• Proceedings of the Korean Society of Computer Information Conference
• /
• 2015.01a
• /
• pp.329-330
• /
• 2015

최근 한류의 유행과 결혼 이주여성 등의 증가로 인해 다양한 첨단 미디어를 통하여 세계 각국에서 외국어로서의 한국어를 배우려는 학습자의 수가 증가하고 있다. 교수자와 학습자간의 교육환경은 다양한 학습미디어의 발전에 따라 학습자가 수동적인 자세에서 벗어나 능동적인 학습 방법으로 진화되고 있다. 특히 다양한 멀티미디어 기기와 관련 기술들의 발전은 기존의 교육방법론적 환경에서 벗어나, 새로운 기술에 기반을 둔 학습자 중심의 교육방법의 개선과 제시에는 현실적으로 고려해야하는 여러 사항과 문제점이 존재한다. 따라서 이 논문에서는 최신 기술에 기반을 둔 모바일을 이용한 엠러닝(M-Learning) 기반의 한국어교육 콘텐츠관리를 위한 시스템을 제안하고자 한다.

• Journal of the Korea Convergence Society
• /
• v.1 no.1
• /
• pp.1-15
• /
• 2010

The Education has responsibility for predicting the social changes and cultivating global talent which the society needs. The ministry of education, science and technology in govern ment has been the concerns on social educational changes and thus built the '5 31 educational reform policy' in 1995 by the educational reform committee. As a solution of a social change, this paper reviews the three-phase educational information policies, and e-learning and u-learning which are the main technologies in educational information. Also, the technologies of e-learning can be divided into m-learning, t-learning, u-learning, r-learning, game-based learning according to the contents mass media. Among them, this paper introduces the concept of robot-learning, called r-learning, and compares it with u-learning.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.04a
• /
• pp.123-124
• /
• 2022

The work of modeling and calculating the quantity of detailed parts requires a lot of time and effort. However, The information of BIM Model can be used to predict the amount of uncreated parts with Deep Learning. In this study, Deep Learning was used to predict the total length of the member of frame that was not created. As a result, it was confirmed that the error rate was inside or outside 3%. And predicting other components in this way will increase productivity in Architectural field.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.1
• /
• pp.1-10
• /
• 2021

This study proposed a Long-Short Term Memory network to consider changes in emotion over time, and applied an attention mechanism to give weights to the emotion states that appear at specific moments. We used 32 channel EEG data from DEAP database. A 2-level classification (Low and High) experiment and a 3-level classification experiment (Low, Middle, and High) were performed on Valence and Arousal emotion model. As a result, accuracy of the 2-level classification experiment was 90.1% for Valence and 88.1% for Arousal. The accuracy of 3-level classification was 83.5% for Valence and 82.5% for Arousal.