• 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.

• Korean Journal of Cognitive Science
• /
• v.3 no.2
• /
• pp.249-270
• /
• 1992

The purpose of this paper is to classify the types of input characters,printed Hangul characters,using Maximum Run Length Projection(MRLP)that is used to extract features of input character.Because the number of Hangul characters is large and its structure is complex,there exists close similarities among characters.This paper,therefore,tried to increment the type classification rate using fuzzy resoning.The Maximum Run Length Projection is very immune to noise,and also useful to extracting the demanding information efficiently.In a test case with the most frequently use 917 printed Hangul characters,it achieved 98.58%correct classification rate.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1999.11a
• /
• pp.388-395
• /
• 1999

본 논문의 목적은 퍼지 엔트로피를 이용하여 비선형신호를 예측하는 것이다. 이 방법은 분할된 여러 부 공간(subspace)에 대해 입력 데이터로부터 퍼지 엔트로피를 이용하여 각각의 규칙에 등급을 정하여 불필요한 제어규칙을 제거하여 바람직한 규칙베이스를 구성하도록 한 것이다. 적용되는 퍼지 신경망의 기본적인 구조는 퍼지 제어기의 규칙베이스와 추론의 과정을 신경회로망을 이용하여 구현하며 퍼지 제어규칙의 매개변수들은 역전파 알고리즘에 의해 적응되어진다. 또한 매개변수의 수를 줄이기 위하여 제어규칙의 결론부의 출력값은 신경망의 가중치로 구성하였다. 결국 퍼지 신경망의 복잡도를 줄일 수 있다. Mackey-Glass 시계열의 예측에 대한 컴퓨터 시뮬레이션을 통하여 본 논문에서 제안한 방법의 효율성을 입증하고, 제안된 방법을 EEG 생리신호 분석에 이용될 수 있다.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.4
• /
• pp.153-162
• /
• 2019

Recently, it is necessary to develop a technology for quantitatively evaluating railway vibration to prevent civil complaints about orbital structures caused by railway noise and normal operation of ultra-precise equipment of orbital industrial complexes. The existing analytical method requires a very complicated dynamic response model, and it is difficult to secure the reliability of the result due to the inaccuracy of the demand model. Therefore, in this paper, we propose a railway vibration evaluation algorithm and system that deduce the vibration value generated from railway operation by using Linear Regression and Gradient Descent technique based on actual measurement railway vibration database that classifies factors affecting railway vibration. The prediction results obtained by the proposed algorithm show higher efficiency and accuracy than the existing analytical methods.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.436-438
• /
• 2003

상황인식은 사용자에 적응된 컴퓨팅 환경 및 서비스를 가능하게 한다. 상황인식이 추가된 홈 환경은 인간의 주거생활의 편리성을 향상시킨다. 상황인식을 지원하는 스마트 홈 환경은 상황데이터의 수집, 가공, 처리, 저장등의 기본적인 요구 뿐만 아니라 보안. 상황추론, 능동결정 등 복잡한 요구사항을 가진다. 그러므로, 홈 환경이 이러한 요구사항들을 지원하기 위해서는 특별한 미들웨어 구조가 필요하다. 본 논문에서는 스마트 홈 환경에서 상황인식 서비스를 지원하기 위한 능동 미들웨어 구조를 제안한다. 그리고 제안된 미들웨어를 적용한 시나리오를 설명한다.

• 전기의세계
• /
• v.40 no.4
• /
• pp.50-58
• /
• 1991

본 연구에서는 로보트에 현재위치와 목적지가 주어지면 로보트가 가지고 있는 세계지도(world map)로부터 경로를 탐색하여 경로의 주위 환경 정보를 가진 경로지도(route map)을 생성하고 이를 해석하여 주행을 하도록 한다. 그리고, 인간은 매우 복잡한 상황을 간단하게 이행하는 능력을 갖고 있으나, 그 상황을 감지하는데 필요한 정보들은 불확실성과 모호성을 내포하고 있으며, 인간의 주관적 판단에 의한 것과 불완전 계측에 의한 것들을 처리하기 위해 퍼지 이론을 이용한 추론 및 주행 알고리즘을 제안한다.

• Communications for Statistical Applications and Methods
• /
• v.5 no.1
• /
• pp.177-191
• /
• 1998

Hamilton(1989)은 시계열 변수가 2가지 이상의 국면을 가지고 있을 때, 현재 어떤 국면이 진행되고 있고 향후 진행될 국면이 무엇일까에 대해 추론이 가능한 시계열모형을 소개하였다. Hamilton모형은 시계열이 2개의 독립적인 관찰불가능한 변수의 합으로 구성되어 있고, 이중 한 변수는 2국면 마르코프 확률과정(2-State Markov Stochastic Process)을 따른다고 가정한다. Hamilton모형은 계수의 추정이 단순하면서도 비 대칭성과 조건부 이분산 등과 같은 복잡한 동학(Dynamics)을 용인한다는 장점이 있다(Lam, 1990). 본 연구에서는 마르코프 국면전환모형에 대해 설명한후, 사례분석으로 KOSPI와 금리의 추이에 따라 국면을 정의하여 각 국면의 특징과 타국면과의 연관성 등을 분석하였다.

• Journal of Advanced Navigation Technology
• /
• v.14 no.1
• /
• pp.108-118
• /
• 2010

In this paper, we propose Context-based Music Recommendation (COMUS) ontology for modeling user's musical preferences and context and for supporting reasoning about the user's desired emotion and preferences. The COMUS provides an upper Music Ontology that captures concepts about the general properties of music such as title, artists and genre and also provides extensibility for adding domain-specific ontologies, such as Mood and Situation, in a hierarchical manner. The COMUS is music dedicated ontology in OWL constructed by incorporating domain specific classes for music recommendation into the Music Ontology. Using this context ontology, we believe that the use of logical reasoning by checking the consistency of context information, and reasoning over the high-level, implicit context from the low-level, explicit information. As a novelty, our ontology can express detailed and complicated relations among the music, moods and situations, enabling users to find appropriate music for the application. We present some of the experiments we performed as a case-study for music recommendation.

• Journal of The Korean Association For Science Education
• /
• v.40 no.1
• /
• pp.77-87
• /
• 2020

Scientific inquiry has emphasized its importance in various aspects of science learning and has been performed according to various methods and purposes. Among the various aspects of science learning, it is emphasized to develop core competencies with science, such as scientific thinking. Therefore, it is necessary to support students to be able to formulate scientific reasoning properly. This study attempts to explore problem-finding and scientific reasoning in the process of performing scientific inquiry. This study also aims to reveal what factors influence this complex process. For this purpose, this study analyzed the inquiry process and results performed by two groups of college students who conducted the inquiry related to osmosis. To analyze, research plans, presentations, and group interviews were used. As a result, it was found that participants used various scientific reasoning, such as deductive, inductive, and abductive reasoning, in the process of problem finding for their inquiry about osmosis. In the process of inquiry and reasoning complexly, anomalous data, which appear regularly, and the characteristics of experimental instruments influenced their reasoning. Various reasons were produced for the purpose of constructing the best explanation about the phenomena observed by participants themselves. Finally, based on the results of this study, several implications for the development context of programs using scientific inquiry are discussed.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.12
• /
• pp.485-496
• /
• 2018

So far, the deep learning, a field of artificial intelligence, has achieved remarkable results in solving problems from unstructured data. However, it is difficult to comprehensively judge situations like humans, and did not reach the level of intelligence that deduced their relations and predicted the next situation. Recently, deep neural networks show that artificial intelligence can possess powerful relational reasoning that is core intellectual ability of human being. In this paper, to analyze and observe the performance of Relation Networks (RN) among the neural networks for relational reasoning, two types of RN-based deep neural network models were constructed and compared with the baseline model. One is a visual question answering RN model using Sort-of-CLEVR and the other is a text-based question answering RN model using bAbI task. In order to maximize the performance of the RN-based model, various performance improvement experiments such as hyper parameters tuning have been proposed and performed. The effectiveness of the proposed performance improvement methods has been verified by applying to the visual QA RN model and the text-based QA RN model, and the new domain model using the dialogue-based LL dataset. As a result of the various experiments, it is found that the initial learning rate is a key factor in determining the performance of the model in both types of RN models. We have observed that the optimal initial learning rate setting found by the proposed random search method can improve the performance of the model up to 99.8%.