• Journal of KIISE:Software and Applications
• /
• v.34 no.6
• /
• pp.549-561
• /
• 2007

Vision-based scene understanding is to infer and interpret the context of a scene based on the evidences by analyzing the images. A probabilistic approach using Bayesian networks is actively researched, which is favorable for modeling and inferencing cause-and-effects. However, it is difficult to gather meaningful evidences sufficiently and design the model by human because the real situations are dynamic and uncertain. In this paper, we propose a learning method of Bayesian network that reduces the computational complexity and enhances the accuracy by searching an efficient BN structure in spite of insufficient evidences and training data. This method represents the domain knowledge as ontology and builds an efficient hierarchical BN structure under constraint rules that come from the ontology. To evaluate the proposed method, we have collected 90 images in nine types of circumstances. The result of experiments indicates that the proposed method shows good performance in the uncertain environment in spite of few evidences and it takes less time to learn.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.51-62
• /
• 2022

AI-based speed prediction studies have been conducted quite actively. However, while the importance of explainable AI is emerging, the study of interpreting and reasoning the AI-based speed predictions has not been carried out much. Therefore, in this paper, 'Explainable Deep Graph Neural Network (GNN)' is devised to analyze the speed prediction and assess the nearby road influence for reasoning the critical contributions to a given road situation. The model's output was explained by comparing the differences in output before and after masking the input values of the GNN model. Using TOPIS traffic speed data, we applied our GNN models for the major congested roads in Seoul. We verified our approach through a traffic flow simulation by adjusting the most influential nearby roads' speed and observing the congestion's relief on the road of interest accordingly. This is meaningful in that our approach can be applied to the transportation network and traffic flow can be improved by controlling specific nearby roads based on the inference results.

• Journal of Oral Medicine and Pain
• /
• v.30 no.1
• /
• pp.35-44
• /
• 2005

Purpose: The aim of this preliminary study was to evaluate the effect of Problem-Based Learning (PBL) curriculum on development of comprehension of basic medical knowledge and quality of semi-structured problem solving including scientific reasoning skill. This scientific reasoning contained five components including: size of simple, design of research cause-effect, construction of risk factor, analysis statistic of data, interpretation of result. Materials and Methods: Seoul National University Dental students (100) participated in this experience during two weeks, 2004. Forty eight multiple-choice questions (MCQ) concerned "Infection Control and Prevention" were asked before and after two sections of Lecture-Based Learning (LBL) and PBL (pretest-posttest control group design). A semi-structured problem in epidemiological research was asked to these students after two sections (posttest-only control group design). Data (mean and SD) were analysed using the t Test for two independent samples (p<.05), comparing PBL versus LBL. Results: Our analyse of scores show no difference between LBL and PBL in the development of comprehension of "Infection Control and Prevention". The quality problem solving (epidemiological research) was significantly different between the two groups (p=.029); specially, two components' scores of reflection on scientific reasoning cause-effect (p=.000) and interpretation of result (p=.001) were significantly better for PBL than for LBL. Conclusion: Theses results indicate that comparing LBL and PBL, PBL curriculum have not been disadvantaged in comprehension of basic knowledge, and have contributed to develop the scientific reasoning in problem solving.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.232-235
• /
• 2004

차세대 정보통신 기술의 가장 중요한 패러다임으로 유비쿼터스 컴퓨팅이 새롭게 주목 받고있다. 그러나 현재 유비쿼터스 환경에서 축적되어 있는 분산데이터베이스의 구체적인 활용 방안에 관한 연구는 아직 불충분하다. 본 논문에서는 분산환경 데이터베이스에 축적되어 있는 데이터를 베이지안 네트워크를 이용하여 인간의 동작이나 행동에 대한 상황 적응형 서비스를 실행하는 방법을 제안한다. 베이지안 네트워크는 변수들 사이의 인과 관계를 표현하기 때문에 사용자의 행동이나 특성들을 기술하는 것이 용이하다 유비쿼터스 환경에서 인간이나 사물의 동작, 행동 등을 축적한 데이터베이스로부터 현재 인간의 상황을 예측하여 인간이 필요로 하는 적절한 서비스를 실행하는 작업이 요구된다. 유비쿼터스 환경 내에서 발생하는 이벤트를 인지하고 인간과 사물간의 대화 생성의 중개역할자로 베이지안 네트워크를 이용하여 적절한 서비스를 추론하고 실행하는 방법을 제시한다.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1996.10a
• /
• pp.23-26
• /
• 1996

인과관계적 추론 방법(causal reasoning)은 시스템 고장을 시스템 구조나 행동의 원인 상과관계를 사용하여 분류하는 것으로서 관측된 행도오가 기대행동의 차이를 조사하여 인식하게 된다. 본 연구에서는 징후(symptom)를 분석 및 분류할 때에 시스템의 기능적인 계층구조를 이용한다. 전문가시스템의 구축은 KAPPA-PC를 사용하였다. KAPPA-PC는 규칙 및 논리에 근거한 방법과 객체지향적 지식 표현 기법을 사용한다. 대다수의 사람들이 일상적으로 사용하는 PC(Personal Computer)는, 특히 하드웨어에서 고장이 일어났을 때 수리자의 노우하우(know-how)로 고쳐지는 경우가 대부분이다. 본 논문에서는 자주 일어날수 있는 PC의 하드웨어적 고장에 일반사용자들이 쉽게 접근해서 그 원인과 진단을 내릴 수 있도록 했으며 작은 고장 원인이 전체 시스템구조내에서 어떤 상관관계를 가지는지를 고찰하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.412-415
• /
• 2006

본 논문에서는 파라미터에 대한 정보가 없는 데이터, 즉, 각각의 이벤트 발생에 불확실성이 존재하는 데이터들에 대한 인과 관계의 학습을 위해 그래픽 모델인 베이지안 네트워크를 사용하였다. 이를 위해 기존에는 주로 네트워크 학습에 K2, Sparse Candidate 등의 방법이 사용되었다. 학습 및 추론에 있어서 어떻게 하면 기존의 방법보다 정확하고 빠르게 처리할 수 있을지에 대한 개선된 알고리즘을 제시하고 다른 알고리즘들과의 성능 비교를 통해 제시한 방법론이 보다 좋은 성능을 가짐을 보였다.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2001.06a
• /
• pp.369-376
• /
• 2001

도심지에서 자주 발생되는 교통체증의 문제를 효과적으로 해결하기 위해서는 교통 상황을 신속하고 정확하게 진단하며, 이를 바탕으로 최대한의 효율을 얻을 수 있도록 교통 신호체계를 수립하는 것이 중요하다. 본 논문에서는 '병렬기반 미시적 교통류 시뮬레이션 시스템'을 활용하여 교통상황을 정확하게 모델링한 결과정보를 추출하고, 이를 바탕으로 교통상황을 종합적으로 진단할 수 있는 '교통류 시뮬레이션 평가 및 진단 시스템'을 제시한다. 교통상황에 대한 시뮬레이션 결과정보를 쉽게 분석할 수 있는 교통류 시뮬레이션 평가 및 진단 시스템을 개발하기 위하여, 교통상황의 해석에 필요한 제반 문제와 원인들의 인과관계를 파악하여 규칙화하고, 이를 바탕으로 규칙 기반추론 기법을 적용할 수 있도록 전문가시스템을 도입하였다. 또한 효율적인 진단을 위하여 시뮬레이션 결과정보로부터 구한 정량적인 각종 평가 지표를 정성적인 측면에서 재평가하여 사유할 수 있도록 fuzzy 기술을 도입하였다. 아울러 교통류 시뮬레이션 평가 및 진단 시스템의 결과는 최적의 신호체계를 수립하는데 활용될 수 있도록 하였다. 서울광역시 과천 주변의 8 개 교차로를 포함하는 교통망에 대한 교통정보를 바탕으로 실험해 봄으로써 사용자가 복잡한 교통망에 대해 보다 효과적으로 교통흐름을 분석하여 정체원인을 실시간으로 판단할 수 있는 가능성을 보여준다.

• Journal of The Korean Association For Science Education
• /
• v.36 no.6
• /
• pp.935-946
• /
• 2016

This study aims to explore cognitive biases relating the core competences of science and instructional strategy in reducing the level of cognitive biases. The literature review method was used to explore cognitive biases and science education experts discussed the relevance of cognitive biases to science education. Twenty nine cognitive biases were categorized into five groups (limiting rational causal inference, limiting diverse information search, limiting self-regulated learning, limiting self-directed decision making, and category-limited thinking). The cognitive biases in limiting rational causal inference group are teleological thinking, availability heuristic, illusory correlation, and clustering illusion. The cognitive biases in limiting diverse information search group are selective perception, experimenter bias, confirmation bias, mere thought effect, attentional bias, belief bias, pragmatic fallacy, functional fixedness, and framing effect. The cognitive biases in limiting self-regulated learning group are overconfidence bias, better-than-average bias, planning fallacy, fundamental attribution error, Dunning-Kruger effect, hindsight bias, and blind-spot bias. The cognitive biases in limiting self-directed decision-making group are acquiescence effect, bandwagon effect, group-think, appeal to authority bias, and information bias. Lastly, the cognitive biases in category-limited thinking group are psychological essentialism, stereotyping, anthropomorphism, and outgroup homogeneity bias. The instructional strategy to reduce the level of cognitive biases is disused based on the psychological characters of cognitive biases reviewed in this study and related science education methods.

• Journal of The Korean Association For Science Education
• /
• v.27 no.5
• /
• pp.367-378
• /
• 2007

The purpose of this study is to investigate the features of science language in Earth science textbooks and Earth science research articles. We examined two Earth science textbooks and two Earth science articles using the taxonomy of scientific words, the text structure analysis of explanations, the analysis of conjunctive relations and reasoning, and the function of conjunction. The results showed that school science language revealed in Earth science textbooks had high proportion of naming words and the text structures in which definition/exemplification structure and description structure were dominant. Also, internal relations that showed additional arrangement rather than logical inference, were predominant in Earth science textbooks. However, scientists' science language revealed in the Earth science articles had more proportion of process words and concept words than the Earth science textbooks and the schematic structure of explanation texts, such as orientation - implication sequence - conclusion. In addition, the text structures in each sentences of implication -sequence showed cause/effect or problem-solving after description structures. Also each sentences expressed causal or abductive reasoning through the internal relations using verbs or adverbial inflection. It is necessary that we bridge the gap between the two languages for students' authentic use of science language. For the bridging, we propose "interlanguage", which mediates between school science language and scientists' language.

• Science of Emotion and Sensibility
• /
• v.10 no.3
• /
• pp.393-402
• /
• 2007

The purpose of this study is to provide the design direction based on consumer sensitivity through the structure between product design preferences - sensitivity image - design elements. For the purpose, we selected men's shaver products for this study subject and collected 164 shavers' pictures released between 2001-2007 years. Then, we carried out a pilot test for collection of sensitivity images about shavers, made a survey using semantic differential method and analyzed the survey. According the result, consumers preferred the sensitivity images "luxury, attractive, stable", design elements satisfied the preference images were "form of body is not a circular arcs or a polygon, material is steel, button is push style, and a color of body is not brown." This study can provide a base of the causal relationship between design preferences - sensitivity image - design elements and a design process to predict consumer sensitivity-oriented design.