• Journal of the Korean Association of Geographic Information Studies
• /
• v.10 no.4
• /
• pp.60-74
• /
• 2007

For quantitative analysis of spatio-temporal distribution pattern on marine environment, spatial autocorrelation statistics on the both global and local aspects was applied to the observed data obtained from Gwangyang Bay in South Sea of Korea. Global indexes such as Moran's I and General G were used for understanding environmental distribution pattern in the whole study area. LISAs (local indicators of spatial association) such as Moran's I ($I_i$) and $G_i{^*}$ were considered to find similarity between a target feature and its neighborhood features and to detect hot spot and/or cold spot. Additionally, the significance test on clustered patterns by Z-scores was carried out. Statistical results showed variations of spatial patterns quantitatively in the whole year. Then all of general water quality, nutrients, chlorophyll-a and phytoplankton had strong clustered pattern in summer. When global indexes showed strong clustered pattern, the front region with a negative $I_i$ which means a strong spatial variation was observed. Also, when global indexes showed random pattern, hot spot and/or cold spot were/was found in the small local region with a local index $G_i{^*}$. Therefore, global indexes were useful for observing the strength and time series variations of clustered patterns in the whole study area, and local indexes were useful for tracing the location of hot spot and/or cold spot. Quantification of both spatial distribution pattern and clustering characteristics may play an important role to understand marine environment in depth and to find the reasons for spatial pattern.

• Journal of the Korean Geographical Society
• /
• v.48 no.6
• /
• pp.897-913
• /
• 2013

The main purpose of the paper is to examine the spatial characteristics of school choice through residential mobility by conducting a correlation analysis on the relationships between the middle schools' entrance rates to special high schools and the elementary schools' net transfer rates. Analyses are done at both the individual school level and the school catchment area level. Prior to the calculation, the two variables involved in the correlation analysis are transformed via a standardization equation, and the standardized scores are mapped and explored. Both the global and local correlation analyses are done for the standardized variables. Main findings are twofold. First, the global correlation analysis reports that there exists a statistically significant correlation between the two variables at both the analytical levels. Second, albeit the prominent positive correlation at the global level, the local analysis reveals the existence of a considerable level of spatial heterogeneity in terms of bivariate association. While several school catchment areas with very high local correlation coefficients (the HH association type) are popped up, other areas with various types of bivariate association including ones even opposite to the global trend are also observed.

• Journal of Korea Water Resources Association
• /
• v.39 no.8 s.169
• /
• pp.669-676
• /
• 2006

Hydrological factors, especially the spatial distribution of interpretation on precipitation is often topic of interest in studying of water resource. The popular methods such as Thiessen method, inverse distance method, and isohyetal method are limited in calculating the spatial continuity and geographical characteristics. This study was intended to overcome those limitations with improved method that will yield higher accuracy. The monthly and yearly precipitation data were produced and compared with the observed daily precipitation to find correlation between them. They were then used as secondary variables in Co-kriging method, and the result was compared with the outcome of existing methods like inverse distance method and kriging method. The comparison of the data showed that the daily precipitation had high correlation with corresponding year's average monthly amounts of precipitation and the observed average monthly amounts of precipitation. Then the result from the application of these data for a Co-kriging method confirmed increased accuracy in the modeling of spatial distribution of precipitation, thus indirectly reducing inconsistency of the spatial distribution of hydrological factors other than precipitation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.64-78
• /
• 2019

This paper explores key factors affecting taxi travel using global positioning system(GPS) data in Seoul, Korea, considering spatial dependence. We first analyzed the travel characteristics of taxis such as average travel time, average travel distance, and spatial distribution of taxi trips according to the time of the day and the day of the week. As a result, it is found that the most taxi trips were generated during the morning peak time (8 a.m. to 9 a.m.) and after the midnight (until 1 a.m.) on weekdays. The average travel distance and travel time for taxi trips were 5.9 km and 13 minutes, respectively. This implies that taxis are mainly used for short-distance travel and as an alternative to public transit after midnight in a large city. In addition, we identified that taxi trips were spatially correlated at the traffic analysis zone(TAZ) level through the Moran's I test. Thus, spatial regression models (spatial-lagged and spatial-error models) for taxi trips were developed, accounting for socio-demographics (such as the number of households, the number of elderly people, female ratio to the total population, and the number of vehicles), transportation services (such as the number of subway stations and bus stops), and land-use characteristics (such as population density, employment density, and residential areas) as explanatory variables. The model results indicate that these variables are significantly associated with taxi trips.

• Communications for Statistical Applications and Methods
• /
• v.17 no.2
• /
• pp.193-204
• /
• 2010

Recently, researchers of the various fields where the spatial analysis is needed have more interested in spatial statistics. In case of data with spatial correlation, methodologies accounting for the correlation are required and there have been developments in methods for spatial data analysis. Lattice data among spatial data is analyzed with following three procedures: (1) definition of the spatial neighborhood, (2) definition of spatial weight, and (3) the analysis using spatial models. The present paper shows a spatial statistical analysis method superior to a general statistical method in aspect estimation by using the trimmed mean squared error statistic, when we analysis the spatial lattice data that outliers are included. To show validation and usefulness of contents in this paper, we perform a small simulation study and show an empirical example with a criminal data in BusanJin-Gu, Korea.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.22 no.1
• /
• pp.1-18
• /
• 2019

This research measured and visualized the spatial dependency and the spatial heterogeneity of the small business in Cheonan-si, Asan-si with $100m{\times}100m$ grids based on global and local spatial autocorrelation. First, we confirmed positive spatial autocorrelation of small business in the research area using Moran's I Index, which is ESDA(Exploratory Spatial Data Analysis). And then, through Getis-Ord $GI{\ast}$, one kind of LISA(Local Indicators of Spatial Association), local patterns of spatial autocorrelation were visualized. These verified that Spatial Regression Model is valid for the location factor analysis on small business commercial buildings. Next, GWR(Geographically Weighted Regression) was used to analyze the spatial relations between the distribution of small business, hourly mobile traffic-based floating population, land use attributes index, residence, commercial building, road networks, and the node of traffic networks. Final six variables were applied and the accessibility to bus stops, afternoon time floating population, and evening time floating population were excluded due to multicollinearity. By this, we demonstrated that GWR is statistically improved compared to OLS. We visualized the spatial influence of the individual variables using the regression coefficients and local coefficients of determinant of the six variables. This research applied the measured population information in a practical way. Reflecting the dynamic information of the urban people using the commercial area. It is different from other studies that performed commercial analysis. Finally, this research has a differentiated advantage over the existing commercial area analysis in that it employed hourly changing commercial service population data and it applied spatial statistical models to micro spatial units. This research proposed new framework for the commercial analysis area analysis.

• Tunnel and Underground Space
• /
• v.32 no.6
• /
• pp.464-477
• /
• 2022

DFN (discrete fracture network) models that take account of spatial variability and correlation between rock fractures have been demanded for analysis of fractured rock mass behavior for wide areas with high reliability, such as that of underground nuclear waste repositories. In this regard, this report describes the spatial distribution characteristics of fracture networks, and the DFN modeling methodologies that aim to represent such characteristics. DFN modeling methods have been proposed to represent the spatial variability of rock fractures by defining fracture domains (Darcel et al., 2013) and the spatial correlation among fractures by genetic modeling techniques that imitate fracture growth processes (Davy et al., 2013, Libby et al., 2019, Lavoine et al., 2020).These methods, however, require further research for their application to field surveys and for modeling in-situ rock fracture networks.

• Korean Journal of Cognitive Science
• /
• v.23 no.3
• /
• pp.295-322
• /
• 2012

In this paper, we cluster similar word senses applying vector space model and HAL (Hyperspace Analog to Language). HAL measures corelation among words through a certain size of context (Lund and Burgess 1996). The similarity measurement between a word pair is cosine similarity based on the vector space model, which reduces distortion of space between high frequency words and low frequency words (Salton et al. 1975, Widdows 2004). We use PCA (Principal Component Analysis) and SVD (Singular Value Decomposition) to reduce a large amount of dimensions caused by similarity matrix. For sense similarity clustering, we adopt supervised and non-supervised learning methods. For non-supervised method, we use clustering. For supervised method, we use SVM (Support Vector Machine), Naive Bayes Classifier, and Maximum Entropy Method.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.1
• /
• pp.29-40
• /
• 2021

Risk factors that threaten public safety such as crime, fire, and traffic accidents have spatial characteristics. Since each region has different dangerous environments, it is necessary to analyze the spatial pattern of risk factors for each sector such as traffic accident, fire, crime, and living safety. The purpose of this study is to analyze the spatial distribution pattern of local safety level index, which act as an index that rates the safety level of each sector (traffic accident, fire, crime, living safety, suicide, and infectious disease) for basic local governments across the nation. The following analysis tools were used to analyze the spatial autocorrelation of local safety level index : Global Moran's I, Local Moran's I, and Getis-Ord's G⁎i. The result of the analysis shows that the distribution of safety level on traffic accidents, fire, and suicide tends to be more clustered spatially compared to the safety level on crime, living safety, and infectious disease. As a result of analyzing significant spatial correlations between different regions, it was found that the Seoul metropolitan areas are relatively safe compared to other cities based on the integrated index of local safety. In addition, hot spot analysis using statistical values from Getis-Ord's G⁎i derived three hot spots(Samchuck, Cheongsong-gun, and Gimje) in which safety-vulnerable areas are clustered and 15 cold spots which are clusters of areas with high safety levels. These research findings can be used as basic data when the government is making policies to improve the safety level by identifying the spatial distribution and the spatial pattern in areas with vulnerable safety levels.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.23-23
• /
• 2019

본 연구의 목적은 아시아-태평양 지역을 대상으로 위성영상 기반 고해상도의 신뢰성이 있고 쉽게 접근할 수 있는 강수 자료를 제공하는 데 있다. 본 연구에서 개발한 기후 관리 시스템은 총 3가지의 위성자료(원시위성자료, 편의보정한 위성자료, 공간상세화한 위성자료)를 제공한다. 위성자료의 공간해상도는 $0.1^{\circ}$, $0.05^{\circ}$이며, 시간해상도는 1 day이다. 비교적 신뢰성이 높은 기후 자료가 구축된 한반도를 대상으로 위성영상 편의보정, 공간상세화 기법을 검증하고, 개발한 기법을 아시아-태평양에 위치한 바누아투에 적용하여 기후 자료를 생산하였다. 원시위성자료는 TRMM (Tropical Rainfall Measurement Mission) 위성과 GPM (Global Precipitation Mission) 위성을 사용하여 구축하였다. 편의보정은 GRA-IDW (Geographical Ratio Analysis-Inverse Distance Weighted), GRA-Kriging, QM (Quantile Mapping) 기법을 검토하여 본 연구에 적합한 알고리즘을 개발하고 이 중 최적의 결과를 보여주는 GRA-IDW 기법을 최종적으로 선정하였다. 공간상세화는 PRISM (Parameter-elevation Regressions on Independent Slopes Model)을 선정하여 수행하였다. 원시위성자료를 검증한 결과를 살펴보면 상관계수는 1998년부터 2017년까지 0.775로 비교적 정확도가 높게 나왔다. bias 값은 원시위성자료 값이 지상관측자료보다 과대추정하는 것으로 나타났다. 최종적인 편의보정 기법으로 GRA-IDW 기법을 선정하여 편의보정한 위성자료를 생산하였다. 공간상세화한 위성자료를 검증한 결과를 앞서 분석한 원시위성자료, 편의보정한 위성자료와 비교하면, 공간상세화를 수행하기 전보다 상관계수는 다소 작아지고, RMSE는 커지는 것으로 나타나나 그 차이가 크지 않아 공간상세화한 위성자료를 응용분야에 직접 사용할 수 있을 것으로 분석된다. 본 연구를 통해 개발된 기법을 활용하면 아시아-태평양에 신뢰성 있는 기후 관측 자료를 제공할 수 있다. 향후 본 연구에서 선정한 대상지역 이외에 기상관측소의 수가 희박하고 불균등하게 분포하고 있는 아시아-태평양 지역에 본 과업에서 개발한 시스템을 적용하여 신뢰성 있는 기후 자료를 제공할 수 있을 것으로 사료된다.