• Journal of Korea Spatial Information System Society
• /
• v.11 no.4
• /
• pp.74-84
• /
• 2009

GIS based new postal marketing method is presented in this paper with spatiotemporal mining to cope with domestic mail volume decline and to strengthening competitiveness of postal business. Market segmentation technique for socialogy of population and spatiotemporal prediction of consumer propensity to purchase through spatiotemporal multi-dimensional analysis are suggested to provide meaningful and accurate marketing information with customers. Internal postal acceptance & external statistical data of local districts in the Seoul Metropolis are used for the evaluation of geo-lifestyle clustering and spatiotemporal cube mining. Successfully optimal 14 maketing clusters and spatiotemporal patterns are extracted for the prediction of consumer propensity to purchase.

• Journal of the Korean Data and Information Science Society
• /
• v.15 no.4
• /
• pp.803-816
• /
• 2004

The decision tree approach is most useful in classification problems and to divide the search space into rectangular regions. Decision tree algorithms are used extensively for data mining in many domains such as retail target marketing, fraud dection, data reduction and variable screening, category merging, etc. CHAID uses the chi-squired statistic to determine splitting and is an exploratory method used to study the relationship between a dependent variable and a series of predictor variables. In this paper we propose CHAID algorithm by cube-based proportional sampling and explore CHAID algorithm in view of accuracy and speed by the number of variables.

• Journal of Korea Multimedia Society
• /
• v.12 no.10
• /
• pp.1386-1396
• /
• 2009

Most decision support functions of spatial data warehouse rely on the OLAP operations upon a spatial cube. Meanwhile, higher performance is always guaranteed by indexing the cube, which stores huge amount of pre-aggregated information. Hierarchical Dwarf was proposed as a solution, which can be taken as an extension of the Dwarf, a compressed index for cube structures. However, it does not consider the spatial dimension and even aggregates incorrectly if there are redundant values at the lower levels. OLAP-favored Searching was proposed as a spatial hierarchy based OLAP operation, which employs the advantages of R-tree. Although it supports aggregating functions well against specified areas, it ignores the operations on the spatial dimensions. In this paper, an indexing approach, which aims at utilizing the concept hierarchy of the spatial cube for decision support, is proposed. The index consists of concept hierarchy trees of all dimensions, which are linked according to the tuples stored in the fact table. It saves storage cost by preventing identical trees from being created redundantly. Also, it reduces the OLAP operation cost by integrating the spatial and aspatial dimensions in the virtual concept hierarchy.

• Journal of Korea Spatial Information System Society
• /
• v.9 no.3
• /
• pp.1-16
• /
• 2007

A spatial data warehouse is a system to support decision making using a spatial data cube. A spatial data cube is composed of a dimension table and a fact table. For decision support using this spatial data cube, the concept hierarchy of spatial dimension and the summarized information of spatial fact should be provided. In the previous researches, however, spatial summarized information is deficient. In this paper, the spatial aggregation for spatial summarized information in a spatial data warehouse is proposed. The proposed spatial aggregation is separated of both the numerical aggregation and the object aggregation. The numerical aggregation is the operation to return a numerical data as a result of spatial analysis and the object aggregation returns the result represented to object. We provide the extended struct of spatial data for spatial aggregation and so our proposed method is efficient.

• Journal of the Korea Convergence Society
• /
• v.10 no.3
• /
• pp.221-225
• /
• 2019

The purpose of this study is to provide the general public with basic data to facilitate the application of Cardio-Pulmonary Resuscitation(CPR). There were two groups using CPR mannequin and CPR cube, and participants were given three days of CPR training and two weeks later evaluated for chest compression. Participants recorded chest compression depth, rate of chest compression, accuracy of chest compression, insufficient recoil and incomplete place. There was a statistically significant difference in insufficient recoil and incomplete place in the study. The use of CPR cube to expand CPR education is also believed to be useful in terms of confidence and quality in implementing CPR.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.21-24
• /
• 2011

본 논문에서는 장기간 축적된 대용량의 축구 비디오 데이터를 데이터 마트로 저장하고, 이를 이용하여 다차원의 고수준 분석이 가능한 멀티미디어 데이터 기반의 데이터 큐브 시스템인 Soccer Cube의 프로토타입을 설계 및 구현한다. 이로써 축구 전략가들은 본인이 분석하고자 하는 관점에 따라 해당 차원들을 선택하고, 각 차원들의 추상화 정도를 조절함으로써 축구 비디오에 대한 고수준의 분석이 가능하다. 실제 2010년 남아프리카 공화국 월드컵의 스페인 팀을 대상으로 Soccer Cube 시스템을 구축한 후, OLAP 연산의 사례 연구를 통하여 다양한 분석이 가능함과 함께 그 실효성을 검증한다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.11
• /
• pp.1916-1921
• /
• 2008

This paper presents the temporal classification method based on data mining techniques for discovering knowledge from measured load patterns of distribution transformers. Since the power load patterns have time-varying characteristics and very different patterns according to the hour, time, day and week and so on, it gives rise to the uninformative results if only traditional data mining is used. Therefore, we propose a temporal classification rule for analyzing and forecasting transformer load patterns. The main tasks include the load pattern mining framework and the calendar-based expression using temporal association rule and 3-dimensional cube mining to discover load patterns in multiple time granularities.

• 한국데이터정보과학회:학술대회논문집
• /
• 2004.04a
• /
• pp.39-50
• /
• 2004

The decision tree approach is most useful in classification problems and to divide the search space into rectangular regions. Decision tree algorithms are used extensively for data mining in many domains such as retail target marketing, fraud dection, data reduction and variable screening, category merging, etc. CHAID(Chi-square Automatic Interaction Detector) uses the chi-squired statistic to determine splitting and is an exploratory method used to study the relationship between a dependent variable and a series of predictor variables. In this paper we propose CHAID algorithm by cube-based proportional sampling and explore CHAID algorithm in view of accuracy and speed by the number of variables.

• The KIPS Transactions:PartD
• /
• v.10D no.1
• /
• pp.143-152
• /
• 2003

XML and Web Services draw a lot of attention as standard technologies for data exchange and integration among heterogeneous platforms XML/A, which supports such technologies, is a SOAP based XML APl that facilitates data exchange between a client application and a data analysis engine through the Internet. The fact that the XML format is used for data exchange makes XML/A to be platform-independent. However. client application developers have to go through a tedious Job of treating the same type of XML documents fur downloading data from the server. Also, an XML query language is needed for extracting data from the XML documents sent by the server. In this paper, we present a high level client OLAP API, called DXML, for the client application developers in the windows environment to easily use the OLAP services of XML/A. XMLMD consists of properties and methods needed for OLAP application development. XMLMD is to XML/A what ADOMD is to OLEDB for OLAP. We also present a web OLAP cube browser that is developed using XMLMD. The browser display's data in various formats such as XML, HTML, Excel, and graph.

• New & Renewable Energy
• /
• v.7 no.2
• /
• pp.43-50
• /
• 2011

The only practical way to measure wind resource at high-altitude over 100 m above ground for a feasibility study on a high-rise building integrated wind turbine might be ground-based remote sensing. The remote-sensing campaign was performed at a 145 m-building roof in Jamsil where is a center of metropolitan city Seoul. The campaign aimed uncertainty assessment of Leosphere WindCube LIDAR and Scintec MPAS SODAR through a mutual comparison. Compared with LIDAR, the data availability of SODAR was about 2/3 at 550 m altitude while both showed over 90% under 400 m, and it is shown that the data availability decrease may bring a distortion of statistical analysis. The wind speed measurement of SODAR was fitted to a slope of 0.92 and $R^2$ of 0.90 to the LIDAR measurement. The relative standard deviation of wind speed difference and standard deviation of wind direction difference were evaluated to be 30% and 20 degrees, respectively over the whole measurement heights.