• Korean Journal of Radiology
• /
• 제24권7호
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권6호
• /
• pp.2799-2823
• /
• 2019

With the help of learning analytics, MOOCs have wider potential to succeed in learning through promoting self-regulated learning (SRL). The current study aims to apply and validate visualization design guidelines for a MOOC dashboard to enhance such SRL capabilities based on learning analytics. To achieve the research objective, a MOOC dashboard prototype, LM-Dashboard, was designed and developed, reflecting the visualization design guidelines to promote SRL. Then, both expert and learner participants evaluated LM-Dashboard through iterations to validate the visualization design guidelines and perceived SRL effectiveness. The results of expert and learner evaluations indicated that most of the visualization design guidelines on LM-Dashboard were valid and some perceived SRL aspects such as monitoring a student's learning progress and assessing their achievements with time management were beneficial. However, some features on LM-Dashboard should be improved to enhance SRL aspects related to achieving their learning goals with persistence. The findings suggest that it is necessary to offer appropriate feedback or tips as well as to visualize learner behaviors and activities in an intuitive and efficient way for the successful cycle of SRL. Consequently, this study contributes to establishing a basis for the visual design of a MOOC dashboard for optimizing each learner's SRL.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제11권2호
• /
• pp.153-163
• /
• 2007

Utilizing the quantitative analysis methodology of questionnaire, the study explores the differences in the factors of achievement motivation, learning mathematics attitude and learning mathematics self-confidence and also the relationship between mathematics academic achievement and these factors in three areas in China. The following conclusions are drawn: 1. The subjects from different development level areas have significant differences in motivation, attitude and self-confidence in mathematics; 2. The subjects from different areas who possess the same ethnic group have significant differences. But the subjects from same area who possess different nationalities have little difference. It can be concluded that that the differences in these factors can be contributed to regional differences, rather than to ethnic differences; 3. The subjects from undeveloped areas have significant gender differences, and the levels of males are higher than those of female.

• International Journal of Computer Science & Network Security
• /
• 제21권11호
• /
• pp.157-164
• /
• 2021

This endeavor is an attempt to explore the effect of flipped classroom strategy (FCS) on (a) academic achievement in the computer and information technology course and (b) students' attitudes towards this strategy. The sample of the study consisted of 64 students, divided into two groups: experimental and control groups. Two instruments were used to collect the data: a test and a questionnaire. The test was used to measure the students' achievement and the questionnaire to measure their attitudes towards the FCS. The results show statistically significant differences at the level of 0.05 in support of the experimental group at all Bloom's levels. Similarly, students' positive attitude towards the FCS was evident. Therefore, expanding this strategy in different courses is highly recommended because it positively impacts students' achievements. Organizing workshops and designing courses that encourage teachers to implement the strategy in the classroom and develop their technical skills are also recommended.

• International Journal of Contents
• /
• 제16권2호
• /
• pp.78-91
• /
• 2020

In this study, an investigation was conducted into the influencing factors for the learning motivation of players in the game, including experience, vicarious experience, the need of achievement, the need of power, and mastery motivation. Then, a discussion was conducted regarding the role played by learning motivation, learning performance, and satisfaction with continuous use. A survey was conducted with 519 players, most at the intermediate gaming level in . As demonstrated by the results of this study, experience, vicarious experience, the need of power, and the mastery of motivation have significant positive association with the players' motivation of learning the game. Learning performance and satisfaction have a positive impact on the continuity of use. Additionally, the correlation between the need of achievement and learning motivation is insignificant. Overall, the research results confirm the significance of the social-cognitive theory relative to the learning motivation. Players began to transform, satisfied with their achievements in the game, as well as gradually evolving toward self-improvement to achieve satisfaction. It offers a new explanation and crucial reference for mastering the gaming trend among the contemporary players.

• 한국해양공학회지
• /
• 제34권2호
• /
• pp.147-154
• /
• 2020

Underwater acoustics that is the study of the phenomenon of underwater wave propagation and its interaction with boundaries, has mainly been applied to the fields of underwater communication, target detection, marine resources, marine environment, and underwater sound sources. Based on the scientific and engineering understanding of acoustic signals/data, recent studies combining traditional and data-driven machine learning methods have shown continuous progress. Machine learning, represented by deep learning, has shown unprecedented success in a variety of fields, owing to big data, graphical processor unit computing, and advances in algorithms. Although machine learning has not yet been implemented in every single field of underwater acoustics, it will be used more actively in the future in line with the ongoing development and overwhelming achievements of this method. To understand the research trends of machine learning applications in underwater acoustics, the general theoretical background of several related machine learning techniques is introduced in this paper.

• Journal of Power Electronics
• /
• 제10권6호
• /
• pp.595-603
• /
• 2010

In this paper, teaching in a "switching converter (SC) design" course using problem-based learning (PBL) with dynamicbehavior- model simulation, given at Lunghwa University of Science and Technology (LHU), Taiwan, is proposed. The devised methodology encourages students to design and implement the SCs and regulate the controller's parameters in frequency domain by using 'sisitool' ('bode') in the MATLAB toolbox. The environment of PBL with converter characterization modeling and simulation reforms the learning outcome greatly and speeds up the teaching-learning process. To qualify and evaluate the learning achievements, a hands-on project cooperated with the continuous assessment approach is performed to modulate the teaching pace and learning direction in good time. Results from surveys conducted in the end of the course provided valuable opinions and suggestions for assessing and improving the learning effect of the proposed course successively. Positive feedbacks from the examinations, homework, questionnaires, and the answers to the lecturer's quizzes during class indicated that the presented pedagogy supplied more helpfulness to students in comparisons with conventional teaching paradigm, their learning accomplishments were better than expected as well.

• 교육심리연구
• /
• 제22권1호
• /
• pp.215-234
• /
• 2008

이 연구는 학습자의 받아쓰기 성취도와 독해력을 향상시키고 흥미를 유발하는 교수 학습 방법으로서 만화와 문자 빈칸 메우기 전략의 효과를 살펴보고자 실시되었다. 초등학교 1학년 학급 중 교과 흥미 사전검사와 국어과 읽기 학업성취 사전평가에서 동질성을 확보한 3개 학급을 선정하여, 실험집단 1은 만화 텍스트 빈칸 메우기 전략, 실험집단 2는 문자 텍스트 빈칸 메우기 전략을 활용하여 읽기 학습을 실시하였으며, 통제집단은 기존의 교과서 위주의 읽기 학습을 실시하도록 하여 총 15차시에 걸쳐 수업을 진행하였다. 실험 결과 첫째, 만화 텍스트 빈칸 메우기 전략의 활용은 교과흥미에 긍정적인 효과를 미쳤으며, 특히 하위 성취도 집단에서 더 큰 효과를 보였다. 둘째, 빈칸 메우기 전략의 활용은 사후 받아쓰기 성취도 및 지연된 받아쓰기 성취도에 긍정적인 영향을 미치며, 특히 하위 성취도 집단에서는 만화 텍스트의 활용이 더 효과적이었다. 셋째 직후 독해력 검사에서는 텍스트 유형에 상관없이 빈칸 메우기 전략을 활용한 읽기 학습이 독해력에 긍정적인 효과를 보였으며, 독해력 하위 요소 중 사실적 이해를 묻는 문항보다 추론적 이해를 묻는 문항에서 더욱 긍정적인 효과를 나타냈다. 이러한 연구결과를 통해 국어 읽기 학습에서 흥미 유발 및 학업성취도에 긍정적인 영향을 미치는 텍스트의 유형과 학습 전략에 대한 시사점도 논의하였다.

• 디지털융복합연구
• /
• 제19권4호
• /
• pp.1-8
• /
• 2021

본 연구는 가상 환경에서의 협력 학습에의 참여가 학생들의 학업 성취도와 만족도에 미치는 영향을 조사하고자 하였다. 세컨드라이프라는 가상현실 플랫폼에 고등학생이 국사 과목을 학습할 수 있는 공간을 만들고 이를 활용하였다. 총 119명의 참가자를 '협력학습 유형'이나 '개인학습 유형'에 무선 할당하였으며, 학생들의 학업 성취도와 만족도를 측정 도구로 수집하였다. 가상공간에서의 협력학습의 효과를 검토하려 독립표본 t검증 및 대응표본 t검증을 실행하였고, 연구의 결과는 개인학습 유형에 참여한 경우보다 협력학습 유형에 참여한 경우가 학업성취도와 만족도에 유의미하게 긍정적 영향을 미치는 것으로 나타났다. 마지막으로 향후 가상현실을 기반으로 한 협력학습의 활용에 대한 제언이 논의되었다.

• Educational Technology International
• /
• 제19권2호
• /
• pp.175-197
• /
• 2018

Flipped classroom (FC) has gained attention as an active learning approach. Designing effective out-of-class activities to help prepare students for in-class activities is fundamental for successful implementation of FC. This study investigated the effectiveness of Goal-Based Scenarios (GBS) for out-of-class learning in FC. Four out of twelve units in a medical humanities course for Year 2 medical students was redesigned into a FC format, where e-learning modules were designed using a GBS approach for out-of-class activities and classroom debates were implemented for in-class activities. The other eight units were delivered in a conventional classroom debate format, which included reading text materials as pre-class assignments. A formative evaluation study was conducted using questionnaires and interview methods and students' academic achievements were evaluated by comparing their pre- and post-test scores between FC and conventional units. Students had positive perceptions of the e-learning modules in GBS approach and preferred the structure of learning in the FC format. Students' pre-test scores were slightly higher in the FC units, yet their post-test scores were comparable with conventional units. This study illustrates students' perceptions that the learning was bettered structured in FC and that the out-of-class learning using the GBS approach helped them better prepared for in-class activities.