• 환경생물
• /
• 제18권3호
• /
• pp.337-345
• /
• 2000

해안생태공원 조성이 추진중인 인천광역시 논현동 일대 염습지의 식물상 및 식생을 1999년 6월부터 2000년 6월까지 조사하였다. 이 지역에는 소래포구의 조간대를 따라 발달한 자연염습지와 함께 조수가 차단된 폐염전이 있다. 이 지역에서 14종의 염생식물이 조사되었는데, 그중 해흥나물이 가장 많이 분포하고 있었으며, 그밖에 퉁퉁마디, 비쑥, 갯개미취 등도 많이 관찰되었다. 폐염전에서 관찰된 염생식물의 종류는 자연염습지에서 조사된 것과 매우 유사하였다. 그러나, 폐염전과 자연염습지 사이의 제방 지역은 염습지 보다 다양한 종이 자라고 있었는데, 귀화식물도 21종이 관찰되었다. 자연염습지의 식생은 해흥나물-비쑥군집과 해흥나물군집으로 구성되어져 있으며 지역에 따른 큰 차이는 없었다. 한편, 폐염전에서는 해흥나물-퉁퉁마디, 나문재-해흥나물, 갈대-애기부들, 갈대군집 등 다양한 군집이 조사되었다. 식생상관과 종다양도에 기초하여 조사지역을 식생양호지역, 인간활동에 따른 교란지역, 식물고사지역 등의 세 구역으로 나눌 수 있었으며, 해안생태공원 조성에 따른 각 구역의 보존대책을 제시하였다.

• Journal of the Korean Statistical Society
• /
• 제22권2호
• /
• pp.209-217
• /
• 1993

The multicollinearity problem in a multiple linear regression model may present deleterious effects on predictions. Thus, its is desirable to consider the optimal fractions with respect to the unbiased estimate of the mean squares errors of the predicted values. Interstingly, the optimal fractions can be also illuminated by the Bayesian inerpretation of the general James-Stein estimators.

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2003년도 추계학술대회논문집
• /
• pp.3-8
• /
• 2003

Census data are usually provided at an aggregated level. However, the aggregated data are essentially arbitrary geographical areas. The areal units used to report census data have no natural or meaningful geographical identity. Unfortunately, this means that analyses of these area aggregations may be conditional upon the set of zones, which are presented. This effect is known as the modifiable areal unit problem (MAUP) and has two related aspects. First, scale effect is the variation in numerical results that occurs due to the number of zones used in an analysis. Second, results may also differ between different ways of aggregating exactly the same data to the same scale; this may be called the aggregation effect (Openshaw, 1984). This study aims to provide a practical tool for the study of MAUP. I have created a set of 91 areal units based on 280 basic units in Nonhyun-2 dong to solve zoning problem and scale problem. We can easily recognize the importance of areal classification as statistics were different according to areal classification.

• 한국측량학회지
• /
• 제12권1호
• /
• pp.25-34
• /
• 1994

현대 도시의 상수도 업무를 효율화, 고도화하기 위해서는 적절한 상수도정보체계의 운용이 필요하다. 이는 궁극적으로 도시종합정보체계의 부분이 되야 한다. 이를 수행하기 위해, 서울시 강남지역을 사례로 한국의 상수도 업무를 분석하고, 이를 바탕으로, 벡테 GIS의 macro-programming language를 이용하여, 한국토지행정업무의 기본인 지번을 기초로 도시상수도정보체계를 구축하여, 사례지역에 적용 후, 한국에서의 도시상수도정보체계가 효율적으로 운용되기 위한 활용방안, 제도적, 기술적 문제점 등을 논의하였다.

• 보건행정학회지
• /
• 제13권2호
• /
• pp.85-100
• /
• 2003

The purpose of this study is to (1) identify socio-demographic, economic, village-effect variables that influence the late payment of the National Health Insurance contribution, (2) to develop the model to predict the probability of a household to make late payment of the contribution. Data is composed of information on 78,858 households, Gangnam branch, National Health Insurance Corporation, as of September 30, 2001. We analyzed the data by using multivariate logistic regressions. The major findings are as follows; (1) an older or female householder whose family consists of smaller number of members is more likely to pay the contribution late than others, (2) as for income, one who belongs to a lower income group or nm a private business tend to pay it late, (3) more attention should be paid to a householders who does not have his/her own house or automobile so as to prevent late payment, (4) lastly, those who live in villages such as Nonhyun-l-dong are less likely to pay the contribution prior to due date.

• Journal of Korean Society for Atmospheric Environment
• /
• 제18권E4호
• /
• pp.203-213
• /
• 2002

Receptor modeling is one of statistical methods to achieve reasonable air pollution strategies. In order to maintain and manage ambient air quality, it is necessary to identify sources and to apportion its sources for ambient particulate matters. The main purpose of the study was to survey seasonal trends of inorganic elements in the coarse and fine particles. Second, this study has attempted emission sources qualitatively by a receptor method, the PMF mo-del. After that. both PMF (positive matrix factorization) model and TTFA (target transformation factor analysis) model were applied to compare and to estimate mass contribution of coarse and fine particle sources at the receptor. A total of 138 sets of samples was collected from 1989 to 1996 by a low volume cascade impactor with 9 size fraction stages at Kyung Hee University in Korea. Sixteen chemical species (Si, Ca, Fe, K, Pb, Na, Zn, Mg, Ba, Ni, V, Mn, Cr, Br, Cu. Co) were characterized by XRF. The study result showed that the weighted arithmetic mean of coarse and fine particles were 51.3 and 54.4 $\mu\textrm{g}$/㎥, respectively. Contribution of both particle fractions were esti-mated using TTFA and PMF models. The number of estimated sources was seven according to TTFA model and 8 according to PMF model. Comparison of TTFA and PMF revealed that both methodologies exhibited similar trends in their contribution pattern. However, large differences between contributions were observed in some sour-ces. The results of this study may help to suggest control strategies in local countries where known source profiles do not exist.

• 패션비즈니스
• /
• 제19권1호
• /
• pp.34-46
• /
• 2015

The purpose of this study was to investigate the distribution state of road shops around the 9 main fashion trade areas in Seoul, and to analyze whether there were any differences in them based on clothing, store types and regions. Furthermore, by investigating the distribution state of road shops in the 9 main fashion trade areas per year, this study provides basic information that can be helpful in opening and securing road shops in major trade areas. The method of investigation was to analyze clothing types and store types with 72 maps of commercial areas. Samsungdesignnet investigated these areas for 8 years around the 9 main fashion trade areas (Garosugil, Gangnam nonhyun, Gangnam Station, Myungdong, Moonjung, Apgujung, Yeonsinne, Edae, and Chungdam). As a result, the distribution state of the fashion road shops based on clothing types revealed that road shops for ladies' wear, bag or shoes, and total fashion were strong, and the distribution state of non brand were strong. When it came to year-to-year trends, road shops for women's wear, bag or shoes, and total fashion showed a steady increasing tendency of being on-trend, but casuals and underwear showed a falling tendency of being on-trend. In terms of store type distribution, non-brand shops showed the most remarkable growth, followed by multi-shop while total fashion store showed a steady growth. Also, when it came to regional distribution, the dominant trade areas were different based on clothing type. Garosugil showed the widest variation in its yearly trend investigation, and Gangnam station also showed a substantial amount of growth. In other areas, there was no considerable change in the total number of shops, but increasing and decreasing markets had a complexity that depended on clothing types.