• Journal of Information Technology Applications and Management
• /
• 제17권1호
• /
• pp.127-139
• /
• 2010

Customer behavior pattern discovery is the fundament for conducting customer oriented services and the services management. But, the composition, need, interest and experience of customers may be continuously changing, thereof lead to the difficulty in refining a stable description of their consistent behavior pattern. This paper presented a new method for the behavior pattern discovery from a changing collection of customers. It was originally inspired from the swarm intelligence of ant colony. By the adaptive clustering, some typical behavior patterns which reflect the characteristics of related customer clusters can extracted dynamically and adaptively.

• 보건교육건강증진학회지
• /
• 제29권2호
• /
• pp.93-105
• /
• 2012

Objectives: The objective of the study was to examine the clustering patterns and correlates of multiple health behaviors (MHBs) in middle-aged Koreans with metabolic syndrome (MetS). Methods: Data on sociodemographics, clinical characteristics, health behaviors (vegetable intake, physical activity, cigarette smoking, and alcohol consumption), and psychological characteristics were collected by a self-reported survey and medical examination from 331 individuals with MetS. Clustering of MHBs was examined by measuring 1) the ratios of observed and expected prevalence of MHBs, and 2) the prevalence odds ratios. A binomial logistic regression were conducted. Results: Men were more likely than women to engage in multiple unhealthy behaviors. Clustering of smoking and heavy drinking was exhibited in the participants. Women with high vegetable intake were more likely to be physically inactive, and those with inadequate vegetable intake were more likely to be physically active. Those with lower self-regulation were more likely to engage in unhealthy behaviors. Conclusions: The findings support the multiple health behavior approach as opposed to the individual health behavior approach. Emphasis of self-regulation is necessary in developing multiple behavior intervention for individuals with MetS.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.504-510
• /
• 1998

In this paper, Fundamental rules governing group intelligence "obstacle avoidance" behavior of multiple autonomous mobile robots are represented by a small number of fuzzy rules. Complex lifelike behavior is considered as local interactions between simple individuals under small number of fundamental rules. The fuzzy rules for obstacle avoidance are generated from clustering the input-output data obtained from the obstacle avoidance algorithm. Simulation shows the fuzzy rules successfully realizes fundamental rules of the obstacle avoidance behavior.

• KEPCO Journal on Electric Power and Energy
• /
• 제2권1호
• /
• pp.61-69
• /
• 2016

Understanding load patterns and customer classification is a basic step in analyzing the behavior of electricity consumers. To achieve that, there have been many researches about clustering customers' daily load data. Nowadays, the deployment of advanced metering infrastructure (AMI) and big-data technologies make it easier to study customers' load data. In this paper, we study load clustering from the view point of yearly and daily load pattern. We compare four clustering methods; K-means clustering, hierarchical clustering (average & Ward's method) and DBSCAN (Density-Based Spatial Clustering of Applications with Noise). We also discuss the relationship between clustering results and Korean Standard Industrial Classification that is one of possible labels for customers' load data. We find that hierarchical clustering with Ward's method is suitable for clustering load data and KSIC can be well characterized by daily load pattern, but not quite well by yearly load pattern.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (A)
• /
• pp.892-894
• /
• 2005

Graph partitioning provides an important tool for data clustering, but is an NP-hard combinatorial optimization problem. Spectral clustering where the clustering is performed by the eigen-decomposition of an affinity matrix [1,2]. This is a popular way of solving the graph partitioning problem. On the other hand, semidefinite relaxation, is an alternative way of relaxing combinatorial optimization. issuing to a convex optimization[4]. In this paper we present a semidefinite programming (SDP) approach to graph equi-partitioning for clustering and then we use eigen-decomposition to obtain an optimal partition set. Therefore, the method is referred to as semidefinite spectral clustering (SSC). Numerical experiments with several artificial and real data sets, demonstrate the useful behavior of our SSC. compared to existing spectral clustering methods.

• Bulletin of the Korean Chemical Society
• /
• 제33권2호
• /
• pp.711-713
• /
• 2012

• Composites Research
• /
• 제30권5호
• /
• pp.323-330
• /
• 2017

본 연구에서는 폴리프로필렌 내에 투입된 탄화규소 나노 입자들의 군집현상이 나노복합재의 역학적 거동에 미치는 영향을 고찰하기 위해 분자동역학 전산모사를 통해 얻은 정보를 연속체 역학 수준에 적용시키는 멀티스케일 해석을 수행하였다. 입자 간의 거리에 따른 계면 물성의 하락을 반영하는 모델을 이용하여, 다양한 군집 상황에 따른 고분자 나노복합재의 탄성거동 변화를 관찰하였다. 또한, 나노복합재의 기계적 거동에 영향을 미치는 주요 요인을 파악하여 군집밀도라는 새로운 지표를 정의하였다. 나노 입자의 군집밀도와 나노복합재의 탄성거동 간의 상관관계를 파악한 결과, 군집밀도의 값이 증가할수록 계면효과가 저하되어 최종적으로 나노복합재의 기계적 물성 상승이 억제되었다. 나노 입자의 랜덤분포를 고려한 해석을 통해, 동일한 군집밀도의 수치에 대해 나노복합재가 가질 수 있는 탄성계수의 범위를 파악할 수 있었다. 상관관계는 지수 함수형태로 표현될 수 있었으며, 이를 통해 나노 입자의 군집밀도를 이용하여 고분자 나노복합재의 기계적 거동을 효과적으로 예측 가능하다.

• 정보처리학회논문지C
• /
• 제10C권7호
• /
• pp.857-866
• /
• 2003

사용자 비정상 행위를 탐지하기 위해서 기존의 연구들은 주로 통계적 기법을 이용해 왔다. 그러나 이들 연구들은 주로 사용자의 평균적인 행위를 분석하기 때문에 사용자의 비정상행위가 정확하게 탐지될 수 없다. 본 논문에서는 사용자의 정상행위를 모델링하는 새로운 클러스터링 방법을 제안한다. 클러스터링은 분석 환경에서 임의 개수의 빈발 영역을 식별할 수 있기 때문에 통계적 기법에서의 부정확한 모델링 방법을 개선할 수 있다. 빈발 공통 지식은 트랜잭션 단위로 발생되는 유사 데이터 객체들의 빈도수와 각 트랜잭션에 포함된 유사 데이터 객체들의 반복 비율로 나타낼 수 있다. 이와 더불어, 제안된 방법은 공통 지식을 축약된 프로파일로 유지하는 방법을 설명한다. 따라서 생성된 프로파일을 이용하여 온라인 트랜잭션에서의 비정상 행위를 쉽게 탐지할 수 있다.

• 한국전산유체공학회지
• /
• 제21권4호
• /
• pp.46-53
• /
• 2016

Direct numerical simulation is conducted to observe the behavior of microbubbles in isotropic turbulence. Navier-Stokes equation and the motion of equation for microbubbles are solved with periodic boundary condition in a cube domain. Vorticity contour, enstrophy ratio, relative reduction of bubble rise velocity, and the closest distance of particles are investigated for various Stokes numbers and gravity factors to understand clustering of microbubbles. Also, clustering due to the effect of the lift force is investigated.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 추계학술대회 학술발표 논문집
• /
• pp.79-82
• /
• 1997

In this paper, group intelligence "arrangement" bahavior of autonomous mobile robots(AMRs) is realized by the fuzzy rules. The fuzzy rules for the arrangement are generated from clustering the input-output data. Simulation shows that a small-number of fuzzy rules successfully realizes the arrangement behavior of AMRs.