• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.12-12
• /
• 2021

현행 하도현황조사는 조사망에 따라 조사대상 하천의 하천기본계획 등을 통해 조사지점을 선정하므로 전체 하천구간의 하도특성 파악에 어려움이 있고, 하천기본계획의 수립년도와 현황조사시 기간에 차이가 있을 경우, 하도특성의 경년적 변동성 파악이 어렵다. 최근 이러한 문제점을 극복하기 위하여 하천조사에 인공위성, 드론 등을 활용한 원격탐사방법이 증가하고 있으며, 유역 성과활용도 조사에서도 위성영상자료 활용의 확대요구가 있다. 본 연구는 중랑천을 대상으로 유럽우주국(ESA)의 Sentinel-1을 활용하여 하도현황조사의 기초가 되는 맞춤형 최적화 수체추출기법을 개발하였다. 이를 위하여 중랑천 지역에 대한 50여 장의 Sentinel-1 위성자료를 수집하였고, 하천 중심선에 대한 유클리드 거리를 가중치로 산정하여 K-mean 군집화를 진행하였다. 검증을 위하여 Sentinel-1과 24시간 이내 촬영된 PlanetLab사(社)의 PlanetScope 영상자료로 정확성을 평가하였다. 그 결과 최대 70%에 근접하는 정확도를 보였다. 본 방법은 현존하는 수체추출방법보다 간단하고 신속하게 수체를 추출할 수 있을 것으로 보인다. 추후 딥러닝을 통한 수체 식별을 추가 진행할 예정이며, 정확도를 높일 수 있을 것으로 기대한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.621-623
• /
• 2023

본 논문에서는 기계 학습 모델의 취약점과 대응책에 초점을 맞추어 적대적인 기계 학습 공격 및 방어 분야를 탐구한다. 신중하게 만들어진 입력 데이터를 도입하여 기계 학습 모델을 속이거나 조작하는 것을 목표로 하는 적대적 공격에 대한 심층 분석을 제공한다. 이 논문은 회피 및 독성 공격을 포함한 다양한 유형의 적대적 공격을 조사하고 기계 학습 시스템의 안정성과 보안에 대한 잠재적 영향을 조사한다. 또한 적대적 공격에 대한 기계 학습 모델의 견고성을 향상시키기 위해 다양한 방어 메커니즘과 전략을 제안하고 평가한다. 본 논문은 광범위한 실험과 분석을 통해 적대적 기계 학습에 대한 이해에 기여하고 효과적인 방어 기술에 대한 통찰력을 제공하는 것을 목표로 한다.

• Journal of Internet Computing and Services
• /
• v.10 no.1
• /
• pp.135-143
• /
• 2009

The purpose of this study was to explore factors that affected the satisfaction of students' experiences in an education course, with the educational method and educational technology designed with a blended learning strategy. Blended learning is currently recognized as a good solution for the problems posed by both online and face-to-face learning, because it has features like flexibility and accessibility by using tools supporting both individualization and socialization. This study is one case that illustrates how blended learning can be applied at the university level. Subjects were 56 students who had participated in the class and responded to the survey questions. The gathered data were analyzed by using Factor Analysis and the Structural Equation Model. Based on the results of Factor Analysis, data revealed 5 factors: learning motivation, previous experience, ability to use information & technology, capability of self-regulated learning, and learning satisfaction. The results of the Structural Equation Model revealed causal relationships among the aforementioned factors as follows: (a) there was a statistically meaningful causal relationship between "learning motivation" and "capability of self-regulated learning", (b) there was a statistically meaningful casual relationship between "previous experience" and "capability of self-regulated learning", and (c) "capability of self-regulated learning" directly affected "learning satisfaction".

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.375-384
• /
• 2017

This paper is intended to provide a good lecture to computer utilizing courses in the Department of Nursing, therefore first analyzes the outlines of relevant qualifying examinations as well as the contents of the textbooks and syllabus that are currently taught in universities, and then design the curriculum by applying blended learning for effective proceedings of computer-utilizing course. The curriculum for computer-utilizing course which this paper suggests is based on blended learning which blends face-to-face classes with e-learning classes, and its two tracks of teaching and practice include weekly core areas, teaching goals, and subjects. Therefore, this curriculum is expected to lead to excellent learning outcomes as it will become a good teaching scheme for teachers and will motivate students to acquire license. and to find employment.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.5
• /
• pp.631-636
• /
• 2019

Over the last decade, many researchers have investigated a number of vision-based construction object detection algorithms for the purpose of construction site monitoring. However, previous methods require the ground truth labeling, which is a process of manually marking types and locations of target objects from training image data, and thus a large amount of time and effort is being wasted. To address this drawback, this paper proposes a vision-based construction object detection framework that employs an active learning technique while reducing manual labeling efforts. For the validation, the research team performed experiments using an open construction benchmark dataset. The results showed that the method was able to successfully detect construction objects that have various visual characteristics, and also indicated that it is possible to develop the high performance of an object detection model using smaller amount of training data and less iterative training steps compared to the previous approaches. The findings of this study can be used to reduce the manual labeling processes and minimize the time and costs required to build a training database.

• The Journal of the Korea Contents Association
• /
• v.21 no.7
• /
• pp.500-509
• /
• 2021

The purpose of this study is to find out the effect and possibility of instructional design conducted by integrating writing education and community service activities based on service learning. Service learning is a teaching method that encourages students to improve learning and self-development through experience by applying the knowledge they have learned in college to the real life of the community. After the course was operated, the effectiveness of the teaching method investigated and analyzed for the participating university students, beneficiaries of service, and staffs of service organization. As a result of the study, meaningful results in cognitive, affective, and social aspects were presented for university students, and positive effects and high satisfaction were confirmed for beneficiaries of service and staffs. As a teaching methord that considers the growth and development of students from various angles. the quantitative and qualitative performance analysis and research of service learning should be conducted continuously.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.973-980
• /
• 2023

This study analyzed the effects of a Micro-learning content-based extracurricular program among university students based on their general characteristics. A survey was conducted on 600 students affiliated with G University, a major national university. Learning immersion and learning motivation were used as the key indicators for measuring the learning effects. Cronbach's α coefficient analysis was performed to validate the reliability of the learning effect measurement tool. Independent sample t-tests were utilized to analyze differences in learning immersion and learning motivation based on gender and major disciplines. One-way analysis of variance (ANOVA) was employed to measure differences in learning immersion and learning motivation according to academic year. According to the research findings, gender and academic year did not significantly influence participation in the Micro-learning content-based program. However, differences in learning immersion and learning motivation were observed depending on the major discipline. Based on this, it is suggested that future programs should provide suitable environments and stimuli based on the students' major disciplines.

• Journal of the Korean Society of Radiology
• /
• v.12 no.2
• /
• pp.225-231
• /
• 2018

Recently, new teaching methods for communicating with teachers and students have been emerged according to the trends of decreasing the school-age population and the development of the mass media. We have applied teaching-learning model based on the flip learning to the college students in this work. As a result of the test for the customized flipped learning teaching-learning model in pre-class, the attendance rate of the major subject was 92.3% whereas that in liberal arts courses other than majors revealed 87.6%. This result for attendance rate shows that first year students in the radiology department have been actively participated in pre-class of the major subject than that of the liberal arts curriculum. From comparing the differences between the study group that was applied flipped learning in class and the non-applied group, the research group showed higher scores in knowledge, skills, and attitudes than the comparative group. In addition, more than 90% of the learners improved their responsibility, problem solving ability, creative thinking, cooperative ability, and communication ability through this learning program. From the test for the difference in the role of radiologists in the post class, the mean score was 4.40 for the group applied the teaching-learning model while that for non-applied group was 2.10. Hence, from such results, we see that this teaching-learning model is appropriate and needs to be extended to cultivate basic skills in radiology and relevant vocational education.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.2 no.2
• /
• pp.10-15
• /
• 2010

The subject of basic fluid power practice which is used in various industries requiring factory automation aims at understanding of the composition and operating principles of pneumatic components and programming of electric sequential circuits, building the design ability of pneumatic system. This subject goes by 3 hour classes with theory and practice side by side. So it is not enough time to instruct students various contents related in this subject. In this research a supplementary learing using E-learning is proposed as a solution for this problem. The off-line classes of this subject went with E-learning side by side and analyzed the effects of E-learning as a supplementary learning through the students survey who attended the class. And further needed research is presented.

• Journal of Digital Convergence
• /
• v.17 no.8
• /
• pp.71-80
• /
• 2019

It is very important to have pre-service teachers enhance actual content development skill for STEAM classes through deep understanding of the concept. Thus the purpose of the study is to explore the educational methodology for improving pre-service teachers' competence of designing STEAM classes. The research performed with 17 pre-service teachers from Y university and 15 from S university in 2015. It includes blended learning methodology mixing online and offline classes. The result revealed that the students' perception on and the materialization skill of the STEAM education was improved by the methods of Lesson Study and blended learning. A positive result also came out in the respect of the perception on teaching with technology.