• 한국컴퓨터정보학회논문지
• /
• 제24권8호
• /
• pp.87-93
• /
• 2019

These days, as interest in the recommendation system with deep learning is increasing, a number of related studies to develop a performance for collaborative filtering through autoencoder, a state-of-the-art deep learning neural network architecture has advanced considerably. The purpose of this study is to propose autoencoder which is used by the recommendation system to predict ratings, and we added more hidden layers to the original architecture of autoencoder so that we implemented deep autoencoder with 3 to 5 hidden layers for much deeper architecture. In this paper, therefore we make a comparison between the performance of them. In this research, we use 2-dimensional arrays and 3-dimensional tensor as the input dataset. As a result, we found a correlation between matrix entry of the 3-dimensional dataset such as item-time and user-time and also figured out that deep autoencoder with extra hidden layers generalized even better performance than autoencoder.

• East Asian mathematical journal
• /
• 제35권4호
• /
• pp.509-528
• /
• 2019

As various changes in education in general and learning environment in particular have promoted different needs and expectations for learning at both personal and social levels, the roles that schools and school teachers typically have with respect to their students are being challenged. Especially with the recent, rapid progress of the artificial intelligence(AI) field, AI could serve beyond the way in which it has been used. Based on a review of some of the related literature and the current development of AI, a view on utilizing AI to be a collaborative, complementary partner with an human mathematics teacher in the classroom in order to support both students and teachers will be discussed.

• International Journal of Advanced Culture Technology
• /
• 제12권3호
• /
• pp.336-344
• /
• 2024

The purpose of this study is to analyze the need of college students for experiential learning, collaborative learning, and enquiry-based learning. To achieve this goal, a survey was conducted with 308 college students. The need for experience, collaboration, and enquiry-based learning was comprehensively analyzed through t-tests, Borich needs analysis, and priority determination using The Locus for Focus model. The research findings are as follows: First, in Borich need analysis, the highest needs were identified for deep learning, self-directed learning, connecting theoretical knowledge with practical application, immersion, and application to real-life situations. Second, in The Locus for Focus model, the highest needs were found for abstract conceptualization, interest, conflict management, self-directed learning, and curiosity. In summary, since self-directed learning showed the highest priority simultaneously in Borich need analysis and The Locus for Focus model, it should be considered as the most prioritized item.

• 의학교육논단
• /
• 제18권3호
• /
• pp.167-173
• /
• 2016

This study analyzed participation experiences in a voluntarily learning community using both quantitative and qualitative methods. Sixty freshmen and sophomore medical school students in 10 learning communities participated in the study. At the time of the survey, learning communities had been operating for 10 weeks and had weekly in-person meetings. Satisfaction questionnaires and reflective essays were given and analyzed. The results showed that learning community experiences were effective in promoting students' learning motivation, cooperative learning, responsibility, and communication skills. Three essential topics and nine subjects were analyzed in the reflective essays. Three essential topics were conflict with each other due to the difference, forming deep relationships, and sharing and learning together with an in-depth study. The results of this study will contribute to collaborative learning culture and the development of learning communities in medical schools.

• Educational Technology International
• /
• 제8권1호
• /
• pp.91-100
• /
• 2007

This paper describes the experiences of three middle school teachers during the year following a two-week summer workshop in which they were introduced to a technology-enhanced problem-based learning (PBL) pedagogy. Based on their collaborative experiences during the school year, developing and implementing a PBL unit, the three teachers increased their confidence in using technology and indicated shifts in their pedagogical beliefs regarding classroom instruction. Results suggest that administrative support, collaboration with other teachers, and the development of a school culture that valued the sharing of teachers' experiences were keys to teachers' successful implementation.

• International Journal of Advanced Culture Technology
• /
• 제9권1호
• /
• pp.162-167
• /
• 2021

The aim of this paper is to analyze the development of effective online Problem-Based Learning (PBL) and Project-Based Learning (PjBL). The collaborative PBL/PjBL become one of the hot issues with the rapid growth of online learning in the era of COVID-19. Educators try to get innovative to continue instruction without sacrificing student engagement, thus adopting an instructional model of PBL/PjBL. The PBL process involves clarifying terms, defining complex problems, brainstorming, structuring and hypothesis while PjBL includes project-planning, implementation, communicating the results of a project in a presentation and evaluations with immediate individually tailored feedback within a predetermined period. Despite the differences between online and offline learning, the benefits of learning online or offline are practically the same if enough bidirectional interactions between instructors and students are possible. We argue that online qualifications are just the same as those of offline ones in PBL/PjBL models, therefore, the standards of online/offline learning are identical since education is a two-way communication.

• International Journal of Advanced Culture Technology
• /
• 제10권2호
• /
• pp.43-52
• /
• 2022

This study used a descriptive survey design to examine the impact of the clinical learning environments and learning transition nursing students experienced the gerontological nursing clinical on the satisfaction with clinical practice. A convenient sample of 211 4^th year nursing students who had the gerontological nursing clinical practicum from one College of Nursing at Private University in South Korea was recruited and completed the surveys from October to December 2019. This study showed that the satisfaction with a gerontological nursing clinical practicum was significantly correlated with clinical learning environments and learning transition. The results of this study highlights the need to create a safe and positive clinical learning environment for quality gerontological nursing clinical practicum, so hospitals and nursing schools need to make efforts to promote clinical sites as an educational learning environment in collaborative relationships.

• 대한수학교육학회지:학교수학
• /
• 제5권2호
• /
• pp.191-208
• /
• 2003

본 연구는 수학 및 과학 영재 아동과 일반 아동의 성격유형과 학습양식의 차이를 알아보는 것을 목적으로 하였다. 이를 위해 수학 및 과학 영재교육을 받고 있는 부산광역시 소재의 초등학교 5, 6학년 135명과 일반아동 66명을 대상으로 하여 MMTIC과 학습양식검사를 실시하였다. 성격유형의 분석은 선호지표와 기능별, 기질별 분포를 중심으로 하였고, 학습양식은 독립형, 의존형, 협동형, 경쟁형, 참여형, 회피형의 유형으로 분류되었다. 연구결과에 의하면, 수학 및 과학 영재 아동은 성격유형, 학습양식 그리고 성격유형에 따른 학습양식에서 큰 차이가 없었으나, 일반 아동과는 유의한 차이를 나타냈다. 또한 연구대상의 성격유형에 따라 선호하는 학습양식에는 차이가 있는 것으로 나타났다.

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.148-157
• /
• 2021

The effectiveness of recommendation systems depends on the performance of the algorithms with which these systems are designed. The quality of the algorithms themselves depends on the quality of the strategies with which they were designed. These strategies differ from author to author. Thus, designing a good recommendation system means implementing the good strategies. It's in this context that several research works have been proposed on various strategies applied to algorithms to meet the needs of recommendations. Researchers are trying indefinitely to address this objective of seeking the qualities of recommendation algorithms. In this paper, we propose a new algorithm for recommending learning items. Learner performance predictions and collaborative recommendation methods are used as strategies for this algorithm. The proposed performance prediction model is based on convolutional neural networks (CNN). The results of the performance predictions are used by the proposed recommendation algorithm. The results of the predictions obtained show the efficiency of Deep Learning compared to the k-nearest neighbor (k-NN) algorithm. The proposed recommendation algorithm improves the recommendations of the learners' learning items. This algorithm also has the particularity of dissuading learning items in the learner's profile that are deemed inadequate for his or her training.

• 한국컴퓨터정보학회논문지
• /
• 제26권3호
• /
• pp.9-17
• /
• 2021

동적 시스템 환경에서 지능형 협업 자율 시스템을 위한 기계학습 기반의 다양한 방법들이 연구 및 개발되고 있다. 본 연구에서는 분산 노드 기반 컴퓨팅 방식의 자율형 다중 에이전트 경로 탐색 방법을 제안하고 있으며, 지능형 학습을 통한 시스템 최적화를 위해 강화학습 방법을 적용하여 다양한 실험을 진행하였다. 강화학습 기반의 다중 에이전트 시스템은 에이전트의 연속된 행동에 따른 누적 보상을 평가하고 이를 학습하여 정책을 개선하는 지능형 최적화 기계학습 방법이다. 본 연구에서 제안한 방법은 강화학습 기반 다중 에이전트 최적화 경로 탐색 성능을 높이기 위해 학습 초기 경로 탐색 방법을 개선한 최적화 방법을 제안하고 있다. 또한, 분산된 다중 목표를 구성하여 에이전트간 정보 공유를 이용한 학습 최적화를 시도하였으며, 비동기식 에이전트 경로 탐색 기능을 추가하여 실제 분산 환경 시스템에서 일어날 수 있는 다양한 문제점 및 한계점에 대한 솔루션을 제안하고자 한다.