• Title/Summary/Keyword: domain knowledge

Search Result 1,002, Processing Time 0.028 seconds

Explanation-based Data Mining in Data Warehouse (데이터 웨어하우스 환경에서의 설명기반 데이터 마이닝)

  • 김현수;이창호
    • Proceedings of the Korea Inteligent Information System Society Conference
    • /
    • 1999.03a
    • /
    • pp.115-123
    • /
    • 1999
  • 산업계 전반에 걸친 오랜 정보시스템 운용의 결과로 대용량의 데이터들이 축적되고 있다. 이러한 데이터로부터 유용한 지식을 추출하기 위해 여러 가지 데이터 마이닝 기법들이 연구되어왔다. 특히 데이터 웨어하우스의 등장은 이러한 데이터 마이닝에 있어 필요한 데이터 제공 환경을 제공해 주고 있다. 그러나 전문가의 적절한 판단과 해석을 거치지 않은 데이터 마이닝의 결과는 당연한 사실이거나, 사실과 다른 가짜이거나 또는 관련성 없는(trivial, spurious and irrelevant)내용만 무수히 쏟아낼 수 있다. 그러므로 데이터 마이닝의 결과가 비록 통계적 유의성을 가진다 하더라도 그 정당성과 유용성에 대한 검증과정과 방법론의 정립이 필요하다. 데이터 마이닝의 가장 어려운 점은 귀납적 오류를 없애기 위해 사람이 직접 그 결과를 해석하고 판단하며 아울러 새로운 탐색 방향을 제시해야 한다는 것이다. 본 논문에서는 데이터 마이닝 기법 중 연관규칙탐사로 얻어진 결과를 설명가능성 여부의 판단을 통해 검증하는 기법을 제안하며, 이를 통해 얻어진 검증된 지식을 토대로 일반화를 통한 새로운 가설을 생성하여 데이터 웨어하우스로부터 연관규칙을 검증하는 일련의 아텍쳐(architecture)를 제시하고다 한다. 먼저 데이터 마이닝 결과에 대한 설명의 필요성을 제시하고, 데이터 웨어하우스와 데이터 마이닝 기법들에 대한 간략한 설명과 연관규칙탐사에 대한 정의 및 방법을 보이고, 대상 영역에 대한 데이터 웨어하우스으 스키마를 보였다. 다음으로 도메인 지식(domain knowledge)과 연관규칙탐사를 통해 얻어진 결과를 표현하기위한 지식표현 방법으로 Relational Predicate Logic을 제안하였다. 연관규칙탐사로 얻어진 결과를 설명하기 위한 방법으로는 연관규칙탐사로 얻어진 연관규칙에 대해 Relational Predicate Logic으로 표현된 도메인 지식으로서 설명됨을 보이게 한다. 또한 이러한 설명(explanation)을 토대로 검증된 지식을 일반화하여 새로운 가설을 연역적으로 생성하고 이를 연관규칙탐사를 통해 검증한 후 새로운 지식을 얻는 반복적인 Explanation-based Data Mining Architecture를 제시하였다. 본 연구의 의의로는 데이터 마이닝을 통한 귀납적 지식생성에 있어 귀납적 오류의 발생을 도메인 지식을 통해 설명가능 함을 보임으로 검증하고 아울러 이러한 설명을 통해 연역적으로 새로운 가설지식을 생성시켜 이를 가설검증방식으로 검증함으로써 귀납적 접근과 연역적 접근의 통합 데이터 마이닝 접근을 제시하였다는데 있다.

  • PDF

A Study on the Process for Web Domain Applications Development Based on the UML+Navigation Diagrma (UML+Navigation Diagram 기반 웹 도메인 응용 개발 프로세스에 관한 연구)

  • Kim, Haeng-Kon;Shin, Ho-Jun
    • The Transactions of the Korea Information Processing Society
    • /
    • v.7 no.9
    • /
    • pp.2846-2856
    • /
    • 2000
  • Recently, according to the rapid development of web technology, a lot of applications based on web techniques have been developed. However, most of web applications have been developed relying on knowledge and experiences of the developer without systematic process. Web Applications are seldom developed in isolation. For web application designers, the simple and semantically rich methodology is needed to improve design and development process. In this paper, we propose a new development process methodology to improve low level technology based application development process which do not provide high level abstraction. We also suggest a new methodology to construct applications based on web. We describe a systematic web application development process by using Navigation Diagram as a analysis, design modeling method to develop web application with productivity and Quality. We apply the new development process to the EPBS(Electronic Problem Bank System) as examples. Web application development process proposed in this thesis can be maintained through reverse development, because it can be defined as high level abstraction for modeling. It is very easy to be understood as a process based on models. Also, analysis and design models can be reused as useful component whenever similar web application is developed.

  • PDF

Ontology Alignment by Using Discrete Cuckoo Search (이산 Cuckoo Search를 이용한 온톨로지 정렬)

  • Han, Jun;Jung, Hyunjun;Baik, Doo-Kwon
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.3 no.12
    • /
    • pp.523-530
    • /
    • 2014
  • Ontology alignment is the way to share and reuse of ontology knowledge. Because of the ambiguity of concept, most ontology alignment systems combine a set of various measures and complete enumeration to provide the satisfactory result. However, calculating process becomes more complex and required time increases exponentially since the number of concept increases, more errors can appear at the same time. Lately the focus is on meta-matching using the heuristic algorithm. Existing meta-matching system tune extra parameter and it causes complex calculating, as a consequence, the results in the various data of specific domain are not good performed. In this paper, we propose a high performance algorithm by using DCS that can solve ontology alignment through simple process. It provides an efficient search strategy according to distribution of Levy Flight. In order to evaluate the approach, benchmark data from the OAEI 2012 is employed. Through the comparison of the quality of the alignments which uses DCS with state of the art ontology matching systems.

A Software Architecture Design Method that Matches Problem Frames and Architectural Patterns (문제틀과 아키텍처 패턴의 매칭을 이용한 소프트웨어 아키텍처 설계 방법)

  • Kim, Jungmin;Kang, Sungwon;Lee, Jihyun
    • Journal of KIISE
    • /
    • v.42 no.3
    • /
    • pp.341-360
    • /
    • 2015
  • While architectural patterns provide software development solutions by providing schemas for structural organizations of software systems based on empirical knowledge, Jackson's problem frames provide a method of analyzing software problems. Problem frames are useful to understanding the software development problem, by putting emphasis on the problem domain, rather than on the solution space. Research exists that relates problem frames and software architecture, but most of this research uses problem frames only to understand given problems. Moreover, none of the existing research derives architectural patterns by considering both problem frames and quality attributes. In this paper, we propose a software architecture design method for pattern-based architecture design, by matching problem frames and architectural patterns. To that end, our approach first develops the problem model based on the problem frames approach, and then uses it to match with candidate architectural patterns, from the perspectives of both functionality, and quality attributes. Functional matching uses the problem frame diagram to match the problem model of an architectural pattern. We conduct a case study to show that our approach can systematically decide the right architectural patterns, and provide a basis for fine-grained software architecture design.

Comparison of Textbook Objectives and Paper Test Items Based on Physics I 'Space-Time and the Universe' (고등학교 물리 I '시공간과 우주' 단원의 지필평가 문항과 교과서 목표와의 비교)

  • Yang, Donghyuk;Yun, Eunjeong;Park, Yunebae
    • Journal of Science Education
    • /
    • v.44 no.1
    • /
    • pp.38-49
    • /
    • 2020
  • The purpose of this study is to analyze the paper test items of high school physics I 'Space-Time and the Universe' unit and how similar the textbook goals are to the cognitive and content areas. This study analyzed paper test items used from nine high schools and KICE about the unit. In order to analyze the distribution of items, they were classified by contents and by cognitive level which is knowledge, comprehension and application levels. As conclusion, application level items were a few, and unbalanced contents distribution appeared in school items. In comparison through the ratio difference index, the objectives of the textbook and the school items were very similar, but the similarities were low when comparing the school items with the KICE items. Based on the above, we suggested some ways to increase the validity of test items.

The Access-Enhanced Search Interface Design for Korean Paintings (다양한 접근점 기반의 한국화 검색 인터페이스에 관한 연구)

  • Seo, Eun-Gyoung;Lee, Won-Kyung
    • Journal of the Korean Society for information Management
    • /
    • v.25 no.2
    • /
    • pp.25-48
    • /
    • 2008
  • The purpose of this study is to suggest retrieval interfaces for Korean paintings which support users to retrieve specific digitalized images of them through various access points and to widely browse based on unique features Korean paintings. The study, first, develops a set of descriptive elements suitable for Korean Paintings. Twenty-six core elements and one hundred seventy-two attributes are selected as descriptive items for Korean paintings based on the opinion of 8 experts. Then, to gam realistic evidence of what descriptive elements of image serve users as access points, it is investigated which elements are used as retrieval access points among 26 core elements by 300 peered users who are consisted with two groups such as common users and domain specialists. The study, in final, designs two(general and advanced) types of search interfaces and display interfaces based on the most popular top 15 descriptive elements. This access-enhanced platform which enables user-oriented searches will satisfy users in image retrieving.

Learning Relational Instance-Based Policies from User Demonstrations (사용자 데모를 이용한 관계적 개체 기반 정책 학습)

  • Park, Chan-Young;Kim, Hyun-Sik;Kim, In-Cheol
    • Journal of KIISE:Software and Applications
    • /
    • v.37 no.5
    • /
    • pp.363-369
    • /
    • 2010
  • Demonstration-based learning has the advantage that a user can easily teach his/her robot new task knowledge just by demonstrating directly how to perform the task. However, many previous demonstration-based learning techniques used a kind of attribute-value vector model to represent their state spaces and policies. Due to the limitation of this model, they suffered from both low efficiency of the learning process and low reusability of the learned policy. In this paper, we present a new demonstration-based learning method, in which the relational model is adopted in place of the attribute-value model. Applying the relational instance-based learning to the training examples extracted from the records of the user demonstrations, the method derives a relational instance-based policy which can be easily utilized for other similar tasks in the same domain. A relational policy maps a context, represented as a pair of (state, goal), to a corresponding action to be executed. In this paper, we give a detail explanation of our demonstration-based relational policy learning method, and then analyze the effectiveness of our learning method through some experiments using a robot simulator.

Semantic Web Ontology for Research Community (국가과학기술 R&D 기반정보 온톨로지)

  • Kang, In-Su;Jung, Han-Min;Lee, Seung-Woo;Kim, Pyung;Sung, Won-Kyung
    • Proceedings of the Korea Contents Association Conference
    • /
    • 2006.05a
    • /
    • pp.231-234
    • /
    • 2006
  • Semantic web ontologies can be viewed as logic-based domain-oriented contents which allow distributed and heterogeneous information to be semantically integrated, automatically circulated, and enable implicit knowledge to be reasoned. This paper describes the 'Science and Technology Research Area' ontology which is being developed by the Korea Institute of Science and Technology Information (KISTI). This ontology was defined to assist actual researchers and project planners to grasp the researchers community from a variety of viewpoints. We describe classes and properties as ontology components and exemplify the representation of real instances in the ontology. In order to represent the identities of real world instances within the ontology, the above ontology employs both class-dependent URI assignment schemes and the identity resolution methods.

  • PDF

Evaluation of Interpretability for Generated Rules from ANFIS (ANFIS에서 생성된 규칙의 해석용이성 평가)

  • Song, Hee-Seok;Kim, Jae-Kyeong
    • Journal of Intelligence and Information Systems
    • /
    • v.15 no.4
    • /
    • pp.123-140
    • /
    • 2009
  • Fuzzy neural network is an integrated model of artificial neural network and fuzzy system and it has been successfully applied in control and forecasting area. Recently ANFIS(Adaptive Network-based Fuzzy Inference System) has been noticed widely among various fuzzy neural network models because of outstanding performance of control and forecasting accuracy. ANFIS has capability to refine its fuzzy rules interactively with human expert. In particular, when we use initial rule structure for machine learning which is generated from human expert, it is highly probable to reach global optimum solution as well as shorten time to convergence. We propose metrics to evaluate interpretability of generated rules as a means of acquiring domain knowledge and compare level of interpretability of ANFIS fuzzy rules to those of C5.0 classification rules. The proposed metrics also can be used to evaluate capability of rule generation for the various machine learning methods.

  • PDF

Robust Watermarking for Digital Images in Geometric Distortions Using FP-ICA of Secant Method (할선법의 FP-ICA를 이용한 기하학적 변형에 강건한 디지털영상 워터마킹)

  • Cho Yong-Hyun
    • The KIPS Transactions:PartB
    • /
    • v.11B no.7 s.96
    • /
    • pp.813-820
    • /
    • 2004
  • This paper proposes a digital image watermarking which is robust to geometric distortions using an independent component analysis(ICA) of fixed-point(FP) algorithm based on secant method. The FP algorithm of secant method is applied for better performance in a separation time and rate, and ICA is applied to reject the prior knowledges for original image, key, and watermark such as locations and size, etc. The proposed method embeds the watermark into the spatial domain of original image The proposed watermarking technique has been applied to lena, key, and two watermarks(text and Gaussian noise) respectively. The simulation results show that the proposed method has higher speed and better rate for extracting the original images than the FP algorithm of Newton method. And the proposed method has a watermarking which is robust to geometric distortions such as resizing, rotation, and cropping. Especially, the watermark of images with Gaussian noise has better extraction performance than the watermark with text since Gaussian noise has lower correlation coefficient than the text to the original and key images. The watermarking of ICA doesn't require the prior knowledge for the original images.