• 디지털융복합연구
• /
• 제12권12호
• /
• pp.227-232
• /
• 2014

전 세계적으로 기술의 융합은 과학기술 분야에서 메가트렌드를 형성하고 있으며 선진국에서는 자국이 보유한 강점 기술을 기반으로 하는 새로운 융합기술의 도출에 주력하고 있다. 융복합과제의 융합지수를 도출함에 있어서 임의로 융합지수를 올리기 위한 조작이 가능하고, 사업계획서의 내용과 다소 차이가 있는 항목들이 추가되어 융합지수가 산출되는 등의 문제점이 예상되지만 평가 시에 이를 검증하기가 쉽지 않다. 따라서 본 논문에서는 융복합과제에 대한 융합지수 도출 시 연계되는 항목을 정하여 일관성을 유지할 수 있도록 하고, 평가 시 에도 이를 쉽게 확인할 수 있도록 하는 방안에 대해 제시하였다.

• 한국문헌정보학회지
• /
• 제44권2호
• /
• pp.241-262
• /
• 2010

본 연구에서는 국내 주요 검색 포털들인 네이버, 네이트, 다음, 야후에서 제공하는 서비스들의 분류체계를 분류체계의 일관성, 분류체계의 논리성, 인터페이스의 일관성, 카테고리명의 명확성, 카테고리 및 사이트 배열 순서, 계층 구조 설계 등의 관점에서 비교, 분석하였다. 이러한 기준에 따라 조사한 결과, 동일한 포털에서 제공하는 서비스들이 공통점이 거의 없는 독자적인 분류체계를 구축, 운영하고 있는 것으로 나타났다. 따라서 향후 포털들의 통합 분류체계 구축과 인터페이스 표준화가 요구된다. 본 연구의 결과는 포털들의 분류체계의 개선에 활용될 수 있을 것으로 기대된다.

• 한국문헌정보학회지
• /
• 제40권2호
• /
• pp.415-434
• /
• 2006

우리 고전 문집에 나타난 용어로 작성된 디스크립터들을 분류하기 위해서 분류 체계를 개발하는 것이 이 연구의 목적이다. 고전 용어 시소러스의 분류 구조는 6개의 패싯으로 범주화를 시작하여 고전 분야의 지식을 근거로 연역적으로 분류 체계를 구조화하였다. 그리고 기존의 인문학 분야의 다른 시소러스들의 분류 체계와 비교하였고, 이러한 비교를 통해서 얻은 것은 고전 용어 분류 체계만이 갖는 여러 장점들 즉 패싯 기법을 적용한 장점 등을 확인할 수 있었다. 이러한 장점들로 인해서 범주 설정의 일관성과 분류 구조의 복잡성을 줄일 수 있었다. 또한 시대나 지역을 구분하기 위한 공통 구분을 독립적으로 설정하여 분류표의 크기를 줄일 수 있었다. 이 분류 체계는 디스크립터들을 배정하는 과정을 통해 보다 나은 분류 체계로 발전해 나갈 것이다.

• 한국의류학회지
• /
• 제44권2호
• /
• pp.354-368
• /
• 2020

Accurate and versatile image data-sets are essential for fashion AI research and AI-based fashion businesses based on a systematic attribute classification system. This study constructs a color and texture attribute hierarchical classification system by collecting fashion item images and analyzing the metadata of fashion items described by consumers. Essential dimensions to explain color and texture attributes were extracted; in addition, attribute values for each dimension were constructed based on metadata and previous studies. This hierarchical classification system satisfies consistency, exclusiveness, inclusiveness, and flexibility. The image tagging to confirm the usefulness of the proposed classification system indicated that the contents of attributes of the same image differ depending on the annotator that require a clear standard for distinguishing differences between the properties. This classification system will improve the reliability of the training data for machine learning, by providing standardized criteria for tasks such as tagging and annotating of fashion items.

• 한국문헌정보학회지
• /
• 제36권2호
• /
• pp.265-284
• /
• 2002

본 연구의 목적은 원문정보를 데이터베이스로 구축하여 이용자에게 제공하는 국회도서관의 전자도서관시스템에 대한 이용자들의 기대와 만족을 살펴보고, 이용자들의 기대와 만족에서 얼마나 차이를 나타내는가를 분석하고자 한 것이다. 설문지를 분석한 결과에 의하면 정보의 양, 정보의 최신성, 정보의 질, 분류의 체계성, 정보의 일관성, 정보의 정확성은 전체 기대수준의 평균보다 높게 나타나고, 응답의 속도 정보의 질, 정보의 일관성, 검색의 편리성, 정보의 양, 정보의 정확성은 전체 만족수준의 평균보다 높게 나타나고 있다. 분석대상요인 전체에서 정보의 최신성, 정보의 양, 정보의 다양성, 분류의 체계성, 정보의 정확성은 기대와 만족의 차이가 높은 편으로 나타나고 있다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.1409-1411
• /
• 2003

The application of simulated KOMPSAT-2 imagery to monitor graveyards is to be developed. Positions calculated from image were compared with those obtained from Geographic Positioning System. With 24 checkpoints, the position of graveyards showed within 5-meter range. Unsupervised classification, supervised classification, and objected-orientation classification algorithms were used to extract the graveyard. Unsupervised classification with masking processes based on National topographic data gives the best result. The graveyards were categorized with four types in field studies while the two types of graveyards were shown in descriptive statistics. Cluster Analysis and discriminant analysis showed the consistency with two types of tombs. It was hard to get a specific spectral signature of graveyards, as they are covered with grasses at different levels and shaded from the surrounding trees. The slopes and aspects of location of graveyards did not make any difference in the spectral signatures. This study gives the basic spectral characteristics for further development of objected-oriented classification algorithms and plausibility of KOMPSAT-2 images for management of mountainous areas in the aspect of position accuracy and classification accuracy.

• 한국비블리아학회지
• /
• 제8권1호
• /
• pp.197-227
• /
• 1997

The main purpose of this study is ① to settle and to analyze the classification of the Internet Search Engine comparitively, and ② to build the compatible model of Internet Search Engine classification in order to seek information on the Internet resources. specially in the branch of the Computers and Internet areas. For this study, four Internet Search Engine (Excite, 1-Detect, Simmany, Yahoo Korea!), Inspec Classification and two distionaries were used. The major findings and result of analysis are summarized as follows : 1. The basis of the classification is the scope of topics, the system logic, the clearness, the efficiency. 2. The scope of topics is analyzed comparitively by the number of items from each Search Engine. In the result, Excite is the most superior of the four 3. The system logic is analyzed comparitively by the casuality balance and consistency of the items from each Search Engine. In the result, Excite is the most superior of the four 4. The clearness is analyzed comparitively by the clearness and accuracy of items, the recognition of the searchers. In the result, Excite is the most superior of the four. 5 The efficiency is analyzed comparitively by the exactness of indexing and decreasing the effort of the searchers. In the result, Yahoo Korea！ is the most superior of the four. 6 The compatible model of Internet Search Engine classification is estavlished to uplift the scope of topics, the system logic, the clearness, and the efficiency. The model divides the area mainly based upon the topics and resources using‘bookmark’and‘shadow’concept.

• Communications for Statistical Applications and Methods
• /
• 제10권3호
• /
• pp.879-894
• /
• 2003

We evaluated the efficiencies of applying attribute selection methods and prior discretization to supervised learning, modelled by C4.5 and Naive Bayes. Three databases were obtained from UCI data archive, which consisted of continuous attributes except for one decision attribute. Four methods were used for attribute selection : MDI, ReliefF, Gain Ratio and Consistency-based method. MDI and ReliefF can be used for both continuous and discrete attributes, but the other two methods can be used only for discrete attributes. Discretization was performed using the Fayyad and Irani method. To investigate the effect of noise included in the database, noises were introduced into the data sets up to the extents of 10 or 20%, and then the data, including those either containing the noises or not, were processed through the steps of attribute selection, discretization and classification. The results of this study indicate that classification of the data based on selected attributes yields higher accuracy than in the case of classifying the full data set, and prior discretization does not lower the accuracy.

• Communications for Statistical Applications and Methods
• /
• 제24권6호
• /
• pp.543-559
• /
• 2017

Tree-based regression and classification ensembles form a standard part of the data-science toolkit. Many commonly used methods take an algorithmic view, proposing greedy methods for constructing decision trees; examples include the classification and regression trees algorithm, boosted decision trees, and random forests. Recent history has seen a surge of interest in Bayesian techniques for constructing decision tree ensembles, with these methods frequently outperforming their algorithmic counterparts. The goal of this article is to survey the landscape surrounding Bayesian decision tree methods, and to discuss recent modeling and computational developments. We provide connections between Bayesian tree-based methods and existing machine learning techniques, and outline several recent theoretical developments establishing frequentist consistency and rates of convergence for the posterior distribution. The methodology we present is applicable for a wide variety of statistical tasks including regression, classification, modeling of count data, and many others. We illustrate the methodology on both simulated and real datasets.

• 대한치과기공학회지
• /
• 제46권2호
• /
• pp.36-41
• /
• 2024

Purpose: This study aimed to generate virtual mandibular left first molar teeth using deep convolutional generative adversarial networks (DCGANs) and analyze their matching accuracy with actual tooth morphology to propose a new paradigm for using medical data. Methods: Occlusal surface images of the mandibular left first molar scanned using a dental model scanner were analyzed using DCGANs. Overall, 100 training sets comprising 50 original and 50 background-removed images were created, thus generating 1,000 virtual teeth. These virtual teeth were classified based on the number of cusps and occlusal surface ratio, and subsequently, were analyzed for consistency by expert dental technicians over three rounds of examination. Statistical analysis was conducted using IBM SPSS Statistics ver. 23.0 (IBM), including intraclass correlation coefficient for intrarater reliability, one-way ANOVA, and Tukey's post-hoc analysis. Results: Virtual mandibular left first molars exhibited high consistency in the occlusal surface ratio but varied in other criteria. Moreover, consistency was the highest in the occlusal buccal lingual criteria at 91.9%, whereas discrepancies were observed most in the occusal buccal cusp criteria at 85.5%. Significant differences were observed among all groups (p<0.05). Conclusion: Based on the classification of the virtually generated left mandibular first molar according to several criteria, DCGANs can generate virtual data highly similar to real data. Thus, subsequent research in the dental field, including the development of improved neural network structures, is necessary.