• 로봇학회논문지
• /
• 제16권2호
• /
• pp.122-129
• /
• 2021

For the Simultaneous Localization and Mapping (SLAM) problem, a different path results in different SLAM results. Usually, SLAM follows a trail of input data. Active SLAM, which determines where to sense for the next step, can suggest a better path for a better SLAM result during the data acquisition step. In this paper, we will use reinforcement learning to find where to perceive. By assigning entire target area coverage to a goal and uncertainty as a negative reward, the reinforcement learning network finds an optimal path to minimize trajectory uncertainty and maximize map coverage. However, most active SLAM researches are performed in indoor or aerial environments where robots can move in every direction. In the urban environment, vehicles only can move following road structure and traffic rules. Graph structure can efficiently express road environment, considering crossroads and streets as nodes and edges, respectively. In this paper, we propose a novel method to find optimal SLAM path using graph structure and reinforcement learning technique.

• 한국초등과학교육학회지:초등과학교육
• /
• 제34권1호
• /
• pp.1-14
• /
• 2015

The variety of learners include students with disabilities and general students, and an ongoing focus of inclusive education research is non-discrimination. As part of integrated education, UDL (Universal Design for Learning) for students with disabilities supports a practical approach, participation, and advancement to improve learning opportunities for all students. The purpose of this study was to examine the effects of using UDL in science classes. The dependent variables of this study were academic achievement in science, scientific attitude, and scientific motivation. In this study, the experimental groups were 9 people in the 5th grade and 11 people in 6th grade. The experimental groups were taught science class using UDL. In order to analyze the learning outcomes, the structure equation model was performed. The results of this study were as follows: First, the science achievement of learning outcomes of the science class applying UDL directly affected both scientific attitude and scientific motivation. Second, the scientific attitude of learning outcomes of the science class applying UDL directly did not affect scientific motivation. According to these results, learning outcomes for science achievement of the science class applying UDL showed that UDL affected both general students and students with disabilities. To summarize the analysis of learning outcomes, science achievement directly affected both scientific attitude and scientific motivation while scientific attitude did not affect scientific motivation. This study offered a specific implementation method for integrated education. Using the structure equation model for analyzing the effect has more significance.

• Composites Research
• /
• 제36권2호
• /
• pp.92-100
• /
• 2023

본 논문에서는 유리섬유 직물 강화 복합재 소재위에 Cross-Dipole 패턴이 배치된 정형적 Circuit Analog(CA) 전파 흡수 구조 설계를 위한 머신러닝 및 딥러닝 모델을 제시하였다. 제시된 모델은 Cross-Dipole 패턴의 형상에 따라서 Ku-band (12-18 GHz)에서의 전파흡수성능을 3차원 전자파 수치해석 없이 바로 계산할 수 있다. 이를 위하여 다양한 머신러닝 및 딥러닝 기술을 적용한 최적 학습 모델을 도출하고, 학습 모델이 계산한 결과를 3차원 전자파 수치해석결과로 얻은 전파흡수특성과 비교함으로써 각각의 모델 간의 성능의 비교우위를 평가하였다. 개발된 모델들은 대부분 수치해석결과와 유사한 계산결과를 보여주었지만, 그 중 Fully-Connected 모델이 가장 유사한 계산결과를 제공할 수 있음을 확인하였다.

• 정보처리학회논문지A
• /
• 제11A권2호
• /
• pp.207-212
• /
• 2004

본 연구에서는 SCORM 시퀀싱 모델을 기반으로 학습객체의 구조에 대한 정보, 학습자에게 학습 객체를 어떻게 전달할 지를 결정하는 규칙 등을 포함하고 있는 학습 컨텐츠 구조를 제시한다. 다양한 학습 환경에서 학습 컨텐츠 객체의 재사용과 공유가 쉬워진다. 서로 다른 교수법을 적용하여 학습이 진행되도록 동일한 학습 객체들에 대한 시퀀싱 생성 도구를 개발한다. 또한 학습자 정보 트래킹을 위한 SCO(Sharable Content Object) 함수를 추가하고 학습 객체가 SCORM RTE(Run-Time Environment)와 통신을 위해 PIF(Package Interchange File)로 자동 패키징 시킨다.

• 한국초등과학교육학회지:초등과학교육
• /
• 제21권2호
• /
• pp.241-252
• /
• 2002

Field learning have not well performed in elementary school for various reasons, in spite of the benefits of field study. Absence of suitable geological field courses for elementary science education is one of several reasons The purpose of this study is to develop learning materials for the field geology in Hampyeong region and apply them to the geological related units for elementary science education. The 5 observation sites for the field geology learning in study area include various rocks and geological structure such as granite, gneiss, conglomerate, sandstone, mudstone, plant fossil, fold, fault and weathering phenomenon changing rocks to soil. This study area is suitable place for the field geology learning of elementary science education in Kwangju and Chonnam province because of convenience access, fresh outcrops and distribution of various geological learning materials as rocks and structure.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1996년도 추계학술대회 학술발표 논문집
• /
• pp.27-34
• /
• 1996

GENIE is a learning-based engine for building intelligent systems. Learning in GENIE proceeds by incrementally modeling its human or technical environment using a neural network and a genetic algorithm. The neural network is used to represent the knowledge for solving a given task and has the ability to grow its structure. The genetic algorithm provides the neural network with training examples by actively exploring the example space of the problem. Integrated into the training examples by actively exploring the example space of the problem. Integrated into the GENIE system architecture, the genetic algorithm and the neural network build a virtually self-teaching autonomous learning system. This paper describes the structure of GENIE and its learning components. The performance is demonstrated on a robot learning problem. We also discuss the lessons learned from experiments with GENIE and point out further possibilities of effectively hybridizing genetic algorithms with neural networks and other softcomputing techniques.

• 한국전산구조공학회:학술대회논문집
• /
• 한국전산구조공학회 1998년도 봄 학술발표회 논문집
• /
• pp.216-225
• /
• 1998

Although artificial neural network based on backpropagation algorithm is an excellent system simulator, it has still unsolved problems of its structure-decision and learning method. That is, we cannot find a general approach to decide the structure of the neural network and cannot train it satisfactorily because of the local optimum point which it frequently falls into. In addition, although there are many successful applications using backpropagation learning algorithm, there are few efforts to improve the learning algorithm itself. In this study, we suggest a general way to construct the hidden layer of the neural network using binary genetic algorithm and also propose the various learning methods by which the global minimum value of the teaming error can be obtained. A XOR problem and line heating problems are investigated as examples.

• 대한화학회지
• /
• 제57권3호
• /
• pp.389-397
• /
• 2013

이 연구에서는 과학 수업에 적용한 STAD 협동학습 전략이 초등학교 학생들의 학업성취도, 학습 동기, 학습 환경에 대한 인식, 수업 목표 구조에 대한 인식에 미치는 영향을 학생들의 집단주의 성향 수준에 따라 조사하였다. 1개 초등학교의 6학년 2개 학급 64명의 학생들을 처치 집단과 통제 집단으로 할당했다. 사전 검사로 개인-집단주의 성향 검사, 학습 동기 검사, 학습 환경에 대한 인식 검사, 수업 목표 구조에 대한 인식 검사를 실시하였다. 협동학습 처치는 24차시 동안 실시하였다. 사후 검사로 학업성취도, 학습 동기, 학습 환경에 대한 인식, 수업 목표 구조에 대한 인식 검사를 실시하였다. 연구 결과, 학업성취도에서 처치 집단 학생들의 점수가 통제 집단에 비해 유의미하게 높았다. 학습 동기에서는 주의력 하위 범주에서 유의미한 적성-처치 상호작용 효과가 발견되었다. 학습 환경에 대한 인식의 경우, 응집성 범주에서는 처치 집단의 점수가 통제 집단에 비해 유의미하게 높았지만, 경쟁도 범주에서는 처치 집단의 점수가 유의미하게 낮았다. 수행 지향 목표 구조에 대한 인식에서는 처치 집단의 점수가 통제 집단에 비해 유의미하게 높았다.

• Korean Chemical Engineering Research
• /
• 제58권2호
• /
• pp.230-234
• /
• 2020

딥러닝 기법을 활용하여 분자 구조로부터 물성을 예측하는 시스템은 화학, 생물학, 재료 연구에 적용하기 위해 개발되었다. 분자 구조와 물성 정보가 축적된 데이터베이스를 기반으로, 구조와 물성간의 관계식을 찾는 딥러닝 모형을 구축한 후 최종적으로는 새로운 분자 구조에 대한 물성 예측값을 제공할 수 있다. 또한 선정된 분자 구조의 실제 물성값에 대한 실험을 병행하여 지속적인 검증 및 모형 업데이트를 수행하게 된다. 이를 통해 다량의 분자구조로부터 물성이 우수한 분자 구조를 빠른 시간 안에 스크리닝할 수 있으며, 연구의 효율성 및 성공률을 높일 수 있다. 본 논문에서는 딥러닝을 활용한 물성 예측 시스템의 전반적인 구성과 LG화학에서 실제 신규 구조 발굴에 적용된 사례를 중심으로 소개하고자 한다.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제12권1호
• /
• pp.1-26
• /
• 2008

The concept field is defined as the schema of all equivalent definitions of a mathematics concept. Concept system is defined as the schema of a group concept network where there are mathematics relations. Proposition field is defined as the schema of all equivalent proposition sets. Proposition system is defined as a schema of proposition sets where one mathematics proposition at least is "derived" from the other proposition. CPFS structure that consists of concept field, concept system proposition field, proposition system describes more precisely mathematics cognitive structure, and reveals the unique psychological phenomena and laws in mathematics learning.