• The Korean Journal of Applied Statistics
• /
• v.12 no.2
• /
• pp.335-345
• /
• 1999

시뮬레이션 실행 시간이 매우 오래 걸려서 보통 이용하는 비선형최고제곱법으로는 시뮬레이션의 입력 파라메터(또는 절대 상수)를 추정하기 힘든 경우의 추정 문제를 통계적인 메타모델을 이용하여 해결하는 방법에 대하여 기술하였다. 미리 답을 알고 있는 장난감 모형을 이용하여 절대 상수를 추정하기 위해 사용되는 세가지 통계적 메타모델들(전통적 희귀모형, 공간적 선형모형 그리고 projection pursuit 희귀모형)의 성능을 비교하였다. 그 결과 일양 크리깅(universal Kriging)에 의한 공간적 모형이 가장 우수하였고, 이를 실제 핵융합 시뮬레이션 자료에 적용하여 절대 상수를 추정하였다.

• Tunnel and Underground Space
• /
• v.13 no.2
• /
• pp.87-99
• /
• 2003

Geostatistics is defined as the theory of modeling of regionalized variables and is an efficient and elegant methodology for estimation and uncertainty evaluation from limited spatial sample data. In this study, we have made a theoretical comparison between kriging estimation and geostatistical simulation methods. Kriging methods do not preserve the histogram of original data nor their spatial structure, and also provide only an incomplete measure of uncertainty when compared to the simulation methods. A practical procedure of geostatistical simulation is suggested in this study and the technique is demonstrated through an application, in which it was used to identify the spatial distribution of RMR as well as to evaluate the spatial uncertainty. It is concluded that the geostatistical simulation is the appropriate method to quantify the spatial uncertainty of geotechnical variables such as RMA. Therefore, the results from the simulation can be used as useful information for designer's considerations in decision-making under various geological conditions as well as the related terms of contract.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.3
• /
• pp.67-81
• /
• 2006

The present study suggests an analytical method to overcome the spatial problems that traditional hedonic methods have. The concept of overlapping neighborhoods is introduced in order to solve the problems of global parameter estimate methods that treat the whole city by the gross. Moreover, a 3rd party program for the tight coupling of GIS and statistics is developed in order to explore hedonic methods efficiently. By using these, this study analyses the spatial variation of location variables that affect the real estate price. The results show that the influences of urban centers do not reach to the whole city, but only to the catchment areas of them. And the coefficients of location variables are different depending on the space. The tight coupling of GIS and statistics offers a powerful tool in analysing the real estate price efficiently.

• Journal of the Economic Geographical Society of Korea
• /
• v.12 no.2
• /
• pp.179-194
• /
• 2009

The spatial distribution of crime incidences in urban neighborhoods is a reflection of their socio-economic environment and spatial inter-relations. Spatial interactions between offenders and victims lead to spatial autocorrelation of the crime incidences. The spatial autocorrelation among the incidences biases the interpretation of the ecological model in OLS framework. This research investigates residential crimes using residential burglaries and robberies occurred in the city of Columbus, Ohio, for 2000. In particular, the spatial distribution of incidence rates of residential crimes are accounted in OLS framework using eigenvectors, which reflect spatial dependence in crime patterns. Result presents that handling spatial autocorrelation enhanced model estimation, and both economic deprivation and crime opportunity are turned out significant in estimating residential crime rates.

• The Journal of Society for e-Business Studies
• /
• v.19 no.3
• /
• pp.107-123
• /
• 2014

Current text mining techniques suffer from the problem that the conventional text representation models cannot express the semantic or conceptual information for the textual documents written with natural languages. The conventional text models represent the textual documents as bag of words, which include vector space model, Boolean model, statistical model, and tensor space model. These models express documents only with the term literals for indexing and the frequency-based weights for their corresponding terms; that is, they ignore semantical information, sequential order information, and structural information of terms. Most of the text mining techniques have been developed assuming that the given documents are represented as 'bag-of-words' based text models. However, currently, confronting the big data era, a new paradigm of text representation model is required which can analyse huge amounts of textual documents more precisely. Our text model regards the 'concept' as an independent space equated with the 'term' and 'document' spaces used in the vector space model, and it expresses the relatedness among the three spaces. To develop the concept space, we use Wikipedia data, each of which defines a single concept. Consequently, a document collection is represented as a 3-order tensor with semantic information, and then the proposed model is called text cuboid model in our paper. Through experiments using the popular 20NewsGroup document corpus, we prove the superiority of the proposed text model in terms of document clustering and concept clustering.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.8 no.1
• /
• pp.40-48
• /
• 2005

This paper will specify geo-objects and geo-fields of the geo-ecological contamination source and implement the system for evaluating an ocean Environmental contamination based on the spatial statistical analysis. In order to produce the grade of fishery that can evaluate the ocean effect, we will analysis the degree of the spatial correlation by semi-veriogram and predicate the elevation raster of spatial data using ordinary kriging method. This paper is to estimate the grade of fishery contamination region and produce the ratio of the area according to the fishery grade. Therefore, we can contribute to produce fishery grade that evaluates the ocean effect by means of deciding an efficient fishery environment.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.11 no.4
• /
• pp.64-75
• /
• 2008

Since the current database systems for managing geotechnical investigation results were limited by being described boring test result in point feature, it has been trouble for using other GIS data. Although there are some studies for spatial characteristics of subsurface modeling, it is rather lack of being interoperable with GIS, considering geotechnical engineering facts. This is reason for difficulty of practical uses. In this study, we has developed subsurface spatial information model through extracting needed geotechnical engineering data from geotechnical information DB. The developed geotechnical information clustering program(GEOCL) has made a cluster of boring formation(and formation ratio), classification of layer, and strength characteristics of subsurface. The interpolation of boring data has been achieved through zonal kriging method in the consideration of spatial distribution of created cluster. Finally, we make a subsurface spatial information model to integrate with digital elevation model, and visualize 3-dimensional model by subsurface spatial information viewing program(SSIVIEW). We expect to strengthen application capacity of developed model in subsurface interpretation and foundation design of construction works.

• Journal of the Korean Geographical Society
• /
• v.43 no.1
• /
• pp.134-153
• /
• 2008

The main purpose of the research is to illustrate the value of the spatial statistical approach to residential differentiation by providing a framework for exploratory spatial data analysis (ESDA) using a local spatial separation measure. ESDA aims, by utilizing a variety of statistical and cartographic visualization techniques, at seeking to detect patterns, to formulate hypotheses, and to assess statistical models for spatial data. The research is driven by a realization that ESDA based on local statistics has a great potential for substantive research. The main results are as follows. First, a local spatial separation measure is correspondingly derived from its global counterpart. Second, a set of significance testing methods based on both total and conditional randomization assumptions is provided for the local measure. Third, two mapping techniques, a 'spatial separation scatterplot map' and a 'spatial separation anomaly map', are devised for ESDA utilizing the local measure and the related significance tests. Fourth, a case study of residential differentiation between the highly educated and the least educated in major Korean metropolitan cities shows that the proposed ESDA techniques are beneficial in identifying bivariate spatial clusters and spatial outliers.

• Spatial Information Research
• /
• v.9 no.2
• /
• pp.239-261
• /
• 2001

A large suite of official statistical data sets has been compiled for geographical units under the national directives, and it is the quantitative regional analysis procedures that could add values to them. This paper reports our attempts at prototyping a statistical GIS which is capable of serving over the Web a variety of regional analysis routines as well as value-added statistics and maps. A pilot database of some major statistical data was ingested for the city of Seoul. The baseline subset of regional analysis methods of practical usage was selected and accommodated into the business logic of the target system, which ranges from descriptive statistics, regional structure/inequality measures, spatial ANOVA, spatial (auto) correlation to regression and residual analysis. The leading-edge information technologies including the application server were adopted in the system design and implementation so that the database, analysis modules and analytic mapping components may cooperate seamlessly behind the Web front-end. The prototyped system supports tables, maps, and files of downloadable format for input and output of the analyses. One of the most salient features of out proposed system is that both the database and analysis modules are extensible via the bi-directional interface for end users; The system provides users with operators and parsers for algebraic formulae such that the stored statistical variables may be transformed and combined into the newly-derived set of variables. This functionality eventually leads to on-the-fly fabrication of user-defined regional analysis algorithms. The stored dataset may also be temporarily augmented by user-uploaded dataset; The extension of this form, in essence, results in a virtual database which awaits for users commands as usual. An initial evaluation of the proposed system confirms that the issues involving the usage and dissemination of information can be addressed with success.

• Spatial Information Research
• /
• v.20 no.4
• /
• pp.1-16
• /
• 2012

There is no doubt that the urban heat island (UHI) is a mounting problem in built-up environments, due to energy retention by the surface materials of dense buildings, leading to increased temperatures, air pollution, and energy consumption. To investigate the UHI, three-dimensional (3-D) information is necessary to analyze complex sites, including dense building clusters. In this research, 3-D building geometry information is combined with two-dimensional (2-D) urban surface information to examine the relationship between urban characteristics and temperature. In addition, this research introduces spatial regression models to account for the spatial spillover effects of urban temperatures, and includes the following steps: (a) estimating urban temperatures, (b) developing a 3-D city model, (c) generating urban parameters, and (d) conducting statistical analyses using both Ordinary Least-Squares (OLS) and Spatial Regression Models. The results demonstrate that 3-D urban characteristics greatly affect temperatures and that neighborhood effects are critical in explaining temperature variations. Finally, the implications of the results are discussed, providing guidelines for policies to reduce the UHI.