• 한국지능시스템학회논문지
• /
• 제22권1호
• /
• pp.81-86
• /
• 2012

본 논문에서는 전형적인 Linear Discriminant Analysis을 확장시켜 전체 입력공간을 다수의 지역공간으로 분할하고 분할된 공간에 Local Linear Discriminant Analysis 기반으로 하여 패턴 분류 규칙을 설계하는 새로운 방법을 제안한다. 전체 입력공간을 여러 개의 지역공간으로 분할하기 위한 방법으로 unsupervised clustering의 대표적인 방법인 k-Means 클러스터링 기법과 최적화 알고리즘인 차분 진화 연산 알고리즘을 사용한다. 제안된 알고리즘의 성능 평가를 위해 기존의 패턴 분류기와 비교 결과를 제시한다.

• 한국인터넷방송통신학회논문지
• /
• 제17권1호
• /
• pp.173-181
• /
• 2017

산업이 발달함에 따라서 빅데이터가 무수히 생산되고 있으며 이에 따라서 데이터에 내재된 불확실성도 증가하고 있다. 본 논문에서는 데이터에 내재된 불확실성을 다루기 위해 interval type-2 퍼지 클러스터링 방법을 제안하고 이를 이용하여 퍼지뉴럴네트워크를 설계하고 최적화한다. 제안한 클러스터링 방법을 이용하여 퍼지 규칙을 설계하고 학습을 수행한다. 최적화하는 방법으로서 유전자 알고리즘을 이용하고 모델 파라미터들을 최적 탐색한다. 실험에서는 두 가지 패턴 분류를 시행하였으며 두 가지 실험 모두 우수한 패턴 인식 결과를 보여준다. 제안한 네트워크는 증가하는 불확실성을 다룰 수 있는 방법을 제공할 수 있을 것이다.

• 한국정보과학회논문지:시스템및이론
• /
• 제33권7호
• /
• pp.399-412
• /
• 2006

서버들이 서로 다른 데이타를 저장하고 있는 협동성 캐슁을 사용하는 클러스터링 기반의 무선 인터넷 프록시 서버에서는 Hot-Spot 혹은 임의의 입력 요청 패턴이 발생하면 일부 서버만 과부하가 되어 전체적인 성능이 떨어지는 문제점을 가진다. 본 논문에서는 기존 클러스터링이 가지는 Hot-Spot 및 임의의 입력 요청 패턴을 반영하지 못하는 문제점을 해결하기 위해 새로운 자체 학습 기반의 적응적 클러스터링 기법을 제안한다. 제안된 방법에서는 요청을 처리하는 일부 서버들이 과부하가 되면 해당 요청을 다른 서버들로 재 분산한다. 이러한 재 분산은 자체 학습 알고리즘에 의해 수행되고, 다양한 입력 패턴 혹은 서로 다른 성능의 서버들을 가지는 클러스터에도 적용이 가능하다 제안된 방법들은 16대의 컴퓨터와 부하 분산기를 가지고 클러스터링 환경에서 실험되었고, 실험 결과는 기존 방법들에 비해 54.62% 성능이 향상되었음을 보여준다.

• 대한지역사회영양학회지
• /
• 제6권1호
• /
• pp.97-107
• /
• 2001

The clustering of insulin resistance with hypertension, glucose intolerance, hyperinsulinemia, increased triglyceride and decreased HDL cholesterol levels, and central and overall obesity has been called syndrome X, or the insulin resistance syndrome(IRS). To develop a nutrition service for IRS, this study was performed to evaluate the prevalence of each component of the metabolic abnormalities of IRS and analyze the clustering pattern of IRS among subjects living in the Taegu community. Participants in this study were 9234(mean age ; M/F 48/40yrs);63.5% were men, 24.4% were obese, 13.3% had hypertension. 3.7% had hyperglycemia, and 32.4% had hyperlipidemia. The IRS was defined as the coexistence of two or more components among metabolic abnormalities; obesity, hypertension. hyperglucemia and hyperlipidemia. The prevalence of IRS in Taegu was 19.2%(M/F:20.8%/16.4%), the clustering of these fisk variables was higher in advanced age group. Among the subjects of IRS having two of more diseases, 75.6% were obese, the pattern were similar in men and women. The younger, the higher the prevalence of obesity associated clustering patterns. The prevalence of obesity associated patterns among the hyperglycemia associated clustering patterns was 44.5%. The samples of the representative clustering patterns were obesity and hyperlipidemia (8.0%), hypertension and hyperlipidemia(3.2%), hypertension, obesity and hyperlipiemia(3.1%), hypertension and obesity(2.3%), and hyperglycemia and hyperlipidemia(0.8%). The clustering of obesity and hyperlipidemia until 50 year old groups, and the clustering of hypertension and hyperlipidemia in the 60 and 70 age groups were the most prevalent. We concluded that insulin resistance syndrome was a relatively common disorder in the Taegu community, and prevalence and the characteristics of the intervention strategies for IRS are desired, an effective improvement will be achieved.

• Communications for Statistical Applications and Methods
• /
• 제12권2호
• /
• pp.335-348
• /
• 2005

The rapid development of microarray technologies enabled the monitoring of expression levels of thousands of genes simultaneously. Recently, the time course gene expression data are often measured to study dynamic biological systems and gene regulatory networks. For the data, biologists are attempting to group genes based on the temporal pattern of their expression levels. We apply the consensus clustering algorithm to a time course gene expression data in order to infer statistically meaningful information from the measurements. We evaluate each of consensus clustering and existing clustering methods with various validation measures. In this paper, we consider hierarchical clustering and Diana of existing methods, and consensus clustering with hierarchical clustering, Diana and mixed hierachical and Diana methods and evaluate their performances on a real micro array data set and two simulated data sets.

• Communications for Statistical Applications and Methods
• /
• 제27권6호
• /
• pp.589-602
• /
• 2020

The development of smart grids has enabled the easy collection of a large amount of power data. There are some common patterns that make it useful to cluster power consumption patterns when analyzing s power big data. In this paper, clustering analysis is based on distance functions for time series and clustering algorithms to discover patterns for power consumption data. In clustering, we use 10 distance measures to find the clusters that consider the characteristics of time series data. A simulation study is done to compare the distance measures for clustering. Cluster validity measures are also calculated and compared such as error rate, similarity index, Dunn index and silhouette values. Real power consumption data are used for clustering, with five distance measures whose performances are better than others in the simulation.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 추계종합학술대회 논문집(4)
• /
• pp.247-250
• /
• 2000

This paper proposes a finger crease pattern identification algorithm utilizing a clustering method. The algorithms has been developed for the use of biometric person identification system. Since the finger crease pattern may be well-imaged utilizing low cost imaging devices such as low-end CCD camera with LED lighting, the feasibility of commercialization of the algorithm and the system utilizing the algorithm may be well justified if the finger crease pattern is a reasonable choice for the biometric feature. In this paper, we exploit this possibility and show the potential of using the finger crease pattern as a feature for biometric person identification.

• 한국산업정보학회논문지
• /
• 제18권3호
• /
• pp.35-46
• /
• 2013

국내 전력 수요량 예측을 위한 정확한 분석 모델을 개발하기 위하여 고차원 데이터 군집 분석에 적합한 차원 축소 개념의 부분공간 군집 기법과 SMO 분류 기법을 결합한 전력 수요 패턴 예측 방법을 제안하였다. 전력 수요 패턴 예측은 무선부하감시 데이터 뿐 아니라 소지역 단위의 센서스 정보를 통합하여 시간대별 전력 부하 패턴 분석과 인구통계학 및 지리학적 특성 분석이 가능하다. 서울지역 대상의 센서스 정보 및 전력 부하를 이용한 소지역 전력 수요 패턴 예측 결과 총 18개의 특성 군집을 구성하였으며, 전력 수요 패턴 예측 정확도는 약 85%를 보였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제6권3호
• /
• pp.210-216
• /
• 2006

In the rule based modeling, data partitioning plays crucial role be cause partitioned sub data set implies particular information of the given data set or system. In this paper, we present an empirical study result of the data pattern estimation to find underlying data patterns of the given data. Presented method performs crisp type clustering with given n number of data samples by means of the sequential agglomerative hierarchical nested model (SAHN). In each sequence, the average value of the sum of all inter-distance between centroid and data point. In the sequel, compute the derivation of the weighted average distance to observe a pattern distribution. For the final step, after overall clustering process is completed, weighted average distance value is applied to estimate range of the number of clusters in given dataset. The proposed estimation method and its result are considered with the use of FCM demo data set in MATLAB fuzzy logic toolbox and Box and Jenkins's gas furnace data.

• 한국의류산업학회지
• /
• 제23권4호
• /
• pp.480-490
• /
• 2021

Sales forecasting is crucial for many retail operations. For apparel retailers, accurate sales forecast for the next season is critical to properly manage inventory and plan their supply chains. The challenge in this increases because apparel products are always new for the next season, have numerous variations, short life cycles, long lead times, and seasonal trends. In this study, a sales forecasting model is proposed for apparel products using machine learning techniques. The sales data pertaining to outerwear items for four years were collected from a Korean sports brand and filtered with outliers. Subsequently, the data were standardized by removing the effects of exogenous variables. The sales patterns of outerwear items were clustered by applying K-means clustering, and outerwear attributes associated with the specific sales-pattern type were determined by using a decision tree classifier. Six types of sales pattern clusters were derived and classified using a hybrid model of clustering and decision tree algorithm, and finally, the relationship between outerwear attributes and sales patterns was revealed. Each sales pattern can be used to predict stock-keeping-unit-level sales based on item attributes.