• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.05a
• /
• pp.277-285
• /
• 2007

본 연구는 시맨틱웹 응용의 중심 기술인 웹 온톨로지의 표현과 추론을 위해 서술 논리와 규칙언어를 기반으로하는 웹 온톨로지 모델링 방법을 제안한다. 현재 웹 온톨로지 표현 언어인 OWL DL은 서술 논리에 근거하여 표현되는 것이나, 기계나 온톨로지 공학자가 OWL로 기술된 온톨로지를 직관적으로 이해하고 공유할 수 있는 형식적이고 명시적인 온톨로지의 지식 표현은 부족한 실정이다. 따라서 본 연구는 시맨틱웹이 목적하는 웹 온톨로지 구축을 위한 웹 온톨로지 모델링 방법으로 웹 온톨로지 모델링 계층을 제안하고, 제안된 각 계층에 따라 서술 논리의 TBox와 ABox의 구조와 SWRL을 기반으로 지식을 표현하는 웹 온톨로지 모델링 방법을 제안한다. 제안된 웹 온톨로지 모델링 방법의 성능 검증을 위해 제안 방법에 따라 웹 온톨로지를 구축하였고, SPARQL과 TopBraid의 DL Inference를 이용하여 구축된 웹 온톨로지의 성능을 검증하였다.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.340-347
• /
• 2007

"유비쿼터스 컴퓨팅"과 "상황인지 컴퓨팅"이 점차 확산되어짐에 따라 유비쿼터스 환경이 급격하게 발전하면서 변화하고 있다. 이러한 변화로 인해 사용자 정보와 사용자 주변의 환경 정보를 파악하여, 적절한 시간에 적절한 서비스를 제공할 수 있는 기술과 인간과 컴퓨터 관계가 증가하면 할 수 록 인간과 인간의 관계처럼 좀 더 자연스러운 관계를 유지 할 수 있는 상황인지 컴퓨팅이라는 개념이 나타나기 시작하였다. 이러한 상황인지 컴퓨팅을 통하여 상황을 인지하고 사용자에게 필요한 정보를 제공하기 위해서는 상황을 정의 할 수 있는 상황인지 모델이 필요하다. 그러나 현재, 상황을 인지하기 위한 상황인지 모델에 관한 연구는 미비한 상태이다. 본 논문에서는 5W1H를 이용하여 상황을 정의하고, RFMatrix를 이용하여 주변 환경과 사람들과의 관계를 반영한 RFMatrix 기반의 상황인지 모델을 제안한다. 또한 제안된 RFMatrix모델의 유용성을 검증하기 위해 학습공간의 실험을 통하여 정확성을 검증하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2024.05a
• /
• pp.617-618
• /
• 2024

본 논문에서 핵심적으로 연구할 내용은 기존 논문에서 소개된 BERT-base 모델의 경량화 버전인 DistilBERT 모델을 임베디드 시스템(Raspberry PI 5) 환경에 탑재 및 구현하는 것이다. 또한, 본 논문에서는 임베디드 시스템(Raspberry PI 5) 환경에 탑재한 DistilBERT 모델과 BERT-base 모델 간의 성능 비교를 수행하였다. 성능 평가에 사용한 데이터셋은 SQuAD(Standford Question Answering Dataset)로 질의응답 태스크에 대한 데이터셋이며, 성능 검증 지표로는 EM(Exact Match) Score와 F1 Score 그리고 추론시간을 사용하였다. 실험 결과를 통해 DistilBERT와 같은 경량화 모델이 임베디드 시스템(Raspberry PI 5)과 같은 환경에서 온 디바이스 AI(On-Device AI)로 잘 작동함을 증명하였다.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.1
• /
• pp.72-76
• /
• 2009

Recently, as the interest of ubiquitous computing has been increased there has been lots of research about recognizing human activities to provide services in this environment. Especially, in mobile environment, contrary to the conventional vision based recognition researches, lots of researches are sensor based recognition. In this paper we propose to recognize the user's activity with multi-modal sensors using hierarchical dynamic Bayesian networks. Dynamic Bayesian networks are trained by the OVR(One-Versus-Rest) strategy. The inferring part of this network uses less calculation cost by selecting the activity with the higher percentage of the result of a simpler Bayesian network. For the experiment, we used an accelerometer and a physiological sensor recognizing eight kinds of activities, and as a result of the experiment we gain 97.4% of accuracy recognizing the user's activity.

• Journal of Digital Convergence
• /
• v.20 no.1
• /
• pp.249-255
• /
• 2022

The purpose of this study is to establish and propose a post-diagnosis checklist for the revitalization of domestic regional co-brands that have not been activated despite many strengths. First, I looked into the brand revitalization methodology through prior researches and among them, referring to the cause-remedies model, the cause of the deactivation of the co-brand and the currently used revitalization method were examined through case studies and expert interviews. Regarding the currently used method, the reason for using the method was inferred, and the factors corresponding to the cause and effect were found and categorized in the inferred sentence, and the corresponding detailed items were set and the checklist items were presented. Although this study has a limitation in that there is no practical checklist verification, it is expected that a specific activation plan will be presented through verification of future studies.

• Journal of The Korean Association For Science Education
• /
• v.37 no.1
• /
• pp.25-37
• /
• 2017

The purpose of this study is to analyze the effects on particulate concept formation based on abductive reasoning model for elementary science class. For this study, an author selected two groups in the sixth grade. One group is an ordinary textbook-based control group (N=26) and the other group is an abductive reasoning model-based treatment group (N=26). After twelve lessons, the scores of Concepts Test for Gas were analyzed by t-test and two-way ANOVA. The result of t-test showed both the control and treatment groups have higher score than before they take the lesson. But after the lesson, an author found out that the treatment group had higher score than that of the control group. And compared to the number of particles expressed, the number of the treatment group were higher than that of the control class. The two-way ANOVA result revealed that the interaction effect between their cognitive level and treatment was not significant. And regardless of the level of cognition, the scores of treatment group are higher than those of control group. Therefore, abductive reasoning model-based elementary science class were found to be more effective for particulate concept formation. Based on the results, an author concluded that abductive reasoning model is very effective in teaching particulate concepts to elementary students.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.1
• /
• pp.53-61
• /
• 2011

For construction projects, the importance of early cost estimates is highly recognized by the project team and sponsoring organization because early cost estimates are frequently a foundation of business decisions as well as a basis for identifying any changes as the project progresses from design to construction. However, it is difficult to accurately estimate construction cost in the early stage of a project due to various uncertainties in construction. To deal with these uncertainties, cost estimates should be made several times over the course of the project. In particular, early cost estimates are essential process for successful project management. For accurate construction cost estimates, it is necessary to compare cost estimates with actual costs based on historical project data. In this context, case-based reasoning (CBR), which is the process of solving new problems based on the solutions of similar past problems, can be considered as an effective method for cost estimating. To obtain this, it is also required to define the attribute similarities and the attribute weights. However, no existing method is capable of determining attribute weights of qualitative variables. Consequently, it has been a well-known barrier of accurate early cost estimates. Using Genetic Algorithms (GA), this research suggests the method of determining the attribute weight of qualitative variables. Based on building project case studies, the proposed methodology was validated.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.5B
• /
• pp.439-447
• /
• 2011

It is a main concern for sustainable development in water resources management to evaluate adaptation capability of water resources structures under the future climate conditions. This study introduced the Fuzzy Inference System (FIS) to represent the change of release and storage of reservoirs in the Han River basin corresponding to various inflows. Defining the adaptation capability of reservoirs as the change of maximum and/or minimum of storage corresponding to the change of inflow, the study showed that Gangdong Dam has the worst adaptation capability on the variation of inflow, while Soyanggang Dam has the best capability. This study also constructed an Adaptive Neuro-Fuzzy Inference System (ANFIS) for the more accurate and efficient simulation of the adaptation capability of the Soyanggang Dam. Nine Inflow scenarios were generated using historical data from frequency analysis and synthetic data from two general circulation models with different climate change scenarios. The ANFIS showed significantly different consequences of the release and reservoir storage upon inflow scenarios of Soyanggang Dam, whilst it provides stable reservoir operations despite the variability of rainfall pattern.

• Journal of the Korean Society for Railway
• /
• v.19 no.2
• /
• pp.145-158
• /
• 2016

This paper introduces a risk graph which is one method for determining the SIL as a measure of the effectiveness of signaling system. The purpose of this research is to make up for the weakness of the qualitative determination, which has input value ambiguity and a boundary problem in the SIL range. The fuzzy input valuable consists of consequence, exposure, avoidance and demand rate. The fuzzy inference produces forty eight fuzzy rule by adapting the calibrated risk graph in the IEC 61511. The Max-min composition is utilized for the fuzzy inference. The result of the fuzzy inference is the fuzzy value. Therefore, using the de-fuzzification method, the result should be converted to a crisp value that can be utilized for real projects. Ultimately, the safety requirement for hazard is identified by proposing a SIL result with a tolerable hazard rate. For the validation the results of the proposed method, the fuzzy risk graph model is compared with the safety analysis of the signaling system in CENELEC SC 9XA WG A10 report.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.2
• /
• pp.55-62
• /
• 2004

In this paper, the diagnostic expert system for silicone oil-filled transformer is developed using dissolved gas analysis(DGA). There are many diagnostic methods for diagnostic oil-immersed transformer. But DGA is used to the proposed expert system since it has been verified that DGA is very efficient diagnostic method for transformer. In addition, it is resonable that fuzzy rule, degree of inclusion and fuzzy measure must be considered to handle the uncertainty nature of gas boundary and rules. The proposed expert system consists of knowledge base module, inference engine module and human-machine interface(HMI) module. The knowledge base module consists of the knowledge using the rule. The inference engine module is used to the fuzzy rule. The history of the transformer gas data is managed by the database. the effect of the proposed expert system is verified by case studies.