• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2007년도 Proceedings of ISRS 2007
• /
• pp.341-344
• /
• 2007

A major obstacle to classify and validate Land Cover maps is the high cost of generating reference data or multiple thematic maps for subsequent comparative analysis. In case of inaccessible area such as North Korea, the high resolution satellite imagery may be used as in situ data so as to overcome the lack of reliable reference data. The objective of this paper is to investigate the possibility of utilizing QuickBird (0.6m) of North Korea obtained from Google Earth data provided thru internet. Monthly NDVI images of nine months from the summer of 2004 were classified into L=54 cluster using ISODATA algorithm, and these L clusters were assigned to 7 classes; coniferous forest, deciduous forest, mixed forest, paddy field, dry field, water and built-up area. The overall accuracy and Kappa index were 85.98% and 0.82, respectively, which represents about 10% point increase of classification accuracy than our previous study based on GCP point data around North Korea. Thus we can conclude that Google Earth may be used to substitute the traditional in situ data collection on the site where the accessibility is severely limited.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.1287-1292
• /
• 2005

This paper presents an effective pattern classification model by designing an artificial neural network based pattern classifiers for face recognition. First, a RGB image inputted from a frame grabber is converted into a HSV image which is similar to the human beings' vision system. Then, the coarse facial region is extracted using the hue(H) and saturation(S) components except intensity(V) component which is sensitive to the environmental illumination. Next, the fine facial region extraction process is performed by matching with the edge and gray based templates. To make a light-invariant and qualified facial image, histogram equalization and intensity compensation processing using illumination plane are performed. The finally extracted and enhanced facial images are used for training the pattern classification models. The proposed H-ART2 model which has the hierarchical ART2 layers and F-LVQ model which is optimized by fuzzy membership make it possible to classify facial patterns by optimizing relations of clusters and searching clustered reference patterns effectively. Experimental results show that the proposed face recognition system is as good as the SVM model which is famous for face recognition field in recognition rate and even better in classification speed. Moreover high recognition rate could be acquired by combining the proposed neural classification models.

• 전자공학회논문지CI
• /
• 제47권3호
• /
• pp.36-41
• /
• 2010

본 논문에서는 다단계 특성벡터 기반의 분류기 모델(Multistage Feature-based Classification Model: MFCM)의 성능을 향상시킨 진보된 형태의 MFCM (Advanced MFCM: AMFCM)을 제안하는데, AMFCM은 MFCM과 같이 주어진 데이터에서 추출된 전체의 특징벡터를 연결하여 이용하지 않고, 같은 성질의 특징벡터들끼리 모아서, 각각의 국지적 학습기를 통하여 분류에 이용한다. 그러나, AMFCM은 MFCM에서 사용되는 각각의 국지적 분류기를 위한 각 특징벡터의 분류기여도를 더욱 섬세하게 조정하여 최종적인 분류의 정확도를 높이는 방안을 제안한다. 제안된 AMFCM의 성능을 검증하기 위하여, 음악장르 분류의 문제에 대한 실험을 진행하였다. 또한, 국지적 분류기로 Self-Organizing Map과 중심 신경망을 사용하여 실험을 수행하였는데, 제안된 AMFCM은 사용된 국지적 분류기의 종류와 사용된 군집의 개수에 따라 기존의 MFCM에 비해 평균 8% - 15% 이상의 성능향상을 보여 준다.

• 대한전기학회논문지:전력기술부문A
• /
• 제55권4호
• /
• pp.172-178
• /
• 2006

In this paper, an advanced demand clustering algorithm which can explore the planned maintenance outage of generators in changed electricity industry is proposed. The major contribution of this paper can be captured in the development of the long-term estimates for the generation availability considering planned maintenance outage. Two conflicting viewpoints, one of which is reliability-focused and the other is economy-focused, are incorporated in the development of estimates of maintenance outage based on the advanced demand clustering algorithm. Based on the advanced clustering algorithm, in each demand cluster, conventional effective outage of generators which conceptually capture maintenance and forced outage of generators, are newly defined in order to properly address the characteristic of the planned maintenance outage in changed electricity markets. First, initial market demand is classified into multiple demand clusters, which are defined by the effective outage rates of generators and by the inherent characteristic of the initial demand. Then, based on the advanced demand clustering algorithm, the planned maintenance outages and corresponding effective outages of generators are reevaluated. Finally, the conventional demand clusters are newly classified in order to reflect the improved effective outages of generation markets. We have found that the revision of the demand clusters can change the number of the initial demand clusters, which cannot be captured in the conventional demand clustering process. Therefore, it can be seen that electricity market situations, which can also be classified into several groups which show similar patterns, can be more accurately clustered. From this the fundamental characteristics of power systems can be more efficiently analyzed, for this advanced classification can be widely applicable to other technical problems in power systems such as generation scheduling, power flow analysis, price forecasts, and so on.

• 한국병원경영학회지
• /
• 제28권2호
• /
• pp.9-20
• /
• 2023

Purpose: This study classified the actual functions of geriatric hospitals and examined the differences in their characteristics, in order to provide a basis for discussions on defining the functions of geriatric hospitals and how to pay for care. Methodology: This study used various administrative data such as health insurance data and long-term care insurance data. Cluster analysis was used to categorize geriatric hospitals. To examine the validity of the cluster analysis results, we conducted a discriminant analysis to calculate the accuracy of the classification. To examine cluster characteristics, we examined structure, process, and outcome indicators for each cluster. Findings: The cluster analysis identified five clusters. They were geriatric hospitals with relatively short stays for cancer patients(cluster 1; cancer patient-centered), geriatric hospitals with relatively large numbers of patients using rehabilitation services(cluster 2; rehabilitation patient-centered), geriatric hospitals with a high proportion of relatively severe elderly patients(cluster 3; severe elderly patient-centered), geriatric hospitals with a high proportion of mildly ill elderly patients with various conditions(cluster 4; mildly ill elderly patient-centered), and geriatric hospitals with a significantly higher proportion of dementia patients(cluster 5; dementia patient-centered). The largest number of geriatric hospitals were categorized in clusters 4 and 5, and the structure and process indicators for these clusters were generally lower than for the other clusters. Practical Implications: We have confirmed the existence of geriatric hospitals where the medical function, which is the original purpose of a geriatric hospital, has been weakened. It has been observed that the quality level of these geriatric hospitals is likely to be lower compared to hospitals that prioritize enhanced medical functions. Therefore, it is suggested to consider the conversion of these geriatric hospitals into long-term care facilities, and careful consideration should be given to the review of care-giver payment coverage.

• 한국산림과학회지
• /
• 제104권3호
• /
• pp.375-382
• /
• 2015

속리산 천왕봉 일대의 천연림을 대상으로 식생 단위별 생태적 시업방안을 도출하기 위한 기초자료를 제공하기 위해 산림형을 구분하고 각 산림형별로 생태적 특성을 파악하였다. 사분각법을 적용하여 250개의 표본점을 추출하였고, 각 표본점 마다 층위별 식생자료를 수집하였다. 연구대상지의 산림형을 구분하기 위해 다양한 다변량 통계분석 기법을 이용하였으며, 산림형별 식생의 안정성과 성숙도를 파악하기 위해 종다양성지수를 분석하였다. 군집분석을 통해 2~10개의 Cluster로 산림형을 분류하였고, 지표종분석으로 적절한 Cluster의 수를 5개로 추정하였으며, 다중판별분석으로 추정된 Cluster 수가 적절했음을 검증하였다. 5개의 산림형별로 수종구성을 분석한 결과, 계곡부에서는 졸참나무림과 중생혼합림, 능선부에서는 신갈나무림, 주능선에서 뻗어 나온 보조능선부에서는 소나무림, 보조능선과 계곡부 사이에서는 굴참나무-소나무림 등으로 분류되었으며, 전체적으로 참나무류와 소나무가 우점하는 것으로 나타났다. 상층의 수종 구성이 단조로운 소나무림의 종다양성지수가 가장 낮았던 반면, 식생 구성이 다양한 중생혼합림의 경우 종다양성지수가 가장 높은 것으로 나타나 식생구성이 다양할수록 종다양성지수가 증가하는 양상을 보였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권9호
• /
• pp.1161-1170
• /
• 2004

본 논문에서는 군집화 알고리즘을 사용하여 피부색 영역을 분할하는 방법을 제안한다. 기존의 군집화 알고리즘들의 대부분은 주로 구형의 군집을 검출하고, 배치형으로 수행되며, 군집의 개수를 미리정해야 한다는 문제점을 가지고 있다. 본 논문에서는 대표적인 타원형 군집화 알고리즘인 EM 알고리즘을 변형하여, 온라인으로 학습가능하며, 군집의 개수를 자동적으로 찾아낼 수 있는 EAM 알고리즘을 사용하였다. EAM 알고리즘외 유효성은 피부색 영역 분할에 대해 증명되었다. 실험결과는 군집의 개수가 미리 주어지지 않더라도, EAM 알고리즘은 주어진 영상에 대해 자동적으로 옳은 군집의 개수를 찾아냈고, EM 알고리즘과 비교하여 더 좋은 분할 결과를 보여주고 있다. 영역에 대한 조건부 확률을 이용하여 성공적인 피부색 영역의 탐지 및 분할 결과를 얻었다. 또한 사람이 포함된 영상을 분류하는 문제에도 적용하여 좋은 분류 결과를 얻었다.

• International Journal of Oral Biology
• /
• 제43권2호
• /
• pp.101-111
• /
• 2018

Understanding the classification of malocclusion is a crucial issue in Orthodontics. It can also help us to diagnose, treat, and understand malocclusion to establish a standard for definite class of patients. Principal component analysis (PCA) and k-means algorithms have been emerging as data analytic methods for cephalometric measurements, due to their intuitive concepts and application potentials. This study analyzed the macro- and meso-scale classification structure and feature basis vectors of 1020 (415 male, 605 female; mean age, 25 years) orthodontic patients using statistical preprocessing, PCA, random matrix theory (RMT) and k-means algorithms. RMT results show that 7 principal components (PCs) are significant standard in the extraction of features. Using k-means algorithms, 3 and 6 clusters were identified and the axes of PC1~3 were determined to be significant for patient classification. Macro-scale classification denotes skeletal Class I, II, III and PC1 means anteroposterior discrepancy of the maxilla and mandible and mandibular position. PC2 and PC3 means vertical pattern and maxillary position respectively; they played significant roles in the meso-scale classification. In conclusion, the typical patient profile (TPP) of each class showed that the data-based classification corresponds with the clinical classification of orthodontic patients. This data-based study can provide insight into the development of new diagnostic classifications.

• 대한인간공학회지
• /
• 제13권2호
• /
• pp.25-31
• /
• 1994

This research examines classifying and characterizing breast form's classification on elderly women, 242 subjects from 55 to 75 years of age participated. 27 direct anthropometric measurement were applied to classify the breast typesl. We analyzed measurement data using factor analysis, cluster analysis, analysis of variance. The results of the study were as follows. 1) 55-64 aged group was taller and higher than 65-79 aged group. Typical breast form in 55-64 aged group was more obese than breast form in 65-79 aged group. 2) We extracted 5 factors(obesity of breast, height of breast, height of breast items, location & size of breast, width of upper chest & shouldet length, height of breast & lower length of nipples) from total items through factor analysis. 3) Through cluster analysis, we categorized 3 clusters. Namely, type 1; characterized the best slender type, type 2; characterized middle sized type, type 3: characterized obesity type. Type 2 is the typical type on elderly women.

• 산업공학
• /
• 제15권2호
• /
• pp.182-188
• /
• 2002

Clustering is widely used in various fields in order to investigate structural characteristics of the given data. One of the main tasks of clustering is to partition a set of objects into homogeneous groups for the purpose of data reduction. In this paper a simple but computationally efficient clustering procedure is devised and some statistical techniques to validate its clustered results are discussed. In the given procedure, the proper number of clusters and the clustered groups can be determined simultaneously. The whole procedure is applied to a practical clustering problem for the classification of reusable fuels in nuclear power plants.