• Economic and Environmental Geology
• /
• v.31 no.1
• /
• pp.69-84
• /
• 1998

A geochemical study was carried out to define how marine shore sediments are related to their terrestrial source rocks in the region of Taean and Byunsan Peninsula, western Korea. The lithology of the coastal part of the study area is composed of Pre-Cambrian granite gneiss, schist, Jurassic terrestrial sedimentary rocks, and Cretaceous plutonic intrusives. Shore sediments are transported from three drainage tributaries. The sediments consist of quatrz with clay minerals, such as illite, kaolinite, smectite, chlorite. Heavy minerals include hematite, ilmenite, rare amount of zircon and apatite. Compared to those in coastal rocks, amount of heavy minerals in the sediments is considerably low. The low content of heavy minerals is thought to be attributed to the heavy mineral detainment in the river beds and influences of tidal currents which cause heavy minerals to accumulate in specific spots. Chemical composition of the major and trace elements, trace elements, and REE chondrite normalized pattern suggest that shore sediments transported from the corresponding drainage tributary show close mineralogical and geochemical relationships with the source rocks distributed in the Taean and Byunsan Peninsula.

• Journal of Distribution Science
• /
• v.15 no.4
• /
• pp.33-40
• /
• 2017

Purpose - This study aims to examine the analysis of pattern on Arab countries consumers' preferences of the Korean Contents using social media, Facebook since Korean entertainment contents have been distributed in the global marketplace. Then we focus on developing Predictive model using a Data Mining Technique. Research design, data and methodology - In order to understand preference growth of Korean contents in Arabic countries, we- collected data from two popular Facebook pages: 'Korean movies and drama' and 'K-pop'. Then, we adopted a data-driven approach based on Data Mining techniques. Results - It is obvious that the number of likes for K-pop will increase for all North African and Middle Eastern countries, however concerning Korean Movies and Drama except Tunisia it is decreasing for Algeria, Egypt and Morocco. Also, concerning Saudi Arabia and United Arab Emirates, the number of likes will decrease for Korean Movies and Drama which is not the case for Iraq. Conclusions - It is noted in this study that K-contents such as drama, movie and music are sometimes a gateway to a wider interest in Korean culture, food and brands. Moreover, this study gives significant implications for developing predictive model to forecast Korean contents' consumption and preferences.

• Computers and Concrete
• /
• v.17 no.5
• /
• pp.639-653
• /
• 2016

The present article discusses the effect of the ratio of bridge surface to total shear surface, number of bridge areas and normal stress on the failure behavior of the planar non-persistent open joints. Totally, 38 models were prepared using plaster and dimensions of $15cm{\times}15cm{\times}15cm$. The bridge area occupied $45cm^2$, $90cm^2$ and $135cm^2$ out of the shear surface. The number of rock bridges increase in fixed area. Two similar samples were prepared on every variation in the rock bridges and tested for direct shear strength under two high and low normal loads. The results indicated that the failure pattern and the failure mechanism is mostly influenced by the ratio of bridge surface to total shear surface and normal stress so that the tensile failure mode change to shear failure mode by increasing in the value of introduced parameters. Furthermore, the shear strength and shear stiffness are closely related to the ratio of bridge surface to total shear surface, number of bridge areas and normal stress.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.29 no.4
• /
• pp.41-60
• /
• 2004

A stream data is a data set that is accumulated to the data storage from a data source over time continuously. The size of this data set, in many cases. becomes increasingly large over time. To mine information from this massive data. it takes much resource such as storage, memory and time. These unique characteristics of the stream data make it difficult and expensive to use this large size data accumulated over time. Otherwise. if we use only recent or part of a whole data to mine information or pattern. there can be loss of information. which may be useful. To avoid this problem. we suggest a method that efficiently accumulates information. in the form of rule sets. over time. It takes much smaller storage compared to traditional mining methods. These accumulated rule sets are used as prediction models in the future. Based on theories of ensemble approaches. combination of many prediction models. in the form of systematically merged rule sets in this study. is better than one prediction model in performance. This study uses a customer data set that predicts buying power of customers based on their information. This study tests the performance of the suggested method with the data set alone with general prediction methods and compares performances of them.

• The Journal of Bigdata
• /
• v.2 no.2
• /
• pp.105-114
• /
• 2017

Today, many services are supported on the web sites. Analysis of usage patterns of web site visitors is very important to optimize the use and efficiency of the web sites. In this study, analysis of usage patterns and comparative analysis of user groups were conducted by analyzing web access log provided by BPI Challenge 2016. This data provides access logs to the web site in the IT system of a Dutch Employee Insurance Agency (UWV). The customer information, and the click data describing the customers' behavior when using the agency's web site. In this study, we use process mining techniques to analyze the usage patterns of customers and the characteristics of customer groups, and ultimately improve the service quality of customers using web services.

• Journal of Internet Computing and Services
• /
• v.18 no.1
• /
• pp.121-129
• /
• 2017

Demand forecasting is one of the most critical tasks in defense logistics, because the failure of the task can bring about a huge waste of budget. Up to date, ROK-MND(Republic of Korea - Ministry of National Defense) has analyzed past component consumption data with time-series techniques to predict each component's demand. However, the accuracy of the prediction still needs to be improved. In our study, we attempted to find consumption pattern using data mining techniques. We gathered an 18,476 component consumption data first, and then derived diverse features to utilize them in identification of demanding patterns in the consumption data. The results show that our approach improves demand forecasting with higher accuracy.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.41 no.6
• /
• pp.1060-1070
• /
• 2017

This study seeks methods to analyze users' perception in fashion designs shown in social media using textmining analysis methods. The research methods selected 'men's stripe shirts' as subjects and collected texts related to the subject mainly from blogs. Texts from 13,648 posts from November 1st, 2015 to October 31st, 2016 were analyzed by applying the LDA algorithm and content analysis. As a result, the wearing status per season and subjects of men's stripe shirts were derived. Across the entire period, the main topics discussed by users to be pattern, customized suits, brands, coordination and purchase information. In terms of seasons, spring time showed the sharing of information on coordinating daily looks or boyfriend looks, and during the winter season the information shared were about shirts suitable for special occasions such as job interviews and stripe shirts that match suits. The study results showed that text-mining analysis is capable of analyzing the context and provide a user-centered index responding to demands newly mentioned by users along with the rapid changes in fashion design trends.

• Journal of Information Technology Applications and Management
• /
• v.24 no.4
• /
• pp.187-196
• /
• 2017

It is urgent to prepare countermeasures for traffic congestion problems of Korea's metropolitan area where central functions such as economic, social, cultural, and education are excessively concentrated. Most users of public transportation in metropolitan areas including Seoul use the traffic cards. If various information is extracted from traffic big data produced by the traffic cards, they can provide basic data for transport policies, land usages, or facility plans. Therefore, in this study, we extract valuable information such as the subway passengers' frequent travel patterns from the big traffic data provided by the Seoul Metropolitan Government Big Data Campus. For this, we use a Hadoop (High-Availability Distributed Object-Oriented Platform) to preprocess the big data and store it into a Mongo database in order to analyze it by a sequential pattern data mining technique. Since we analysis the actual big data, that is, the traffic cards' data provided by the Seoul Metropolitan Government Big Data Campus, the analyzed results can be used as an important referenced data when the Seoul government makes a plan about the metropolitan traffic policies.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.1 s.39
• /
• pp.293-300
• /
• 2006

The Recommender systems help users to find and evaluate items of interest. Such systems have become powerful tools in the domains from electronic commerce to digital libraries and knowledge management. Sellers can recommend products to customers with the prediction of future buying behavior on the basis of the consumer's population statistics and past selling behavior. In this paper, we are describing the design and the development of personalization recommender system which increases satisfaction level of customers by searching products to reflect the pattern and propensity of customers properly. The suggested system supplies the real-time analysis service to predict the customers purchase situation by applying the association rule of the data mining.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.2
• /
• pp.285-290
• /
• 2009

An association rule mining has been studied to find hidden data pattern in data mining. A realization of fast processing method have became a big issue because it treated a great number of transaction data. The time which is derived by association rule finding method geometrically increase according to a number of item included data. Accordingly, the process to reduce the number of rules is necessarily needed. We propose the T-algorithm that is efficient rule reduction algorithm. The T-algorithm can reduce effectively the number of association rules. Because that the T-algorithm compares transaction data item with binary format. And improves a support and a confidence between items. The performance of the proposed T-algorithm is evaluated from a simulation.