• Computational Structural Engineering
• /
• v.3 no.3
• /
• pp.58-61
• /
• 1990

교량유지관리 업무는 교량의 건설(신설), 노후교량의 개축, 교통량 증가에 따른 교량의 확장, 보수를 통한 원상복구, 또한 보수기록의 보관문제, 기존교량의 계속적인 점검 및 조사 등으로 분류된다. 이러한 문제를 전산화 하는 것은 필요항목들을 특성별로 분류하여 각 항목 등에 대한 데이타베이스를 구축하고 교량의 점검 및 조사 등을 통하여 교량의 손상상태를 파악함은 물론 개축, 보수, 확장, 신설 등에 대한 판정 및 그 우선순위를 제시하여 주는 의사결정시스템 개발이다. 본 고에서는 교량관리업무를 전산화하기 위해 한국건설기술연구원에서 개발한 교량관리용 DB(DATA BASE)시스템에 대하여 간략히 소개하고자 한다.

• The Korean Journal of Applied Statistics
• /
• v.27 no.5
• /
• pp.717-729
• /
• 2014

Projection pursuit classification tree uses a 1-dimensional projection with the view of the most separating classes in each node. These projection coefficients contain information distinguishing two groups of classes from each other and can be used to calculate the importance measure of classification in each variable. This paper reviews the variable importance measure with increasing interest in line with growing data size. We compared the performances of projection pursuit classification tree with those of classification and regression tree(CART) and random forest. Projection pursuit classification tree are found to produce better performance in most cases, particularly with highly correlated variables. The importance measure of projection pursuit classification tree performs slightly better than the importance measure of random forest.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.3
• /
• pp.14-24
• /
• 1996

A fuzzy classifier which needs various analyses of features using genetic algorithms is proposed. The fuzzy classifier has a simple structure, which contains a classification part based on fuzzy logic theory and a rule generation ation padptu sing genetic algorithms. The rule generation part determines optimal fuzzy membership functions and inclusior~ or exclusion of each feature in fuzzy classification rules. We analyzed recognition rate of a specific object, then added finer features repetitively, if necessary, to the object which has large misclassification rate. And we introduce repetitive analyses method for the minimum size of string and population, and for the improvement of recognition rates. This classifier is applied to three examples of the classification of iris data, the discrimination of thyroid gland cancer cells and the recognition of confusing handwritten and printed numerals. In the recognition of confusing handwritten and printed numerals, each sample numeral is classified into one of the groups which are divided according to the sample structure. The fuzzy classifier proposed in this paper has recognition rates of 98. 67% for iris data, 98.25% for thyroid gland cancer cells and 96.3% for confusing handwritten and printed numeral!;.

• Korean Journal of Remote Sensing
• /
• v.19 no.2
• /
• pp.135-147
• /
• 2003

This study used the multistage hierarchical clustering image classification to analyze the satellite images for the land-cover types of an area in the Korean peninsula. The multistage algorithm consists of two stages. The first stage performs region-growing segmentation by employing a hierarchical clustering procedure with the restriction that pixels in a cluster must be spatially contiguous, and finally the whole image space is segmented into sub-regions where adjacent regions have different physical properties. Without spatial constraints for merging, the second stage clusters the segments resulting from the previous stage. The image classification of hierarchical clustering, which merges step-by step two small groups into one large one based on the hierarchical structure of digital imagery, generates a hierarchical tree of the relation between the classified regions. The experimental results show that the hierarchical tree has the detailed information on the hierarchical structure of land-use and more detailed spectral information is required for the correct analysis of land-cover types.

• Proceedings of the Korea Contents Association Conference
• /
• 2019.05a
• /
• pp.425-426
• /
• 2019

전통적인 마이닝 기법은 다양한 디지털 매체와 센서 등에서 생산되는 빅데이터를 처리하기 어려울 뿐 아니라 신규 데이터 누적시 전체 데이터를 재분석 해야하는 비효율성과 대용량의 문서를 학습함에 있어 메모리부족 문제, 학습 소요시간 문제 등이 있다. 이러한 문제를 해결하기 위하여 본 논문에서는 자질축소 기법에 의존하지 않고 대량의 문서를 자유롭게 학습하고 부분적인 자질 추가 변경 시에 변경요소만을 추가 반영할 수 있는 범용적이고 일반적인 분류기의 구조설계 방법을 설계 및 구현하였다. 점진적 학습 모듈은 일반적인 학습 방법이 데이터의 추가 및 변동시마다 모든 데이터를 재학습하는 데 반해, 기존의 학습 결과에 증분된 데이터만 재처리 없이 추가적으로 학습한다. 재학습을 위해 사용자는 작업 수행 중 자원 관리를 통해 기존에 처리된 데이터를 자유롭게 가져와서 새로운 데이터와 병합이 가능하다. 이러한 점직적 학습 효율성은 빅데이터 기반 데이터 처리에 주요한 특성인 데이터 생산 속도를 극복하기 위한 좋은 대안이 될 수 있음을 확인하였다.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.6
• /
• pp.1571-1580
• /
• 1999

When a hierarchical structure is derived from data set for data mining and machine learning, using a conceptual clustering algorithm, one of the unsupervised learning paradigms, it is not unusual to have a different set of outcomes with respect to the order of processing data objects. To overcome this problem, the first classification process is proceeded to construct an initial partition. The partition is expected to imply the possible range in the number of final classes. We apply center sorting to the data objects in the classes of the partition for new data ordering and build a new partition using ITERATE clustering procedure. We developed an algorithm, REIT that leads to the final partition with stable and best partition score. A number of experiments were performed to show the minimization of order bias effects using the algorithm.

• Ecology and Resilient Infrastructure
• /
• v.8 no.2
• /
• pp.97-111
• /
• 2021

This study was conducted to develop a habitat type classification system and its map based on the ecological characteristics of species, spatial type, vegetation, topography, and geological conditions preferred by species. To evaluate the relationships between species and their habitats in Korean national parks, we prepared a classification standard table for systematic classification of habitat types. This classification system divides habitats into 6 low-level and 59 mid-level ecological classes based on habitat structure. The mid-level system divided forest ecosystems into 20 subtypes, stream and wetland ecosystems into 8 types, coastal ecosystems into 7 types, arable land into 6 types, development land into 9 types, and 1 type of marine ecosystem. A habitat classification map was drawn utilizing square images, detailed vegetation maps, and forest stand maps, based on the above habitat classification system, and it covered 1,461 plots spanning 21 national parks. The habitat classification system and survey protocol, which consider domestic habitat conditions, should be further developed and applied to habitat assessment, to enhance the utility of this study.

• Explosives and Blasting
• /
• v.24 no.1
• /
• pp.21-28
• /
• 2006

Rock mass classification systems such as RMR and Q system have been widely served as a simple empirical approach for the design of various rock mass structures in the stage of site survey as well as under the construction. For the RQD determination, the boring is partially carried out and what is more, the survey boring is not normally carried out under construction. Therefore RQD is frequently determined by empirical method or indirect method. Since it is difficult to determine the discontinuity characteristics such as RQD, spacing, persistence, filling and so on, it is essential to develop suitable and simple systems without drilled core and a cert 없 n number of representative parameters. One of the primary objectives of the classification systems for a practicing engineer has been to make it simple to use as a preliminary design tool for the structures in rock mass. In the present study, the modifications for both the RMR and GSI system are suggested by authors to introduce new classification system as well as to improve the scope of some of the existing classification systems for a practicing engineer.

• The Journal of the Korea Contents Association
• /
• v.18 no.1
• /
• pp.336-344
• /
• 2018

This research proposes a suitable classification and analysis standard for digital exhibition to analyze digital exhibition. Through the previous studies on digital exhibition classification, the necessity of the new standard is suggested and the analysis standard which can be easily applied to the change of concept and form of the newly emerging digital exhibition is established. Digital exhibition should take into account the elements of audience participation that naturally arise from exhibition planning and interactive storytelling format. Classification and analysis of existing digital exhibition spaces are conceptual classification based on keywords. This is because traditional exhibition methodology has been applied in the process of classifying exhibitions and works. However, in digital exhibitions, the interactive aspect between exhibition space, works, and visitors become so important that it is necessary to perform a performative classification between the works and the audience in the digital exhibition. Accordingly, the way of participating directly or indirectly in the exhibition classification should be considered based on what the audience feel. In this research, the interpretation of the classification and composition of the exhibition is based on Benjamin's argument which the classification of the sensory experience of the audience and 'Aktualisierung' closely related to the interaction with the audience. We also present analysis standard for digital exhibition according to the structure of the art exhibition narrative based on the narrative structure of Chatman. This classification methodology will provide the exhibition information in a way that can be easily understood by the visitors and it will be a precedent research that secures the expansion and accessibility of the digital exhibition.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.1
• /
• pp.131-141
• /
• 2016

SRM is designed to meet operating standards such as low cost, simple magnetic structure, a desired operating speed range, high efficiency, high performance, and good matching for DC power. The magnetic flux of SRM is independent of its direction to develop a torque and it allows the flexible characteristics of the magnetic structure for SRM. In this paper, SRM can widely classify two types, Radial-Flux SRM and Axial-Flux SRM, according to the flux direction. Radial-Flux SRM includes Conventional, Segmented stator and rotor, and Double stator SRM, etc. and Axial-Flux SRM includes C-core stator and the Axial-airgap SRM. This paper is subjected the basic characteristics to select the best of the magnetic structure of SRM in the appropriate application by the classification of SRM.