• 한국측량학회지
• /
• 제40권3호
• /
• pp.177-185
• /
• 2022

본 연구에서는 딥러닝을 통해 고해상도 광학 위성영상에 동종센서로 촬영한 영상을 참조하여 폐색 영역을 복원하는 방법을 제안하였다. 패치 단위로 분할된 영상에서 원본 영상의 화소 분포를 최대한 유지하며 폐색 영역을 모의한 영상과 주변 영상의 자연스러운 연속성을 위해 ConvNeXt 블록을 적용한 CycleGAN (Cycle Generative Adversarial Network) 방법을 사용하여 실험을 진행하였고 이를 3개의 실험지역에 대해 분석하였다. 또한, 학습패치 크기를 512*512화소로 하는 경우와 2배 확장한 1024*1024화소 크기의 적용 결과도 비교하였다. 서로 특징이 다른 3개의 지역에 대하여 실험한 결과, ConvNeXt CycleGAN 방법론이 기존의 CycleGAN을 적용한 영상, Histogram matching 영상과 비교하여 개선된 R² 값을 보여줌을 확인하였다. 학습에 사용되는 패치 크기별 실험의 경우 1024*1024화소의 패치를 사용한 결과, 약 0.98의 R²값이 산출되었으며 영상밴드별 화소 분포를 비교한 결과에서도 큰 패치 크기로 학습한 모의 결과가 원본 영상과 더 유사한 히스토그램 분포를 나타내었다. 이를 통해, 기존의 CycleGAN을 적용한 영상 및 Histogram matching 영상보다 발전된 ConvNeXt CycleGAN을 사용할 때 원본영상과 유사한 모의 결과를 도출할 수 있었고, 성공적인 모의를 수행할 수 있음을 확인하였다.

• 한국초등과학교육학회지:초등과학교육
• /
• 제33권2호
• /
• pp.306-321
• /
• 2014

This study aims to analyze difficulties that pre-service elementary teachers experience in investigating the life cycle of a common cabbage butterfly in person. As difficulties they face during the process of this research, they pointed out collecting eggs, observing molting, creating environments for a breeding cage, feeding, building a breeding cage, and making butterfly specimens. Out of all the environmental difficulties related to their school fields, they pointed out a difficulty of time management most of all, followed by placing a breeding cage in the classroom and the lack of microscopes for observation. In regard to difficulties related to their evaluations on students' activities, they found it difficult to evaluate students' activity with the life cycle of an insect in the aspect of knowledge and even to set evaluation criteria. Besides, many of them responded that it would be appropriate to evaluate a research on the life cycle of an insect through a portfolio or an observation journal. In regard to difficulties in terms of teachers' knowledge, they found it difficult to understand insect molting, metamorphoses, complete metamorphoses, incomplete metamorphoses, the structure of an insect body, and how to distinguish a female insect from a male one. In regard to the application of class models, they knew it is important for students to have various experiences through direct observation, so the experience-based learning model was proper for the process of observing the life cycle of a common cabbage butterfly. However, they found it difficult for students to observe each stage of the life cycle in person.

• 인터넷정보학회논문지
• /
• 제23권3호
• /
• pp.97-110
• /
• 2022

연합학습은 학습데이터의 전송없이 모델의 학습을 수행할 수 있는 학습방법이다. IoT 혹은 헬스케어 분야는 사용자의 개인정보를 다루는 만큼 정보유출에 민감하여 시스템 디자인에 많은 주의를 기울여야 하지만 연합학습을 사용하는 경우 데이터가 수집되는 디바이스에서 데이터가 이동하지 않기 때문에 개인정보 유출에 자유로운 학습방법으로 각광받고 있다. 이에 따라 많은 연합학습 구현체가 개발되었으나 연합학습을 사용하는 시스템의 개발과 운영을 위한 시스템 설계에 관한 구체적인 연구가 부족하다. 본 연구에서는 연합학습을 실제 프로젝트에 적용하여 IoT 디바이스에 배포하고자 할 때 연합학습의 수명주기, 코드 버전 관리, model serving, 디바이스 모니터링에 대한 대책이 필요함을 보이고 이러한 점을 보완해주는 개발환경에 대한 설계를 제안하고자 한다. 본 논문에서 제안하는 시스템은 중단 없는 model-serving을 고려하였고 소스코드 및 모델 버전 관리와 디바이스 상태 모니터링, 서버-클라이언트 학습 스케쥴 관리기능을 포함한다.

• 한국정밀공학회지
• /
• 제22권3호
• /
• pp.170-178
• /
• 2005

The purpose of this study is to develop a gait-event detection system, which is necessary for the cycle-to-cycle FES control of locomotion. Proposed gait event detection system consists of a signal measurement part and gait event detection part. The signal measurement was composed of the sensors and the LabVIEW program for the data acquisition and synchronization of the sensor signals. We also used a video camera and a motion capture system to get the reference gait events. Machine learning technique with ANN (artificial neural network) was adopted for automatic detection of gait events. 2 cycles of reference gait events were used as the teacher signals for ANN training and the remnants ($2\sim5$ cycles) were used fur the evaluation of the performance in gait-event detection. 14 combinations of sensor signals were used in the training and evaluation of ANN to examine the relationship between the number of sensors and the gait-event detection performance. The best combinations with minimum errors of event-detection time were 1) goniometer, foot-switch and 2) goniometer, foot-switch, accelerometer x(anterior-posterior) component. It is expected that the result of this study will be useful in the design of cycle-to-cycle FES controller.

• Journal of Mechanical Science and Technology
• /
• 제17권12호
• /
• pp.1969-1976
• /
• 2003

In the early phases of the product life cycle, Life Cycle Assessment (LCA) is recently used to support the decision-making for the product concepts, and the best alternative can be selected based on its estimated LCA and benefits. Both the lack of detailed information and time for a full LCA for a various range of design concepts need a new approach for the environmental analysis. This paper explores a new approximate LCA methodology for the product concepts by grouping products according to their environmental characteristics and by mapping product attributes into environmental impact driver (EID) index. The relationship is statistically verified by exploring the correlation between total impact indicator and energy impact category. Then, a neural network approach is developed to predict an approximate LCA of grouping products in conceptual design. Trained learning algorithms for the known characteristics of existing products will quickly give the result of LCA for newly designed products. The training is generalized by using product attributes for an EID in a group as well as another product attributes for the other EIDs in other groups. The neural network model with back propagation algorithm is used, and the results are compared with those of multiple regression analysis. The proposed approach does not replace the full LCA but it would give some useful guidelines for the design of environmentally conscious products in conceptual design phase.

• 한국정밀공학회지
• /
• 제20권3호
• /
• pp.221-229
• /
• 2003

In the early phases of the product life cycle, Life Cycle Assessment (LCA) is recently used to support the decision-making fer the conceptual product design and the best alternative can be selected based on its estimated LCA and its benefits. Both the lack of detailed information and time for a full LCA fur a various range of design concepts need the new approach fer the environmental analysis. This paper suggests a novel approximate LCA methodology for the conceptual design stage by grouping products according to their environmental characteristics and by mapping product attributes into impact driver index. The relationship is statistically verified by exploring the correlation between total impact indicator and energy impact category. Then a neural network approach is developed to predict an approximate LCA of grouping products in conceptual design. Trained learning algorithms for the known characteristics of existing products will quickly give the result of LCA for new design products. The training is generalized by using product attributes for an ID in a group as well as another product attributes for another IDs in other groups. The neural network model with back propagation algorithm is used and the results are compared with those of multiple regression analysis. The proposed approach does not replace the full LCA but it would give some useful guidelines fer the design of environmentally conscious products in conceptual design phase.

• 한국컴퓨터정보학회논문지
• /
• 제25권9호
• /
• pp.63-69
• /
• 2020

이미지-이미지 변환은 입력 이미지를 통해서 목적 이미지를 만들어내는 기술로 최근 비지도 학습 구조인 GAN을 활용하여 더 실제와 같은 이미지를 만들어내는 높은 성과를 보였다. 이에 따라 GAN을 활용한 이미지-이미지 변환 연구는 다양하게 진행되고 있다. 이때 일반적으로 이미지-이미지 변환은 하나의 속성 변환을 목표한다. 그러나 실제 생활에서 사용되고 얻을 수 있는 자료들은 한 가지 특징으로 설명하기 힘든 다양한 특징으로 이루어진다. 그래서 다양한 속성을 활용하기 위하여 속성별로 이미지 생성 과정을 나누어 학습할 수 있도록 하는 다중 속성 변화를 목표로 한다면 더 이미지-이미지 변환의 역할을 잘 수행할 수 있을 것이다. 본 논문에서는 GAN을 활용한 이미지-이미지 변환 구조 중 높은 성과를 보인 CycleGAN을 활용해 이중 속성 변환 구조인 Multi CycleGAN을 제안한다. 이 구조는 입력 도메인을 두 가지의 속성에 대하여 학습하기 위하여 3개의 도메인이 양방향 학습을 진행하는 이중 변환 구조를 구현하였다. 새로운 구조를 통해 생성된 이미지와 기존 이미지-이미지 변환 구조들을 통해 생성된 이미지를 비교할 수 있도록 실험을 진행하였다. 실험 결과 새로운 구조를 통한 이미지는 입력 도메인의 속성을 유지하며 목표한 속성이 적용되는 높은 성능을 보였다. 이 구조를 활용한다면 앞으로 더 다양한 이미지를 생성하는 일이 가능지기 때문에 더 다양한 분야에서의 이미지 생성의 활용을 기대할 수 있다.

• 한국과학교육학회지
• /
• 제17권3호
• /
• pp.333-343
• /
• 1997

The purpose of the present study was to investigate an appropriate instructional model in order to remedy students' misconception. As hypotheses of this study, three instructional models, cognitive conflicting, hypothesis testing, and learning cycle models, on biological 'osmosis' concept were tested in 176 high school students. Results of the present study are as follows: 1. All groups used one of three instructional models showed a statistically significant improvement in conceptual change on the 'osmosis' concept between before and after the instruction. In addition, the three hypothesized instructional models were more effective in conceptual change than a traditional expository instruction. 2. There was a statistically significant difference among three experimental groups. Cognitive conflicting model and hypothesis testing model was more effective than learning cycle models. 3. An interviewing after instruction showed that students who had scientific concept on the 'osmosis' through the instruction could effectively apply the concept to other context more than students who had no scientific concept through instruction. The present study indicated that instructional model play an important role on students' conceptual change in science classroom. According to the result of this study, the instruction emphasizing students' active participation in class and scientific reasoning process is more appropriate to remedy misconception that the instruction using students' passive participation in class and expository teaching procedure. This study also indicated that students' concept acquired through instruction is one of important factors to apply it to other context.

• 한국응급구조학회지
• /
• 제25권3호
• /
• pp.111-125
• /
• 2021

Purpose: This study aimed to analyze the impact of rapid cycle deliberate practice (RCDP) simulation education on advanced cardiac life support knowledge, confidence, satisfaction, and performance ability among paramedic students, and provide basic data on the appropriate methods of educational instruction. Methods: The 48 subjects to be instructed were divided into the traditional simulation education group and the RCDP simulation education group. Six participants were randomly assigned to each group and pre-surveyed. They were then exposed to a lecture about advanced cardiac life support related theories for 60 min and post-surveyed through questionnaires with the same learning goals and scenarios. Results: The advanced cardiac life support knowledge (t=-4.813, p=.000) and performance ability (t=-2.903, p=.006) were significantly different between the traditional simulation education and RCDP simulation education groups The results also showed a significant difference in attach monitor (z=6.857, p=.009), analyze EKG rhythm (z=11.111, p=.001), and defibrillation (z=12.632, p=.000), indicating differences in performance capabilities between the two groups. Conclusion: To improve advanced cardiac life support knowledge, performance ability, and confidence in the paramedic students who receive RCDP simulation education, simulation education methods that are appropriate for the subjects being taught, and detailed learning goals and feedback are necessary.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제26권3호
• /
• pp.167-202
• /
• 2023

A central problem of mathematics teaching worldwide is probably the insufficient adaptive handling of tasks-especially in computational practice phases and modeling tasks. All students in a classroom must often work on the same tasks. In the process, the high-achieving students are often underchallenged, and the low-achieving ones are overchallenged. This publication uses different modeling of the tennis serve as an example to show a possible solution to the problem and develops and discusses one adaptive task each for middle school, high school, and college using three mathematical models of the tennis serve each time. From model to model within the task, the complexity of the modeling increases, the mathematical or physical demands on the students increase, and the new modeling leads to more realistic results. The proposed models offer the possibility to address heterogeneous learning groups by their arrangement in the surface structure of the so-called parallel adaptive task and to stimulate adaptive mathematics teaching on the instructional topic of mathematical modeling. Models A through C are suitable for middle school instruction, models C through E for high school, and models E through G for college. The models are classified in the specific modeling cycle and its extension by a digital tool model, and individual modeling steps are explained. The advantages of the presented models regarding teaching and learning mathematical modeling are elaborated. In addition, we report our first teaching experiences with the developed parallel adaptive tasks.