• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.1771-1774
• /
• 2003

Image segmentation is very important technique as preprocessing. It is used for various applications such as object recognition, computer vision, object based image compression. In this paper, a method which segments the multidimensional image using a hierarchical histogram approach, is proposed. The hierarchical histogram approach is a method that decomposes the multi-dimensional situation into multi levels of 1 dimensional situations. It has the advantage of the rapid and easy calculation of the histogram, and at the same time because the histogram is applied at each level and not as a whole, it is possible to have more detailed partitioning of the situation.

• 응용통계연구
• /
• 제31권4호
• /
• pp.517-528
• /
• 2018

다변량 자료에서 특이점을 검출하고, 검출된 특이점을 시각화와 연결한 R 스크립트를 제공한다. 개발된 R 스크립트는 특이점을 검출하는 방법으로서 1) Robust Mahalanobis distance, 2) High Dimensional data, 3) Density-based approach 방법을 이용하였다. 특이점을 연결하면서 데이터 구조를 파악하기 위한 시각화 방법으로는 1) multidimensional scaling (MDS)와 minimal spanning tree (MST)를 K-means 군집분석과 연결하여 표시하는 방법, 2) MDS를 fviz cluster와 연결하는 방법, 3) principal component analysis (PCA)를 fviz cluster와 연결한 방법을 이용하였다. 사례분석의 예로서는 Major League Baseball (MLB) 자료에서 류현진이 적극적으로 활동하던 2013년, 2014년 투수자료를 이용하였다. 개발된 R 스트립트는 "http://www.knou.ac.kr/~sskim/ddpoutlier.html (R 스크립트와 R 패키지도 다운로드 받을 수 있다. 실행방법도 설명되어 있다.)"에서 다운받으면 된다.

• Nuclear Engineering and Technology
• /
• 제54권9호
• /
• pp.3567-3579
• /
• 2022

This paper provides an assessment of fluid transport and mixing processes inside the primary circuit of the test facility ROCOM through the numerical simulation of Test 2.1 with the system code ATHLET. The experiment represents an asymmetric injection of cold and non-borated water into the reactor coolant system (RCS) of a pressurized water reactor (PWR) to restore core cooling, an emergency procedure which may subsequently trigger a core re-criticality. The injection takes place at low velocity under single-phase subcooled conditions and presents a major challenge for the simulation in lumped parameter codes, due to multidimensional effects in horizontal piping and vessel arising from density gradients and gravity forces. Aiming at further validating ATHLET 3-D capabilities against horizontal geometries, the experiment conditions are applied to a ROCOM model, which includes a newly developed horizontal pipe object to enhance code prediction inside coolant loops. The obtained results show code strong simulation capabilities to represent multidimensional flows. Enhanced prediction is observed at the vessel inlet compared to traditional 1-D approach, whereas mixing overprediction from the descending denser plume is observed at the upper-half downcomer region, which leads to eventual deviations at the core inlet.

• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.838-855
• /
• 2019

Online product reviews are a vital source for companies in that they contain consumers' opinions of products. The earlier methods of opinion mining, which involve drawing semantic information from text, have been mostly applied in one dimension. This is not sufficient in itself to elicit reviewers' comprehensive views on products. In this paper, we propose a novel approach in opinion mining by projecting online consumers' reviews in a multidimensional framework to improve review interpretation of products. First of all, we set up a new framework consisting of six dimensions based on a marketing management theory. To calculate the distances of review sentences and each dimension, we embed words in reviews utilizing Google's pre-trained word2vector model. We classified each sentence of the reviews into the respective dimensions of our new framework. After the classification, we measured the sentiment degrees for each sentence. The results were plotted using a radar graph in which the axes are the dimensions of the framework. We tested the strategy on Amazon product reviews of the iPhone and Galaxy smartphone series with a total of around 21,000 sentences. The results showed that the radar graphs visually reflected several issues associated with the products. The proposed method is not for specific product categories. It can be generally applied for opinion mining on reviews of any product category.

• ALGAE
• /
• 제31권1호
• /
• pp.1-16
• /
• 2016

Paralia species have been frequently reported as P. sulcata in Korea, despite the species diversity within the genus. To understand the species diversity of Paralia in Korea, we collected phytoplankton samples at 79 sites from April 2006 to April 2015. Five Paralia species, P. fenestrata, P. guyana, P. marina, P. cf. obscura, and P. sulcata, were observed during this study, and we described their fine structure in terms of quantitative and qualitative morphological characteristics. To provide additional criteria to identify Paralia species more clearly, we morphometrically analysed four quantitative characteristics on valve diameter: pervalvar axis / diameter, internal linking spines / diameter, marginal linking spines / diameter, and fenestrae/diameter using non-metric multidimensional scaling (MDS). MDS analysis distinguished four Paralia species: P. guyana, P. marina, P. cf. obscura, and P. sulcata, with the exception of P. fenestrata. This new approach in using morphometric analysis is useful for the accurate identification of Paralia species.

• 산업기술연구
• /
• 제20권B호
• /
• pp.213-218
• /
• 2000

The nearest neighbor query is an important operation widely used in multimedia databases for finding the object that is most similar to a given query object. Most of techniques for processing nearest neighbor queries employ multidimensional indexes for effective indexing of objects. However, the performance of previous multidimensional indexes, which use N-dimensional rectangles or spheres for representing the capsule of the object cluster, deteriorates seriously as the number of dimensions gets higher. This paper proposes a new index structure based singular value decomposition resolving this problem and the query processing method using it. We also verify the superiority of our approach through performance evaluation by performing extensive experiments.

• Asian Journal of Business Environment
• /
• 제2권1호
• /
• pp.5-13
• /
• 2012

The aim of this paper is to propose an integrative definition of key account management (KAM) at the organizational level through a content analysis of the existing definitions of KAM available in the business literatures. A representative pool of definitions of key account management was generated through literature review from twenty three journals that covers the divergence of name variety like global account management, strategic account management, national account management, international key account management, key client management, major account management, key customers management and key account management. Relating to the definition of key account management various attributes are identified through content analysis and according to the relevance, profile for each attributes are developed. On the basis of these attributes a diagrammatic and textual definition is proposed that covers the different standpoints and aspects of key account management approach and captures its essence as well. Eventually, several strategic implications are derived that create the field for further empirical investigation.

• Asian Journal of Innovation and Policy
• /
• 제12권3호
• /
• pp.277-303
• /
• 2023

The importance of ecosystem service such as green spaces has risen due to restrictions on outdoor activities amid the climate crisis and COVID-19. While gardens significantly impact economic development, quality of life, and social well-being, comprehensive studies on their multidimensional values are lacking. This research categorizes garden values into social, cultural, environmental, and health dimensions and proposes an integrated assessment framework that introduces detailed elements and evaluation methods. An empirical assessment of carbon storage index in two Korean gardens, Semiwon and Juknokwon, reveals Semiwon's higher carbon storage per unit area. The proposed framework, emphasizing a quantitative approach, enables cross-national and regional comparisons, contributing to a broader understanding and evaluation of garden values beyond specific facilities.

• 한국콘텐츠학회논문지
• /
• 제14권6호
• /
• pp.129-139
• /
• 2014

이 연구의 목적은 다양한 차원의 박탈지표를 이용하여 아동빈곤의 특성을 규명하는 것이다. 이 연구의 목적을 위해 2012년 7차 한국복지패널조사자료를 이용하였으며, 잠재집단 분석기법을 활용하여 아동빈곤 집단을 유형화하였다. 분석결과, 아동이 있는 가구를 주거비 과부담, 다차원 박탈, 비빈곤 등 세 개의 집단으로 유형화하였다. 주거비 과부담 집단은 다른 영역에서 박탈은 높지 않지만, 주거비 부담이 높은 집단이다. 다차원 박탈 집단은 열악한 주거환경, 식생활 영역 및 고용 등의 다양한 차원에서 박탈을 경험할 확률이 높은 집단이다. 마지막으로 비빈곤 집단은 박탈을 경험할 가능성이 매우 낮은 집단이다. 잠재집단의 특성을 파악하기 위해 다항로짓분석을 수행하였다. 분석결과, 다차원 박탈집단은 다른 두 집단과 차이가 있는 것으로 나타났다. 비빈곤 집단과 주거비 과부담 집단 간에는 큰 차이를 보이지 않는 것으로 나타났다. 분석결과는 아동이 거주하는 가구의 복지, 교육, 문화적 자원의 박탈 등 다차원적인 문제에 대한 통합적인 접근이 필요함을 시사한다.

• 정보처리학회논문지D
• /
• 제13D권6호
• /
• pp.765-774
• /
• 2006

연관 규칙 탐사는 데이터베이스를 분석하여 잠재되어 있는 지식을 발견하기 위한 기법으로 스트림 데이터 시스템에서 연관 규칙 탐사에 대한 연구가 활발하게 진행되고 있다. 그러나 대부분의 연구들은 센서에서 수집되는 단일 스트림 데이터에 관한 것이며 다차원 스트림 데이터간의 연관 정보는 간과하고 있다. 본 논문에서는 다차원 스트림 데이터간의 연관 규칙을 탐사할 수 있는 AR-MS 방법을 제안한다. AR-MS 방법은 한 번의 데이터 스캔으로 연관 규칙 탐사에 필요한 요약 정보를 구축함으로써 스트림 데이터의 특성을 반영하며, 자주 발생하지는 않지만 특정 이벤트와 빈번하게 발생하는 의미 있는 희소 항목 집합에 대한 연관 규칙을 탐사할 수 있다. 또한 AR-MS 방법은 구축된 요약 정보를 사용하여 다차원 스트림 데이터간의 최대 빈발 항목 집합에 대한 연관 규칙도 탐사한다. 그리고 다양한 실험을 통하여 제안하는 방법이 기존의 방법들에 비하여 우수함을 확인하였다.