• Title/Summary/Keyword: 분류이론

Search Result 1,251, Processing Time 0.035 seconds

Implementation of Web-based Document Classification System using Naïve Classifier (Naïve 분류기를 이용한 웹 기반 문서 분류기 구현)

  • Park, Jea-Hyun;Choi, Kwang-Bok;Han, Ju-Hyun;Choi, Won-Jong;Yang, Jaeyoung;Choi, Joongmin
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2004.05a
    • /
    • pp.343-346
    • /
    • 2004
  • 베이지안 확률 모형은 문서 분류에서 널리 사용되는 이론이다. 그러나, 실제로 베이지안 이론에 기초하여 만들어진 시스템은 처리 시간이 많이 소요된다는 단점을 가지고 있다. 이 논문에서는 문서 분류 작업에 있어 기존의 베이지안 모형을 구현함과 동시에 여러 가지 방법을 통해 시간적인 측면을 개선한 시스템을 구현하였다.

  • PDF

A theoretical study of design and Analysis of magnet-structure for a slotless spherical PMDC-mini motor (슬롯리스 구형직류모터에 사용되는 구형(球形)영구자석의 착자방법 및 착자구조에 관한 이론적 연구)

  • Kim, In-Ku
    • Proceedings of the KIEE Conference
    • /
    • 2003.04a
    • /
    • pp.19-21
    • /
    • 2003
  • 일반적으로 PMDC모터에 사용되는 자석은 가격과 재질에 따라서 여러 가지로 분류할 수 있다. 그러나 착자방법에는 등방향과 방사형 착자로 나눌 수 있고 용도에 따라서 다극으로 착자할 수 있다. 하지만 그 기본적인 구조에는 원통형, 판형, 육면체형으로 분류할 수 있는데 구형, 반구형 또는 구형 shell에 관한한 아직까지 소개된 문헌이 빈약하다. 본 논문에서는 슬롯리스 구형직류모터에 사용될 반구형 shell형태의 영구자석의 착자기 구조와 착자방법에 대한 가능성을 찾아보고 이론적으로 증명하고자 한다.

  • PDF

제어공학분야의 최근 국내외 동향

  • 양흥석
    • 전기의세계
    • /
    • v.23 no.5
    • /
    • pp.19-24
    • /
    • 1974
  • 현대제어이론 및 그 응용은 범위가 너무 넓기 때문에 여기서는 1970년 이후 수년간의 경향을 살펴보기로 하였다. 발표된 논문을 내용별로 분류하면 (가) 데이타처리 (나) 고정문제 (다)모델표현 (라)퍼래미터, 상태추정 (마)최적제어 (바)시스템의 응답해석 (사)안정문제등이다. 여기서는 IEEE의 분류법에 따라 계통별로 분류하였다.

  • PDF

The Improvements of the Physical Education Field in the 6th Edition of KDC (한국십진분류법 제6판 체육학 분야의 분류체계 개선방안)

  • Lee, Hee-Jin;Kim, Jeong-Hyen
    • Journal of the Korean BIBLIA Society for library and Information Science
    • /
    • v.24 no.4
    • /
    • pp.301-317
    • /
    • 2013
  • This study investigated general problems concerning the physical education field in the KDC 6th edition based on comparative analysis of academic characteristics and classification system, and suggested some ideas for the improvements of them. Results of this study are is summarized as follows. First, while the academic classification divided items focusing on theoretical disciplines such as physical education, sociology, or business administration, the library classification divided them into details according to sport entries. Second, We examined the classification status of the physical education field of the collection database in the National Library of Korea. The number of physical education field data was 38,585, and of them, that of books having classification codes starting with 692(physical education, sports) was 22,870. This shows that data actually have been published mainly based on academic characteristics rather than sport entries, which causes a problem due to concentration of many data on one classification code. Therefore, this study analyzed keywords around these classification codes. Third, modified classification of items was basically performed through the academic system of the physical education and the keyword analysis, and the typical KDC classification system was maintained as much as possible.

Types of Students' Responses to Anomalous Data (변칙 사례에 대한 학생들의 반응 유형)

  • Noh, Tae-Hee;Lim, Hee-Yeon;Kang, Suk-Jin
    • Journal of The Korean Association For Science Education
    • /
    • v.20 no.2
    • /
    • pp.288-296
    • /
    • 2000
  • In this study, the types and the characteristics of students' responses to anomalous data were investigated. The criteria for classifying students' responses were 'acceptance of validity of anomalous data', 'acceptance of inconsistency between anomalous data and initial theory', and 'change of belief in initial theory'. Seven types of responses were identified as follows: Rejection, reinterpretation, exclusion, uncertainty, peripheral theory change, partial belief change, and theory change. Absolute belief in the intial theory and doubts about methodological accuracy were found to be the major reasons for rejecting anomalous data. The students did not accept the inconsistency between anomalous data and initial theory because they ignored the experimental procedures and focused on the similarity of the experimental results.

  • PDF

최근방재이론의 세계적경향

  • 이귀학
    • 전기의세계
    • /
    • v.32 no.10
    • /
    • pp.582-587
    • /
    • 1983
  • 본고에서는 방재개설들을 거시분류법으로 나눠 자연재해방재, 인위적재해방재, 방위방재, 산업재해방재, 경제방재, 기능방재, 효과방재, 인간훽터방재로 전개했으며, 이는 방재이론을 브로드하게 표현하여 최근의 방재이론의 동향과 이론의 흐름을 소개하였다. 우리의 방재이론과 세계의 그것은 너무도 거리가 있으며 각분야에 방재훽터의 부여율은 후진국의 그것에 멈추고 있음을 실감할 수 있다. 아직 상아탑에서서의 연구는 자료 등의 부족으로 불가능 하겠으나 일백년전 미국이 각 메이커와 협회중심으로 각분야재해책을 연구하였듯이 우리도 각 분야에 종사하는 사람 각자가 방재의식을 갖고 "하고있는 일" 또는 "하려고하는 일에" 방재훽터를 부여하는 방법이 강구 되어야 하겠다.부여하는 방법이 강구 되어야 하겠다.

  • PDF

A Study on Principle and Theory of Main Classes in the Library Classification (문헌분류법에서의 주류설정의 원리)

  • Nam, Tae-Woo
    • Journal of the Korean Society for Library and Information Science
    • /
    • v.40 no.4
    • /
    • pp.333-366
    • /
    • 2006
  • The purpose of this study is principle and theory of main class in a Library Classification. According to Sayers, 'The foundation of the library is the book; the foundation of librarianship is classification.' We looked at the between scientific and bibliographic classification, and at the fact that bibliographic scheme is usually an aspect classification. That is to say, the organization of topics is based on areas or activity and the first division of the scheme is into disciplines or subject domains. This first division of classification creates what are called main class. The sequence of main classes is also important. A rough definition of a amin class is that it corresponds to a sin91e notational character. Main classes usually equivalent to traditional disciplines. What constitutes a main class will vary from one classification to another. The order in which the main classes are listed is often discussed at the theoretical level, and some orders are considered to be better than others.

Performance Analysis of Mulitilayer Neural Net Claddifiers Using Simulated Pattern-Generating Processes (모의 패턴생성 프로세스를 이용한 다단신경망분류기의 성능분석)

  • Park, Dong-Seon
    • The Transactions of the Korea Information Processing Society
    • /
    • v.4 no.2
    • /
    • pp.456-464
    • /
    • 1997
  • We describe a random prcess model that prvides sets of patterms whth prcisely contrlolled within-class varia-bility and between-class distinctions.We used these pattems in a simulation study wity the back-propagation netwoek to chracterize its perfotmance as we varied the process-controlling parameters,the statistical differences between the processes,and the random noise on the patterns.Our results indicated that grneralized statistical difference between the processes genrating the patterns provided a good predictor of the difficulty of the clssi-fication problem. Also we analyzed the performance of the Bayes classifier whith the maximum-likeihood cri-terion and we compared the performance of the neural network to that of the Bayes classifier.We found that the performance of neural network was intermediate between that of the simulated and theoretical Bayes classifier.

  • PDF

Defects Classification with UT Signals in Pressure Vessel Weld by Fuzzy Theory (퍼지이론을 이용한 압력용기 용접부 초음파 결함 특성 분류)

  • Sim, C.M.;Choi, H.L.;Baik, H.K.
    • Journal of the Korean Society for Nondestructive Testing
    • /
    • v.17 no.1
    • /
    • pp.11-22
    • /
    • 1997
  • It is very essential to get the accurate classification of defects in primary pressure vessel and piping welds for the safety of nuclear power plant. Ultrasonic testing has been widely applied to inspect primary pressure vessel and piping welds of nuclear power plants during PSI / ISI. Classification of flaws in weldments from their ultrasonic scattering signals is very important in quantitative nondestructive evaluation. This problem is ideally suited to a modern ultrasonic Pattern recognition technique. Here, a brief discussion on systematic approach to this methodology is presented including ultrasonic feature extraction, feature selection and classification. A stronger emphasis is placed on Fuzzy-UTSCS (UT signal classification system) as efficient classifiers for many practical classification problems. As an example Fuzzy-UTSCS is applied to classify flaws in ferrite pressure vessel weldments into two types such as linear and volumetric. It is shown that Fuzzy-UTSCS is able to exhibit higher performance than other classifiers in the defect classification.

  • PDF

An Iterative Approach to Contextual Classification of Remote Sensing Images (공간적 상관성의 반복적 결합을 이용한 원격탐사 화상 분류)

  • 박노욱;지광훈
    • Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
    • /
    • 2003.04a
    • /
    • pp.9-14
    • /
    • 2003
  • 본 연구에서는 원격탐사 화상의 분류를 목적으로 분광정보와 공간적 상관성의 반복적 결합방법을 제안하였다. 퍼지이론을 기반으로 공간적 상관성을 분류 과정에 적용하기 위하여 초기단계에서 정의된 소속 함수에 대해서 주변영역에 대한 필터링을 적용하였고, 특정 수렴 조건을 만족하는 단계까지 반복적 결합을 수행하였다. Landsat TM 화상에 적용한 결과, 향상된 분류정확도와 분광정보만으로 분류가 애매한 화소의 공간적 분포 양상을 확인할 수 있었다.

  • PDF