• 한국데이터정보과학회:학술대회논문집
• /
• 2003.05a
• /
• pp.19-25
• /
• 2003

데이터베이스에 내재된 패턴이나 관계를 묘사한 것만으로도 의사결정에 필요한 정보를 제공할 수 있는데 이 데이터들의 변수들을 비슷한 특징을 가지는 소그룹으로 나누어 패턴을 찾는 것을 군집분석이라 한다. 이러한 군집 분석에는 분리군집방법과 계층적군집방법이 있는데, 재할당이 가능한 분리군집방법의 여러 알고리즘에 대해 비교해보자. 분리군집알고리즘에는 중심을 평균으로 하는 k-평균 알고리즘과, 중심을 메도이드로하는 PAM, CLARA, CLARANS 알고리즘이 있다. 이러한 알고리즘에 대한 이론과, 장단점을 설명하고, 분산과 중심들간의 평균 거리로 비교해 본다.

• 한국해양학회지
• /
• v.23 no.1
• /
• pp.1-12
• /
• 1988

To clarify the community structure of phytoplankton in the Kyeonggi Bay, the community analysis were performed to investigate the relationship between the environmental factors and the phytoplankton communities. Low diversity with occurrence of few dominant species throughout the year, except summer, implies that ecological environment of this study area is very unstable due to incessant physical perturbation and large fluctuation of other environmental factors. According to the results of the cluster analysis this study area could be divided into river discharge, polluted and unpolluted area. Principal component analysis of overall phytoplankton community in this area clearly showed four seasonal succession patterns grouped into the spring type, the summer type, the late summer type, the late autumn-winter type. Summer communities composed of common phytoplankton are highly correlated with temperature and transparency. Winter communities composed of most tychopelagic plankton are positively correlated with suspended substances and nutrient, while negatively correlated with transparency.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.169-178
• /
• 2021

Recently, a bike-sharing system (BSS) has become popular as a convenient "last mile" transportation. Rebalancing of bikes is a critical issue to manage BSS because the rents and returns of bikes are not balanced by stations and periods. For efficient and effective rebalancing, accurate traffic prediction is important. Recently, cluster-based traffic prediction has been utilized to enhance the accuracy of prediction at the station-level and the clustering step is very important in this approach. In this paper, we propose a k-means based clustering algorithm that overcomes the drawbacks of the existing clustering methods for BSS; indeterministic and hardly converged. By employing the centroid initialization and using the temporal proportion of the rents and returns of stations as an input for clustering, the proposed algorithm can be deterministic and fast.

• Korean Journal of Environment and Ecology
• /
• v.11 no.1
• /
• pp.111-125
• /
• 1997

To investigate the climax forest structure and to construct the ecological basic data, forty nine plots were set up and surveyed in Mt. Minjuji, Chungchongpukdo. According to the analysis of classification by TWINSPAN, the community was divided by seven groups of Pinus densiflora-Carpinus laxiflora-Quercus serrata(community I), Q. mongolica-Q. serrata-Platycarya strobilacea(community II), Q. mongolica(community III), Fraxinus mandshurica-Acer mono(community IV), Cornus controversa-F. mandshurica(community V), F. mandshurica-Carpinus cordata(community VI), and F. mandshurica-C. laxiflora(community VII). In the results of the analysis of species structure, similarity, diversity and DBH, except for community I~III, it was founede out broadleaves-mixed-climax forest. Constructed basic data will be applied to sustainable development such as ecotourism, nature trail etc.

• Journal of the Korea Computer Graphics Society
• /
• v.16 no.4
• /
• pp.25-33
• /
• 2010

With the popularization of digital photography, people are now capturing and storing far more photos than ever before. However, the enormous number of photos often discourages the users to identify desired photos. In this paper, we present a novel method for fast and intuitive browsing through large collections of geo-referenced photographs. Given a set of photos, we construct a hierarchical structure of clusters such that each cluster includes a set of spatially adjacent photos and its sub-clusters divide the photo set disjointly. For each cluster, we pre-compute its convex hull and the corresponding polygon area. At run-time, this pre-computed data allows us to efficiently visualize only a fraction of the clusters that are inside the current view and have easily recognizable sizes with respect to the current zoom level. Each cluster is displayed as a single polygon representing its convex hull instead of every photo location included in the cluster. The users can quickly transfer from clusters to clusters by simply selecting any interesting clusters. Our system automatically pans and zooms the view until the currently selected cluster fits precisely into the view with a moderate size. Our user study demonstrates that these new visualization and interaction techniques can significantly improve the capability of navigating over large collections of geo-referenced photos.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.04a
• /
• pp.115-118
• /
• 2012

다양한 네트워크에서 군집을 분석하고 그 구조를 발견하는 것은 그 네트워크의 복잡도를 낮추어 전체 시스템을 이해하고 관리하는데 중요하다. 특히 기본적인 컴퓨팅이 가능한 여러 기기들이 자율적으로 서로 통신하여 군집을 이루는 자율 군집 네트워크에서 군집을 정확하게 발견하는 것은 집단행동 서비스를 실현하는데 있어서 중요한 기술이다. 따라서 본 연구에서는 자율 군집 네트워크에서 군집 탐지 기법을 제안한다. 제안하는 기법은 군집을 발견하고 그 군집을 식별하기 위해 해당 네트워크에서 한 노드를 공유하는 두 개의 간선 쌍에 대해 계층 군집화를 수행하고 계층 간에 간선 유사도를 계산하여 비교한다. 계층 군집화를 통한 간선들은 트리 구조로 표현할 수 있으며 최적의 분할 밀도를 이용하여 노드들을 클러스터링한 후 최종 군집으로 분리 한다.

• Journal of Korean Society of Environmental Engineers
• /
• v.32 no.4
• /
• pp.369-378
• /
• 2010

Microorganisms are key-role player for stabilization of landfill sites. In order to evaluate the availability of T-RFLP(Terminal Restriction Fragment Length Polymorphism) for monitoring microbial community variations during stabilization of landfill sites, the phylogenic diversity of microbial community in the leachate from 4 different full-scale landfills was characterized by T-RFLP based on bacterial 16S rDNA. Main population of microbial community analyzed by T-RFLP was significantly similar with that of microbial community analyzed by clone library analysis. The results of T-RFLP analysis for main population of microbial community in the leachate from landfills with different landfill structures, waste types and landfill ages showed apparently different microbial diversity and structures. Therefore, long-term monitoring of microbial community in leachate from landfill sites by using T-RFLP is expected to be available for evaluation of landfill stability.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.646-648
• /
• 2004

기계학습의 군집화(clustering) 기법은 예제들 간의 유사성에 근거하여 주어진 예제들을 무리 짓는 방법이다. 준감독(semi-supervised) 군집화는 카테고리가 부여된(labeled) 소수의 예제들을 적극적으로 활용하여 군집형태가 보다 자연스럽게 형성되도록 유도하는 군집화 방법이다. 준감독 군집화 문제에서 예제에 카테고리를 부여하는 작업은 현실적으로 극히 제한적이거나 카테고리를 부여하는데 소요되는 비용이 상당하므로, 제한된 자원 내에서 군집화에 효용성이 높을 예제들을 선정하여 카테고리를 부여하는 것이 필요하다. 본 논문에서는 기존 연구에서 능동적 학습의 초기 훈련예제 선정을 위해 제안된 군집기반 훈련예제 선정 방법을 준감독 군집화에 적용하여 군집 결과의 질을 향상시키고자 한다. 군집화를 이용한 예제 선정 방법은 유사한 예제들은 동일한 카테고리에 속할 가능성이 높다는 가정하에 전체 예제를 활용하여 선정하고자 하는 예제 수만큼 군집을 생성 한 후. 각 군집의 중심점에 가장 가까운 예제들을 대표 예제로 선정하여 훈련 집합을 구성하는 방법이다 본 논문에서는 문서를 대상으로 하는 준감독 군집화 실험을 통해, 카테고리를 부여할 예제를 임의로 선정한 경우에 비해 군집화를 이용한 훈련 예제들로 준감독 군집화를 수행한 경우가 보다 좋은 군집을 형성함을 확인하였다.

• The Korean Journal of Applied Statistics
• /
• v.33 no.5
• /
• pp.591-601
• /
• 2020

The self-organizing map (SOM) is a unsupervised learning method projecting high-dimensional data into low-dimensional nodes. It can visualize data in 2 or 3 dimensional space using the nodes and it is available to explore characteristics of data through the nodes. To understand the structure of data, cluster analysis is often used for nodes obtained from SOM. In cluster analysis, the optimal number of clusters is one of important issues. To help to determine it, various cluster validity indexes have been developed and they can be applied to clustering outcomes for nodes from SOM. However, while SOM has an advantage in that it reflects the topological properties of original data in the low-dimensional space, these indexes do not consider it. Thus, we propose a new cluster validity index for SOM based on connectivity between nodes which considers topological properties of data. The performance of the proposed index is evaluated through simulations and it is compared with various existing cluster validity indexes.

• Economic Analysis
• /
• v.17 no.2
• /
• pp.27-55
• /
• 2011

Although many theoretical studies have tried to explain the volatility in financial markets using models of herd behavior, there have been few empirical studies on dynamic herding due to the technical difficulty of detecting herd behavior with time-series data. Thus, this paper theoretically extends a continuous beliefs system belonging to an agent based economic model by introducing a term representing agents'mutual dependence into each agent's utility function and derives a SV(stochastic volatility)-type econometric model. From this model the time-varying herding parameters are efficiently estimated by a Markov chain Monte Carlo method. Using monthly data of KOSPI and DOW, this paper provides some empirical evidences for stronger herding in the Korean stock market than in the U.S. stock market, and further stronger herding after the global financial crisis than before it. More interesting finding is that time-varying herd behavior has weak autocorrelation and the global financial crisis may increase its volatility significantly.