• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.414-414
• /
• 2011

우리나라 뿐만 아니라 전 세계적으로 기후변화로 인한 집중호우, 폭설 등이 빈번하게 일어나고 있으며 수공구조물 설계에 필요한 확률강우량도 증가하고 있다. 확률강우량을 산정하는 빈도해석의 경우 지점빈도해석의 문제점을 보완한 지역빈도해석에 대한 연구가 꾸준히 진행되고 있다. 지역빈도해석을 적용하기 위해서는 수문학적 동질성을 가지는 지역 구분이 무엇보다 중요하다. 군집 분석은 개체들이 지니고 있는 다양한 속성의 유사성을 동질적인 집단으로 군집화하는 방법을 말한다. 군집분석의 기본원리는 분석하고자 하는 여러 특성등을 유사성(similaruty) 거리(distance)로 환산하고 거리가 상대적으로 가까운 개체들을 동질적으로 군집화하는 것이다. 군집분석을 적용하기 위해서는 기상학적 인자와 지형학적 인자를 이용하여 군집분석을 실시한다. 군집분석을 실시할 때 가장 중요한 것은 입력변수의 선택으로 입력 변수의 적절한 선택이 결과값에 큰 영향을 준다. 상호정보량(Mutual Information, MI) 기법은 두 무작위 변수간의 관련성을 측정하는 방법이며 (Cover and Tomas, 2006), 두 변수간의 독립성 구조에 관한 가정이 없고 데이터 변형이나 잡음(noise)에 대한 영향이 적어 다른 기법보다 신뢰도가 높다고 알려져 있다(Peng et al., 2005). 본 연구에서는 상호정보량 기법을 이용하여 군집된 지점들의 종속성과 독립성의 관계를 정량적으로 산정하여 비교하고자 한다.

• KIISE Transactions on Computing Practices
• /
• v.23 no.8
• /
• pp.481-486
• /
• 2017

There are many scientists who want to perform experiments in a cloud environment, and pay-per-use services allow scientists to pay only for cloud services that they need. However, it is difficult for scientists to select a suitable set of resources since those resources are comprised of various characteristics. Therefore, classification is needed to support the effective utilization of cloud resources. Thus, a dynamic resource clustering method is needed to reflect the characteristics of the application that scientists want to execute. This paper proposes a resource clustering analysis method that takes into account the characteristics of an application in a hybrid cloud environment. The resource clustering analysis applies a Self-Organizing Map and K-means algorithm to dynamically cluster similar resources. The results of the experiment indicate that the proposed method can classify a similar resource cluster by reflecting the application characteristics.

• Journal of the Society of Disaster Information
• /
• v.19 no.1
• /
• pp.184-194
• /
• 2023

Purpose: The purpose of this study is to identify the characteristics of C02 emissions by road before establishing a policy to reduce greenhouse gas emissions. Method: As for the analysis method, the traffic volume and speed of the road were estimated using the traffic Assignment model targeting 27 arterial road axes in Incheon Metropolitan City. And, after estimating CO2 emissions by road axis by applying this, the characteristics of each group were analyzed through cluster analysis. Result: As a result of cluster analysis using total CO2 emissions, CO2 emissions by truck vehicles, and the ratio of truck vehicle emissions to total carbon dioxide emissions, four clusters were classified. When examining the characteristics of each road included in each group, it was analyzed that the characteristics of each group appeared according to the level of impact by CO2 emissions and truck vehicles. Conclusion: It is judged that it is necessary to establish a plan in consideration of CO2 emission characteristics for road CO2 management for greenhouse gas reduction.

• Korean Journal of Environmental Biology
• /
• v.36 no.1
• /
• pp.21-32
• /
• 2018

This study was carried out to define the characteristics of the identified ground-dwelling invertebrate communities at Nari basin and Tonggumi area in Ulleungdo Island, designated as a nationally important agricultural heritage. The habitat types were divided into the following categories: crop land, forest, and ecotone, and the soil-dwelling invertebrates were collected according to habitat type. The ground-dwelling invertebrates were collected using a pitfall trap, and a self-organizing map (SOM) was applied to the invertebrates dataset to define the characteristics in invertebrates distribution. The SOM clearly classified the relevant information into four clusters, and extracted ecological information from the invertebrates dataset. The cluster II was composed of invertebrate communities which are collected in the Tonggumi area. The Tonggumi area is where mountainous areas were developed for agricultural purposes, which has geographical features commonly observed in Ulleungdo Island. It is noted that the cluster II has different characteristics as compared other clusters. The results of this study are expected to be used for the preservation of agricultural environment and maintenance of biodiversity by providing basic data, on the biotope of Ulleungdo Island designated as a nationally important agricultural heritage and information on the characteristics of the applicable ground-dwelling invertebrate communities.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.24 no.1
• /
• pp.9-16
• /
• 2011

An approach to understand the phase distribution in a multi-phase polycrystalline material is important since it can affect material properties and mechanical behaviors. A proper method is needed to describe the phase distribution. For this purpose, contiguity and probability functions(two-point correlation and lineal-path functions) are investigated for representing the phase distributions of microstructures. The mechanical behaviors are evaluated using the finite element method. The characteristics of probability functions and mechanical reponses of virtual samples are represented. It is confirmed that the topology of phase clustering affects the mechanical behavior of materials and that the strength is reduced as the clustering size increases.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.5
• /
• pp.252-266
• /
• 2019

The purpose of this study was to identify the type of health behaviors in Korean adults and to identify related factors. The data used in the analysis was the Korea Health and Nutrition Examination Survey 2014., which was representative of the Korean population. Cluster analysis was used to find the pattern of clustering of smoking, drinking, exercising and nutrition. Differences in the pattern of clustering was examined, first by bivariate chi-square test, and then by multinomial logit regression. Lastly, the association between the clusters of health behaviors and other behavioral risk factors was tested by chi-square test and logistic regression. The distribution of the clusters varied not only across socioeconomic characteristics and local size, but also between individuals with certain chronic diseases and those without. The results of this study can be used as a basis for the usefulness of approaching the cluster rather than individually approaching the health behavior.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1327-1331
• /
• 2010

최근 50년간 한반도는 산업화와 근대화로 인하여 급격한 도시화가 진행되었다. 도시화는 자연적으로 조성된 생태환경을 변화시키고, 열섬현상과 고층빌딩 등으로 인해 대기의 이동과 특성의 변화를 야기시키게 된다. 따라서 본 연구에서는 우리나라의 과거부터 인구자료와 시가화면적비 자료를 이용하여 도시화가 많이 진행된 지역과 비도시화 지역으로 구분하여 발생된 강우특성자료에 대한 비교분석을 수행하였다. 따라서 우리나라의 관측자료가 존재하는 57개 지점을 대상으로 위도, 경도, 연강우량, 연최대일강우량, 강우일수, 10mm 이상의 강우일수 및 80mm 이상의 강우일수를 이용하여 군집분석을 수행하였다. 군집분석을 통해 우리나라를 크게 4개 권역으로 구분하고, 강우자료의 관측기간을 이등분하여 전후를 비교하였다. 분석 결과에서 도시화가 진행된 지역이 비도시화 지역에 비하여 강우사상의 변화가 연강우량과 강우일수, 80mm 이상 강우일수에서 나타나고 있는 것으로 나타났다. 따라서 도시화가 강우특성 변화에 끼치는 영향에 대한 지속적인 연구가 필요한 것으로 판단된다.

• Journal of Korean Society of Transportation
• /
• v.18 no.5
• /
• pp.7-16
• /
• 2000

This paper is focused on verifying time-space repetition of the highway accident and finding the their causes and deterrents. We classify all months into several seasonal groups, develop the model for each seasonal group and analyze the results of these models for Joong-bu highway. The existence of seasonal effect is verified by the analysis or self-organizing map and the accident indices. Agglomerative hierarchical cluster analysis which is used to decide the seasonal groups in accordance with accident patterns, winter group, spring-fall group. and summer group. The accident features of winter group are that the accident rate is high but the severity rate is low. while those of summer group are that the accident rate is low but the severity rate is high. Also, the regression model which is developed to identify the accident Pattern or each seasonal group represents that the season-related factors, such as the amount of rainfall, the amount of snowfall, days of rainfall, days of snowfall etc. are strongly related to the accident pattern of evert seasonal group and among these factors the traffic volume, amount of rainfall. the amount of snowfall and days of freezing importantly affect the local accident Pattern. So, seasonal effect should be considered to the identification of high-risk road section. the development of descriptive and Predictive accident model, the resource allocation model of accident in order to make safety management plan efficient.

• Korean Journal of Culture and Social Issue
• /
• v.28 no.1
• /
• pp.1-22
• /
• 2022

The purpose of this study was to explore natural groupings among adults based on gender role conflict, ambivalent sexism and aggression, and find differences in their acceptance of rape myths. 372 male and female adults in the Daegu and Gyeongsang province were surveyed and 350 were analyzed on their gender role conflict, ambivalent sexism, aggression and acceptance of rape myths. The cluster analysis divided participants into sub-groups such as 'unaggressive but conflicted about gender stereotypes', 'receptive to adaptive gender notions ' and 'compliant to aggressive gender stereotypes'. The sub-groups had differing levels of gender, age and education. There were differences in acceptance of rape myths among these groups, Post-hoc testing showed that the 'compliant to aggressive gender stereotype' subgroup showed the highest level of acceptance of rape myths, following by 'unaggressive but with gender stereotype conflicts' and 'receptive of adaptive gender notions'. Finally, needs for assessing individual characteristics according to their subgroup types and developing psychoeducational programs focused on the subgroup characteristics were addressed. Then, recommendations for future study were discussed.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2003.04a
• /
• pp.523-528
• /
• 2003

본 연구는 지가의 공간분포 분석(spatial data analysis)을 통하여 합리적인 표준지 선정 방안을 제시하고자 하였다. 우리나라의 경우 개별 공시지가는 표준지 공시지가로부터 비교해서 산정된다. 때문에, 표준지는 개별지의 지가를 산정하는데 편리할 수 있도록 선정되어야 한다. 이를 위하여 표준지를 선정할 때, 개별지의 지가와 토지특성을 고려하여 표준지의 수와 공간적 분포를 결정하여야 한다. 본 연구에서는 지가의 공간적 분포를 해석하기 위하여 군집분석(cluster analysis) 개념을 활용하였다. 이를 통하여 유사 지가구획을 정의하였고, 지가구획의 계층적 해석을 시도하였다. 또한, 군집분석을 반복적으로 수행하고 군집수의 변화에 따른 군집별 지가분포의 특성을 해석함으로써 적정표준지 수를 추정하였다.