systematic methodology to extract keywords for each group that determines the differences between groups such as 'audit plan' and 'interim audit' using audit reports collected in the form of text documents. Methods: The first step of the proposed methodology is to preprocess the document through text mining. In the second step, the documents are classified into groups using machine learning techniques and based on this, important vocabularies that have a dominant influence on the performance of classification are extracted. In the third step, the association rules for each group's documents are found. In the last step, the final keywords for each group representing the characteristics of each group are extracted by comparing the important vocabulary for classification with the important vocabulary representing the association rules of each group. Results: This study quantitatively calculates the importance value of the vocabulary used in the audit report based on machine learning rather than the qualitative research method such as the existing literature search, expert evaluation, and Delphi technique. From the case study of this study, it was found that the extracted keywords describe the characteristics of each group well. Conclusion: This study is meaningful in that it has laid the foundation for quantitatively conducting follow-up studies related to key vocabulary in each stage of auditing.