• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.359-362
• /
• 2020

본 연구에서는 설명 문장 생성을 통한 해석 가능한 시각적 질의응답 모델을 설계하고 학습 방법을 제시한다. 설명 문장은 시각적 질의응답 모델이 응답을 예측하는 데에 필요한 이미지 및 질문 정보와 적절한 논리적인 정보의 조합 및 정답 추론 과정이 함의되어 있을 것으로 기대한다. 설명 문장 생성 과정이 포함된 시각적 질의응답의 기본적인 모델을 기반으로 여러 가지 학습방법을 통해 설명 문장 생성 과정과 응답 예측 과정간의 상호관계를 분석한다. 이러한 상호작용을 적극적으로 활용할 수 있는 보다 개선 시각적 질의응답 모델을 제안한다. 또한 학습한 결과를 바탕으로 설명 문장의 특성을 활용하여 시각적 질의응답 추론 과정을 개선함으로써 시각적 질의응답 모델의 발전 방향을 논의한다. 본 실험을 통해서 응답 예측에 적절한 설명 문장을 제시하는 해석 가능한 시각적 질의응답 모델을 제공한다.

• Journal of KIISE:Software and Applications
• /
• v.32 no.9
• /
• pp.888-900
• /
• 2005

Several researches have been proposed to formalize the knowledge preconditions problem - j.e., an action or a plan is epistemically feasible. However, since the feasibility is only checked at design-time and is assumed that it will also 1)e feasible at run-time, it is not suitable in the context of Semantic Web services composition, where many agents should share the limited resources required for the execution of Web services composition. Therefore, in this paper, we formalize a transactionally executable Web services composition which enables to guarantee its atomicity. Moreover, in order to formalize the transactional executability, we propose $TL-ALCFK_{NF}$ which extends TL-ALCF with the modal operators K and A. Based on $TL-ALCFK_{NF}$, we show how to carry out the epistemic reasoning with TL-ALCF as a language to represent Semantic Web services composition.

• Review of KIISC
• /
• v.23 no.3
• /
• pp.56-60
• /
• 2013

본 논문은 온라인에 공개된 다양한 개인정보의 위험도를 분석하는 기술을 제안한다. 인터넷, SNS에 공개된 다양한 데이터를 수집, 분석하여 개인성향을 파악하고 타겟팅하는 가운데, 분산된 정보를 조합하고 추론하면 공개자의 의도와는 달리 신상이나 민감정보가 노출될 가능성이 크다. 본 논문에서는 이러한 데이터 수집 및 분석을 직접 수행하여 개인정보의 위험도를 분석할 수 있는 기술을 제안한다. 제안 기술이 개발되면, 개인정보 위험도에 따른 클라이언트, 웹사이트, 인터넷 전체 규모의 프라이버시 필터링이 가능해질 것으로 기대된다.

• Journal of the Korea Concrete Institute
• /
• v.14 no.6
• /
• pp.1022-1031
• /
• 2002

This paper presents efficient models for bridge structures using CART-ANFIS (classification and regression tree-adaptive neuro fuzzy inference system). A fuzzy decision tree partitions the input space of a data set into mutually exclusive regions, each region is assigned a label, a value, or an action to characterize its data points. Fuzzy decision trees used for classification problems are often called fuzzy classification trees, and each terminal node contains a label that indicates the predicted class of a given feature vector. In the same vein, decision trees used for regression problems are often called fuzzy regression trees, and the terminal node labels may be constants or equations that specify the predicted output value of a given input vector. Note that CART can select relevant inputs and do tree partitioning of the input space, while ANFIS refines the regression and makes it continuous and smooth everywhere. Thus it can be seen that CART and ANFIS are complementary and their combination constitutes a solid approach to fuzzy modeling.

• Korean Journal of Construction Engineering and Management
• /
• v.17 no.1
• /
• pp.3-9
• /
• 2016

This study proposes a approximate cost estimation system based on Excel with VBA using weighted CBR(Case Based Reasoning). One characteristic of this system is that it generates the sheet automatically as many as the number of similar case and new estimation when it performs a case learning and a new estimate and cell formula is automatically entered into each sheet. User can be free to compose a combination of attribute factors because they can select up to ten attribute factors. This paper presents an applicability of estimation model for estimating the soil remediation cost when it use a landfarming method. When compared to a estimation model by using average unit cost and optimum multiple regression, this model shows a better result. This study was aimed at landfarming method, but it is expected that a cost estimation model using CBR will be more likely to apply in soil remediation technologies which various remediation technologies and pollutant species exist.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2008.10b
• /
• pp.575-582
• /
• 2008

본 논문은 시맨틱 웹 기술이 어떻게 국가 표준(KS) 정보 검색 서비스 내 정보들을 연계시키고 사용자 접근성을 향상시키는 데 도움을 줄 수 있는지를 실증적으로 보여준다. 기존 표준 정보 검색 서비스는 용어 검색의 유연성이 부족하여 표준 정보에서 사용된 용어와 사용자 용어 간의 괴리를 해소하지 못했으며 표준, 기관, 인력 등 상호 관련성을 가진 개체 정보들을 개별적으로 서비스하였다. 이러한 상황은 사용자의 표준 정보 검색 서비스 접근성을 떨어뜨리는 요인으로 작용한다. 본 연구에서는 유의어, 관련어를 중심으로 한 표준 용어 사전 구축을 통해 사용자 용어와 표준 정보 내 용어 간의 원활한 매칭을 지원하며, 표준 관련 개체들을 온톨로지와 추론을 통해 연계시키는 방안을 제시한다. 개선된 표준 정보 검색 서비스는 개선된 표준 정보 검색 서비스는 개체 중심적 통합 검색 결과 제공 방식으로 관련 정보들을 단일 웹 페이지 내에서 확인할 수 있도록 해준다. 예를 들어, 특정 KS 표준 검색 결과 페이지에서는 기존에 DB 접근이나 검색 엔진을 통해 바로 획득할 수 없었던 정부 표준들, 기관들의 해당 KS 표준 인용 현황, 해당 KS 표준 전문가들, 부합화를 위해 참조된 국제 표준들, 해당 KS 표준 전문가들, 부합화를 위해 참조된 국제 표준들, 해당 KS 표준 전문가 네트워크, 해당 KS 표준 내 표준 용어 사전 정보 등 다양한 관련 정보들을 조합하여 서비스한다. 본 연구를 위해 모델링된 온톨로지와 시맨틱 웹기반 서비스 프레임워크인 OntoFrame 상에서 추론 작업이 표준 정보 적재 시에 전방 추론 (Forward-chaining) 방식으로 수행되었으며, 표준 온톨로지 질의 언어인 SPARQL (SPARQL Protocol and RDF Query Language)을 이용해 일반 검색 서비스 수준의 속도로 서비스될 수 있었다.

• Journal of Intelligence and Information Systems
• /
• v.12 no.2
• /
• pp.67-81
• /
• 2006

While the existing Web focuses on the interface with human users based on HTML, the next generation Web will focus on the interaction among software agents by using XML and XML-based standards and technologies. The inference engine, which will serve as brains of software agents in the next generation Web, should thoroughly understand the Semantic Web, the standard language of the next generation Web. As abasis for the service, the W3C (World Wide Web Consortium) has recommended SWRL (Semantic Web Rule Language) which had been made by compounding OWL (Web Ontology Language) and RuleML (Rule Markup Language). In this research, we develop a backward chaining inference engine SMART-B (SeMantic web Agent Reasoning Tools -Backward chaining inference engine), which uses SWRL and OWL to represent rules and facts respectively. We analyze the requirements for the SWRL-based backward chaining inference and design analgorithm for the backward chaining inference which reflects the traditional backward chaining inference algorithm and the requirements of the next generation Semantic Web. We also implement the backward chaining inference engine and the administrative tools for fact and rule bases into Java components to insure the independence and portability among different platforms under the environment of Ubiquitous Computing.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.283-288
• /
• 2009

Semantic service can be defined as the service providing search API or reasoning API based on ontology and Web Services. It performs a pre-defined task by exploiting URI, classes, and properties. This study introduces a semantic service composition method based on a semantic broker referring ontology and management information of semantic services stored in a semantic service manager with requirements of the user. The requirements consist of input instances, an output class, a visualization type, semantic service names, and property names. This composition method provides dynamically generated semantic service pipelines including composit semantic services. The user can execute the pipelines provided by the semantic broker to find a meaningful semantic pipeline. After all, this study contributes to develop a system supporting human service planners who want to find composit semantic services among distributed semantic services.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.6
• /
• pp.1203-1208
• /
• 2016

For young children who are not spontaneous or not accurate in verbal communication of their emotions and experiences, drawing is a good means of expressing their status in mind and thus drawing analysis with chromatics is a traditional tool for art therapy. Recently, children enjoy digital drawing via painting tools thus there is a growing needs to develop an automatic digital drawing analysis tool based on chromatics and art therapy theory. In this paper, we propose such an analyzing tool based on dominant color analysis. Technically, we use ART2 clustering and fuzzy logic to understand the fuzziness of subjects' status of mind expressed in their digital drawings. The frequency of color usage is fuzzified with respect to the membership functions. After applying fuzzy logic to this fuzzified central vector, we determine the dominant color and supporting colors from the digital drawings and children's status of mind is then analyzed according to the color-personality relationships based on Alschuler and Hattwick's historical researches.

• Journal of Labour Economics
• /
• v.30 no.3
• /
• pp.43-75
• /
• 2007

This study reviews the trend of job separation rates for three years from 2002 to 2005 and investigates the various elements which influence this trend, especially the role of the labor unions, by using Korean Labor Panel data. In the basic statistics, the job retention rate of union members were higher by an average of 28.3% points compared to non-union members, but in the results of controlling the observed variables of individual influences in changing jobs, it was estimated that unions increase the job retention rate by 11% to 13% points. To investigate the effect of unions on the job stability of workers in detail, the non-linear decomposition method developed by Fairlie (2003) was used in the analysis. In examining the difference of job separation rates between union members and non-union members through observed variables of workers in explainable parts and unexplainable parts by using the non-linear decomposition technique, the contribution of the explainable part was estimated to be 67% to 74% and the unexplainable part accounted for the rest which was 26% to 33%. This suggests that not only does the union contribute to the job stability of its members, but the propensity to change jobs for a worker who is a union member is on average lower than that of a worker who is not a union member or who works at an establishment that does not have a union. The results of the empirical analysis show that the job stability effect of labor unions is limited within the boundary of a maximum 7% to 9% points. The reason for the effect of labor unions on job stability being so low is due to various reasons such as collective bargaining structure by company, intensified business competition after the financial crisis, and labor market segmentation.