• The Korean Journal of Applied Statistics
• /
• v.27 no.4
• /
• pp.561-575
• /
• 2014

In this paper, we propose a penalized likelihood method to detect local spatial clusters associated with disease. The key computational algorithm is based on genlasso by Tibshirani and Taylor (2011). The proposed method has two main advantages over Kulldorff's method which is popoular to detect local spatial clusters. First, it is not needed to specify a proper cluster size a priori. Second, any type of covariate can be incorporated and, it is possible to find local spatial clusters adjusted for some demographic variables. We illustrate our proposed method using tuberculosis data from Seoul.

• Parasites, Hosts and Diseases
• /
• v.58 no.6
• /
• pp.603-608
• /
• 2020

This study was performed to find out the clusters with high parasite infection risk to discuss the geographical pattern. Clusters were detected using SatScan software, which is a statistical spatial scan program using Kulldorff's scan statistic. Information on the parasitic infection cases in Korea 2011-2019 were collected from the Korea Centers for Disease Control and Prevention. Clusters of Ascaris lumbricoides infection were detected in Jeollabuk-do, and T. trichiura in Ulsan, Busan, and Gyeongsangnam-do. C. sinensis clusters were detected in Ulsan, Daegu, Busan, Gyeongsangnamdo, and Gyeongsangbuk-do. Clusters of intestinal trematodes were detected in Ulsan, Busan, and Gyeongsangnam-do. P. westermani cluster was found in Jeollabuk-do. E. vermicularis clusters were distributed in Gangwon-do, Jeju-do, Daegu, Daejeon, and Gwangju. This clustering information can be referred for surveillance and control on the parasitic infection outbreak in the infection-prone areas.

• Journal of Distribution Science
• /
• v.20 no.6
• /
• pp.1-10
• /
• 2022

Purpose: This research proposes a new modified Recency-Frequency-Monetary (RFM) model by extending the model with spatial analysis for supporting decision-makers in discovering the promotional target market. Research design, data and methodology: This quantitative research utilizes data-mining techniques and the RFM model to cluster a university's provider schools. The RFM model was modified by adapting its variables to the university's marketing context and adding a district's potential (D) variable based on heatmap analysis using Geographic Information System (GIS) and K-means clustering. The K-prototype algorithm and the Elbow method were applied to find provider school clusters using the proposed RFM-D model. After profiling the clusters, the target segment was assigned. The model was validated using empirical data from an Indonesian university, and its performance was compared to the Customer Lifetime Value (CLV)-based RFM utilizing accuracy, precision, recall, and F1-score metrics. Results: This research identified five clusters. The target segment was chosen from the highest-value and high-value clusters that comprised 17.80% of provider schools but can contribute 75.77% of students. Conclusions: The proposed model recommended more targeted schools in higher-potential districts and predicted the target segment with 0.99 accuracies, outperforming the CLV-based model. The empirical findings help university management determine the promotion location and allocate resources for promotional information distribution and student recruitment.

• Journal of the Economic Geographical Society of Korea
• /
• v.16 no.3
• /
• pp.492-511
• /
• 2013

According to IASB(International Accounting Standards Board), R&D(Research and Development) is defined as a tertiary sector industry combining research and development. Many studies investigated R&D industry clusters in the form of high-tech cluster(Coe et al., 2007). However, these studies only generalized various spatial cluster of R&D industries. In particular, the studies could not considers cluster formation process over time lacking statistical significance in space-time perspectives. This study, therefore, indicates the limitation of recent R&D cluster literature which only considers either time or space. In addition, this study explores space-time clusters in R&D industry together with textile and cloth industry for comparison. Discovering the existence and location of clusters, this study utilized space-time K function and space-time scan statistics. The result shows that R&D industry presents significant clusters only in spatial dimension. No significant clusters were found in space-time dimension. However, textile and clothing industry presents significant clusters in both spatial and space-time dimensions.

• Journal of The Korean Astronomical Society
• /
• v.52 no.5
• /
• pp.145-158
• /
• 2019

We conducted a survey of open clusters within 1 kpc from the Sun using the astrometric and photometric data of the Gaia Data Release 2. We found 655 cluster candidates by visual inspection of the stellar distributions in proper motion space and spatial distributions in l - b space. All of the 655 cluster candidates have a well defined main-sequence except for two candidates if we consider that the main sequence of very young clusters is somewhat broad due to differential extinction. Cross-matching of our 653 open clusters with known open clusters in various catalogs resulted in 207 new open clusters. We present the physical properties of the newly discovered open clusters. The majority of the newly discovered open clusters are of young to intermediate age and have less than ~50 member stars.

• Journal of Korea Planning Association
• /
• v.54 no.7
• /
• pp.89-102
• /
• 2019

The growth of vacant housing has been problematic in both Korea and other countries as it causes various socio-economic problems and negatively affects residential environments. Despite the importance of effectively managing vacant housing, few studies have been undertaken regarding spatial patterns of vacant housing growth. This study aims to examine spatial dependence in vacant housing growth. We used 2005 and 2015 Population and Housing Census and employed spatial modeling. The empirical analysis shows that there is spatial dependence in vacant housing growth. Also, the spatial clusters of growing vacant housing are present in the non-capital region and nearby cities while the spatial clusters of declining vacant housing are present in the capital region. The policy implications of this study are as follows: First, local governments should make collaborate efforts with geographically proximate cities for more effective management of vacant housing. Second, given that vacant housing is more prevalent and growing in the non-capital region, it is necessary to employ differential policies to manage housing vacancy between the capital and non-capital regions.

• The Bulletin of The Korean Astronomical Society
• /
• v.35 no.2
• /
• pp.81.1-81.1
• /
• 2010

We present a study of five open clusters (Alessi 53, Berkeley 49, Berkeley 84, Czernik 5, Pfleiderer 3) based on ugriz images of the Sloan Digital Sky Survey (SDSS). Physical properties of these clusters are not yet well known. The center and size of these clusters are determined using the radial number density profile. Using the proper motion data, we select the members of the target clusters. We estimate physical parameters of the clusters based on the isochrone fitting in the Color-Magnitude Diagram (CMD) : reddening, distance, and age. The foreground reddening is determined to be E(B-V)=0.71-1.55 mag. The distances to target clusters are derived to be 2.0-4.4 kpc, corresponding to the galactocentric distances of 7.5-11.9 kpc. Their ages are in the range of 280 to 1000 Myr. Their spatial distribution in our Galaxy is similar to that of other intermediate-age open clusters. We find ten blue straggler star candidates in Berkeley 49. This number of blue stragglers is a typical value for the age of Berkeley 49.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.1
• /
• pp.47.3-47.3
• /
• 2019

We discovered 722 open clusters within 1 kpc using Gaia DR2 data. These clusters are detected in the proper motion space and confirmed on the spatial distribution with parallax information. We divided the 3628 regions and visually searched using python program. Among 722 open clusters, 430 clusters are previously unknown clusters. Catalogue of discovered clusters is unloaded on the online catalogue at https://radio.kasi.re.kr/project/shlee/. Owing to the good membership criteria, we could see the halo structure of the clusters. In that reason, the average size of the discovered cluster is about 9 times than that of previously known clusters.

• Spatial Information Research
• /
• v.20 no.1
• /
• pp.81-90
• /
• 2012

When analyzing geographical phenomena, two properties need to be considered. One is the spatial dependence structure and the other is a variation or an uncertainty inhibited in a geographic space. Two problems are encountered due to the properties. Firstly, spatial dependence structure, which is conceptualized as spatial autocorrelation, generates heterogeneous geographic landscape in a spatial process. Secondly, generic statistics, although suitable for dealing with stochastic uncertainty, tacitly ignores location information im plicit in spatial data. GIS is a versatile tool for manipulating locational information, while spatial statistics are suitable for investigating spatial uncertainty. Therefore, integrating spatial statistics to GIS is considered as a plausible strategy for appropriately understanding geographic phenomena of interest. Geographic hot-spot analysis is a key tool for identifying abnormal locations in many domains (e.g., criminology, epidemiology, etc.) and is one of the most prominent applications by utilizing the integration strategy. The article aims at reviewing spatial statistical perspective for analyzing spatial processes in the framework of GIS by carrying out empirical analysis. Illustrated is the analysis procedure of using spatial scan statistic for detecting clusters in the framework of GIS. The empirical analysis targets for identifying spatial clusters of breast cancer incidents in Erie and Niagara counties, New York.

• Journal of the Korean Geographical Society
• /
• v.40 no.2 s.107
• /
• pp.187-201
• /
• 2005

With the trend of urban polynucleation, the issue of detecting economic clusters or urban employment centers has been considered as crucial. However, the prior researches had some limitations in detecting economic clusters in the empirical analysis: i.e. inherent inefficiency of density-based clustering methods, difficulty in detecting linear types of spatial clusters and lacks of consideration of economic significance. The purpose of this paper is to propose the clustering method with the procedure of testing statistical and economic significance named as VCEC (Variable Clumping method for Economic Clusters) and to apply it to a case analysis of Erie County, New York, in order to test its validity. By applying a search radius and a total employment as an economic threshold, 'the both statistically and economically significant clusters' were detected in the Erie County, and proved to be efficient.