• Journal of Korea Water Resources Association
• /
• 제52권4호
• /
• pp.279-289
• /
• 2019

Unlike other natural disasters, drought is a reoccurring and region-wide phenomenon after being triggered by a prolonged precipitation deficiency. Considering that remote sensing products provide consistent temporal and spatial measurements of precipitation, this study developed a remote sensing data-based drought outlook model. The meteorological drought was defined by the Standardized Precipitation Index (SPI) achieved from PERSIANN_CDR, TRMM 3B42 and GPM IMERG images. Bayesian networks were employed in this study to combine the historical drought information and dynamical prediction products in advance of drought outlook. Drought outlook was determined through a decision-making model considering the current drought condition and forecasted condition from the Bayesian networks. Drought outlook condition was classified by four states such as no drought, drought occurrence, drought persistence, and drought removal. The receiver operating characteristics (ROC) curve analysis were employed to measure the relative outlook performance with the dynamical prediction production, Multi-Model Ensemble (MME). The ROC analysis indicated that the proposed outlook model showed better performance than the MME, especially for drought occurrence and persistence of 2- and 3-month outlook.

• Journal of Intelligence and Information Systems
• /
• 제15권3호
• /
• pp.151-165
• /
• 2009

Fuzzy neural network is an integrated model of artificial neural network and fuzzy system and it has been successfully applied in control and forecasting area. Recently ANFIS(Adaptive Network-based Fuzzy Inference System) has been noticed widely among various fuzzy neural network models because of its outstanding accuracy of control and forecasting area. We design a new classification model based on ANFIS and evaluate it in terms of classification accuracy. We identified ANFIS-based classification model has higher classification accuracy compared to existing classification model, C5.0 decision tree model by comparing their experimental results.

• Journal of Korean Society of Transportation
• /
• 제35권3호
• /
• pp.183-196
• /
• 2017

In this study, policy evaluation scheme was established to encourage the efficient implementation of EcoMobility which has been expanding gradually all around the world. A total of eight evaluation goals and 22 evaluation items are reviewed and suggested based on the three major evaluation categories of "Basic elements for EcoMobility", "Land use and transport system for EcoMobility", and "Implications and impact of EcoMobility". The results of this study are as follows: the result of AHP analysis which reflects only the hierarchical structure shows a high priority in "Elements for EcoMobility promotion", "Eco-fiendly transport infrastructure", and "Safety in transport". While in result of ANP which considered the elements' dependencies, "Eco-fiendly transport Services", "Welfare in transport", and "Environment by transport" have high weights and importances. In conclusion, this study would be useful to make reasonable judgment based on the analysis results of the two techniques in order to ensure reliability in evaluation of EcoMobility policy. Furthermore we have confirmed appropriate evaluation technique between AHP and ANP which is better to reflect the features of EcoMobility.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2013년도 추계학술발표대회
• /
• pp.1042-1045
• /
• 2013

정보기술의 발달로 전 세계에서 발생하는 사건 사고들은 실시간으로 확인 가능하며 정보의 중요성은 더욱 더 중요해지고 있다. 이런 사회 현상에 맞춰 인적자원 솔루션에서도 빅 데이터 분석 기술을 이용하여 인적자원 의사결정에 도움을 주는 기술이 필요하게 되었다. 따라서 본 논문에서는 빅 데이터 분석 기술을 이용하여 인사채용과 관련된 데이터들을 추출하고 분석하여 구직자의 적성과 능력에 맞는 직업을 예측하는 시스템을 설계하였다. 구직자 및 이직을 원하고 있는 사람들이 소셜 네트워크 서비스를 이용하면서 사용하고 있는 특정 단어와 특정 단어의 언급 빈도의 데이터를 추출하고 추출 된 데이터는 통계를 내어 데이터의 특성에 맞게 분류하여 분류된 데이터는 연관된 속성에 의해 그룹화 한다. 그룹화 된 정보를 분석하여 구직자의 적성과 능력을 고려한 직업을 예측하는 정보로 도출하여 직업을 추천 할 수 있는 예측 시스템을 설계하였다.

• Journal of the Korean association of regional geographers
• /
• 제13권1호
• /
• pp.54-67
• /
• 2007

This paper aims to explore the characteristics of regional embeddedness of Korean firms in Daren City, China, with special reference to management practices. To achieve this goal, I attempt to analyze the type and structure of the firm, the structure of decision-making, labor practices, and the inter-organizational networks with the government, trade associations and the business supporting agencies. The major purpose of the investment in Daren by Korean firms is to penetrate and expand the local market. In line with this, the structure of decision-making by Korean firms tends to become increasingly autonomous, especially in terms of employment and marketing. However, the decision-making related to finance and accounting tends to be still highly controlled upon the headquarter in Korea. In addition, it is shown that Korean firms make a great effort to sustain the cooperative relationships with the local society and the local government.

• Journal of the Korean Society for information Management
• /
• 제30권1호
• /
• pp.285-302
• /
• 2013

This study identified topic shifts and patterns over time by analyzing an enormous amount of Twitter data whose characteristics are high accessibility and briefness. First, we extracted keywords for a certain product and used them for representing the topic network allows for intuitive understanding of keywords associated with topics by nodes and edges by co-word analysis. We conducted temporal analysis of term co-occurrence as well as topic modeling to examine the results of network analysis. In addition, the results of comparing topic shifts on Twitter with the corresponding retrieval results from newspapers confirm that Twitter makes immediate responses to news media and spreads the negative issues out quickly. Our findings may suggest that companies utilize the proposed technique to identify public's negative opinions as quickly as possible and to apply for the timely decision making and effective responses to their customers.

• Journal of the Korea Society of Computer and Information
• /
• 제26권12호
• /
• pp.85-97
• /
• 2021

In this paper, in order to support rapid and effective decision-making and response in disaster situations, we identified the author's organization of academic research papers and conducted a collaborative relationship analysis study based on this. For this purpose, 2,308 papers in 69 Korean academic journals classified by disaster and safety type were selected for analysis and experimental data were constructed based on the Korea Science Citation Database (KSCD) and institutional identification data provided by KISTI. Collaborative relationship analysis was conducted for each of the four units (Institution, Institution type, Institution region and University department type). First, statistical status such as frequency of appearance was compared, and basic properties and main centrality index of each co-occurrence network were calculated and analyzed using Social Network Analysis Method. In addition, a visualization map was created and presented for each network so that the collaborative relationship could be viewed and understood as a whole. The results of this study are expected to contribute to the search activities of institutions and cooperative groups that support effective disaster response and to lay the foundation for the information service system.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• 제13권6호
• /
• pp.54-60
• /
• 2014

In industry, several casting process are widely used to manufacture complex and accurate blank part of hard materials such as aluminum, casting steels, bronze and magnesium alloys which are difficult to manufacture in a blank shape. Even if the casting process does not high accuracy superior surface characteristics other machining process, the casting process is widely used in manufacturing blank part. Furthermore, it is difficult to select appropriate casting process a part among several casting process. for effective selection different process, a careful decision given casting application is necessary. An appropriate casting for a given material and shape condition must be selected for novice engineers in industry. In this paper, an expert system based on an analytic network process(ANP) is suggested for best selection of casting considering a prior interdependency effect among various factors such as material, geometry, process capability, economy and equipment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2009년도 추계학술발표대회
• /
• pp.423-424
• /
• 2009

미래의 전쟁양상은 네트워크 개념을 바탕으로 정 첩보의 수집 분석 전파의 신속/정확성 및 대용량 정보의 효율적인 처리가 필수적이다. 이러한 전장 운영개념을 만족시킬 수 있는 C4I중심 정보우위의 시스템 복합체계를 구현함으로써, 군사정보통합처리계는 지휘관에게 신속 정확한 정보를 제공하고 첩보수집부터 의사결정 및 행동에 이르기까지 결정루프를 단축시켜 성공적 작전이 보장되게 한다. 본 논문에서는 이러한 필요성에 의해 향후 한국군 C4I의 정보우위를 발휘하기 위해 현재 추진 중에 있는 군사정보통합처리체계의 개발동향 및 발전방향을 모색해 보기로 하겠다.

• Journal of the Korean Data and Information Science Society
• /
• 제25권2호
• /
• pp.373-384
• /
• 2014

Data mining is to clarify pattern or correlation of mass data of complicated structure and to predict the diverse outcomes. This technique is used in the fields of finance, telecommunication, circulation, medicine and so on. In this paper, we selected risk factors of respiratory diseases in the field of medicine. The data we used was divided into respiratory diseases group and health group from the Gyeongsangbuk-do database of Community Health Survey conducted in 2012. In order to select major risk factors, we applied data mining techniques such as neural network, logistic regression, Bayesian network, C5.0 and CART. We divided total data into training and testing data, and applied model which was designed by training data to testing data. By the comparison of prediction accuracy, CART was identified as best model. Depression, smoking and stress were proved as the major risk factors of respiratory disease.