• 한국수학교육학회지시리즈A:수학교육
• /
• 제60권2호
• /
• pp.159-172
• /
• 2021

본 연구의 목적은 조작 교구와 탐구형 기하 소프트웨어를 활용한 전개도 학습이 초등학교 5학년 학생들의 공간 감각에 주는 영향을 비교·분석하는 것이다. 이를 위해 한 실험집단은 조작 교구인 지오픽스를 한 실험집단은 탐구형 기하 소프트웨어인 Cabri 3D를 활용하여 전개도를 학습하였다. 비교 집단은 교구나 소프트웨어의 사용 없이 학습지만으로 학습을 진행하였다. 사전과 사후에 공간 감각 검사를 실시하여 그 수준을 파악하였고, 시선 추적 검사를 실시하여 전개도 과제를 해결하는 학생들의 전략을 분석하였다. 그 결과 조작 교구인 지오픽스를 활용한 전개도 학습이 공간 감각에 가장 효과적이었으며, Cabri 3D 또한 전개도를 학습하기 위한 좋은 도구가 될 수 있음을 확인할 수 있었다. 또한, 전개도 학습 이후 학생들의 해결 전략은 가장 효율적인 전략이었던 분석적 전략이 증가하였으며, 이러한 과정에서 시선 추적은 학생들의 전략을 탐색하는 매우 유용한 도구가 됨을 알 수 있었다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제12권6호
• /
• pp.243-250
• /
• 2023

흉부 X-ray 영상은 폐와 심장을 검사하는 방사선 검사이며 특히, 폐 질환을 진단하는 데 널리 사용되고 있다. 이러한 흉부 X-ray의 품질은 의사의 진단에 영향을 줄 수 있으므로 품질을 평가하는 과정이 필수적으로 거쳐야 하는데, 이 과정은 영상의학과 전문의의 주관이 개입될 수 있고, 수작업으로 이루어지기 때문에 많은 시간과 비용이 소모된다. 또한, 이러한 품질평가는 X-ray 영상의 특징과 사용 목적에 따라 일반적인 품질평가와는 다른 평가 요소가 필요하다. 따라서 본 논문에서는 X-ray 영상에서 검출되는 장기의 해상도, ,해부학적인 구조, 균형 등을 고려하여 임상 현장에서 사용되는 흉부 X-ray 영상 화질 평가 가이드라인을 적용하여 품질요소를 5가지(인공음영, 포함범위, 환자자세, 흡기정도, 그리고 투과상태)로 나누고 이를 자동화하는 도구를 제안한다. 제안하는 도구는 수작업으로 품질평가를 진행하는 본래의 방식 대비 소요 시간과 비용을 줄여주고, 더 나아가 흉부 X-ray를 이용한 학습 모델 개발에 높은 품질의 학습데이터를 선별하는 과정에도 사용될 수 있다.

• 경영과학
• /
• 제18권2호
• /
• pp.25-38
• /
• 2001

The well-known back-propagation algorithm for multi-layered neural network has successfully been applied to pattern c1assification problems with remarkable flexibility. Recently. the multi-layered neural network is used as a powerful data mining tool. Nevertheless, in many cases with complex boundary of classification, the successful learning is not guaranteed and the problems of long learning time and local minimum attraction restrict the field application. In this paper, an Improved learning procedure of multi-layered neural network is proposed. The procedure is based on the generalized delta rule but it is particular in the point that the architecture of network is not fixed but enlarged during learning. That is, the number of hidden nodes or hidden layers are increased to help finding the classification boundary and such procedure is controlled by entropy evaluation. The learning speed and the pattern classification performance are analyzed and compared with the back-propagation algorithm.

• 전자통신동향분석
• /
• 제34권1호
• /
• pp.98-110
• /
• 2019

Machine learning has been applied to medical imaging and has shown an excellent recognition rate. Recently, there has been much interest in preventive medicine. If data are accessible, machine learning packages can be used easily in digital healthcare fields. However, it is necessary to prepare the data in advance, and model evaluation and tuning are required to construct a reliable model. On average, these processes take more than 80% of the total effort required. In this study, we describe the basic concepts of machine learning, pre-processing and visualization of datasets, feature engineering for reliable models, model evaluation and tuning, and the latest trends in popular machine learning frameworks. Finally, we survey a explainable machine learning analysis tool and will discuss the future direction of machine learning.

• International Journal of Control, Automation, and Systems
• /
• 제1권1호
• /
• pp.142-148
• /
• 2003

Reinforcement learning is considered as an important tool for robotic learning in unknown/uncertain environments. In this paper, we propose an evaluation function expressed in a vector form to realize multi-dimensional reinforcement learning. The novel feature of the proposed method is that learning one behavior induces parallel learning of other behaviors though the objectives of each behavior are different. In brief, all behaviors watch other behaviors from a critical point of view. Therefore, in the proposed method, there is cross-criticism and parallel learning that make the multi-dimensional learning process more efficient. By ap-plying the proposed learning method, we carried out multi-dimensional evaluation (reward) and multi-dimensional learning simultaneously in one trial. A special neural network (Q-net), in which the weights and the output are represented by vectors, is proposed to realize a critic net-work for Q-learning. The proposed learning method is applied for behavior planning of mobile robots.

• 농촌지도와개발
• /
• 제23권4호
• /
• pp.449-457
• /
• 2016

The purpose of this study are to examine the educational use of the Facebook and to examine the effects of the learners perceived usefulness, attitude and self-efficacy on learning flow and learning presence at university classes using social network service. The subjects of this study are 155 university students attending a class at a 4-year university in Seoul, and certain questions verified in the existing studies were modified, complemented, and used as a tool for measurement. The details of the purpose are as follows. First, it turned out that there were significant differences in learning flow and learning presence in accordance with the levels of the usefulness that learners perceived. It can be said that the higher the perceived level of usefulness, the higher the learning flow and learning presence. Second, it turned out that there were significant differences in learning flow and learning presence in accordance with the levels of learners' perceived attitudes. We can interpret such a result as suggesting that the higher a learner's perceived attitude, the higher the learning flow and learning presence.

• 영어어문교육
• /
• 제12권3호
• /
• pp.187-210
• /
• 2006

This study aims to investigate the effects of the implementation of self-directed learning through the homepage between the teacher and the students for English reading classes. The study focuses on the questions of whether the self-directed learning through the homepage, compared to the teacher-centered learning, would enable a significantly positive change in the students' achievements and of what their responses to this new learning method are. 72 students were grouped into an experimental and a control group, and then each group was subdivided into three levels (high, medium, low) of proficiency. Findings demonstrate that the experimental group showed statistically more significant increases in their scores of reading proficiency test than the control group. For the question of students' responses to the learning experience, the three groups within the experimental group responded to a questionnaire survey with regard to the positive attitude of learning, the effectiveness of self-directed learning and its learning materials, and usability of the homepage. In general, the experimental group considered the experience satisfactory, although the degree of positive responses varied according to the proficiency level of the group. This suggests the importance and effectiveness of self-directed learning using the computer and internet as a supplementary learning tool.

• 지식경영연구
• /
• 제17권3호
• /
• pp.207-225
• /
• 2016

Recently, flipped learning is being highlighted especially at the college of engineering because of its self-directed learning which direction matches that of the engineering education system. Although many engineering professors have tended to apply the flipped learning to their classes, they experienced a number of significant problems and challenges in practical implementing. By using TRIZ method as a tool for creative problem solving, that have been developed and applied in many fields ranging from engineering as well as management, this study aims to solve the education dilemma between learning efficiency and learning effectiveness, create a new concept of the flipped learning based on the solutions, and then explore its educational feasibility for successfully adopting it to engineering courses. This study suggests an instructional design for implementing the flipped learning according to the characteristics of engineering classes and then designs a new model of the flipped learning according to that procedure. Also, based on the empirical results in applying a new flipped learning model to the applied mathematics, this paper proposes several guidelines for the successful application of flipped learning in the future.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2007년도 추계학술대회 논문집
• /
• pp.1846-1851
• /
• 2007

According to the Railroad Safety Act and section 42 of the Enforcement Ordinance, railway operators should conduct railway safety training regularly(6 or 3 hours per three months). But Overall Railroad Safety Audit conducted 2006 pointed out nonfulfillment of a regulations on railway worker's safety training to each of every 4 railway operators, which proved that the training management had not carried out properly. E-learning is used in various fields with development of Internet and IT technologies. It might be a good alternative tool for railway workers who is in shift working of the company 24 hours a day. Because it is difficult to collect those employees for training, e-learning could overcome obstacles of time and distance. In order to find out suitable e-learning model to railway sector, e-learning system for railway safety training has been researched through investigating e-learning technology and present railway safety training condition.

• International Journal of Contents
• /
• 제16권3호
• /
• pp.18-32
• /
• 2020

The aim of this study was to perform a meta-analysis of the learning outcomes of immersive learning technologies in English language teaching (ELT). This study examined 12 articles, yielding a total of 20 effect sizes. The Comprehensive Meta-Analysis (CMA) program was employed for data analysis. The findings revealed that the overall effect size was 0.84, implying a large effect size. Additionally, the mean effect sizes of the dependent variables revealed a large effect size for both the cognitive and affective domains. Furthermore, the study analyzed the impact of moderator variables such as sample scale, technology type, tool type, work type, program type, duration (sessions), the degree of immersion, instructional technique, and augmented reality (AR) type. Among the moderators, the degree of immersion was found to be statistically significant. In conclusion, the study results suggested that immersive learning technologies had a positive impact on learning in ELT.