• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.247-275
• /
• 2021

Purpose This study attempted to predict corporate innovation and business performance using ensemble learning. Design/methodology/approach The ensemble techniques uses weak learning to create robust learning, which combines several weak models to derive improved performance. In this study, XGboost, LightGBM, and Catboost were used among ensemble techniques. It was compared and evaluated with traditional machine learning methods. Findings The summary of the research results is as follows. First, the type of innovation is expanding from technical innovation to non-technical areas. Second, it was confirmed that LightGBM performed best for radical innovation prediction, and XGboost performed best for incremental innovation prediction. Third, Catboost performed best for firm performance prediction. Although there was no significant difference in predictive power between ensemble techniques, we found that comparative analysis was necessary to confirm better prediction performance.

• Educational Technology International
• /
• v.9 no.2
• /
• pp.123-142
• /
• 2008

The purpose of this study was to examine how computer conferencing might facilitate collaborative learning for students to engage in meaningful discussion. The participants in this study consisted of the instructor and the students in a graduate level course. Different sources of evidence were used to triangulate the data: in-depth interviews, content analysis of transcripts of discussion, and other archival data including course syllabus, presentation materials, and lecture notes. Participants perceived web-based learning as collaborative process, providing opportunities to share the idea, respect and evaluate different perspectives, and co-construct new insights. Analysis of the data revealed several challenges related collaboration in a web-based learning environment: absence of a sense of community, technical problems, adaptability to different types of learner, and managing the discussion. The data also indicated that a variety of strategies were used to facilitate learning: building a sense of community, technical support, developing instructional methodologies, class size, and design of the content.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.204-211
• /
• 2020

The era of the 4th industrial revolution is a complex environment in which the cyber world and the physical world are integrated and interacted. In order to successfully implement and be sustainable the 4th industrial revolution of hyper-connectivity, hyper-convergence, and hyper-intelligence, not only the technological aspects that implemented digitalization but also the social aspects must be recognized and dealt with as important. There are socio-technical systems and socio-technical systems theory as concepts that describe systems involving complex interactions between the environmental aspects of human, mechanical and tissue systems. This study confirmed how the Socio-technical System was applied in the research literature for the last 10 years through machine learning-based analysis. Eight clusters were derived by performing co-occurrence keywords network analysis, and 13 research topics were derived and analyzed by performing a structural topic model. This study provides consensus and insight on the social and technological perspectives necessary for the sustainability of the 4th industrial revolution.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.01a
• /
• pp.51-52
• /
• 2018

산업 현장에서 작업자의 잘못된 작업행동으로 인한 안전사고가 꾸준히 발생하고 있다. 현재는 관리자가 육안으로 작업자의 위험행동 여부를 관리하고 있지만, 모든 작업자를 관리자 한명이 관리하기에는 현실적으로 어려움이 있다. 본 논문에서는 이 문제를 해결하기 위해 고소 작업자의 안전벨트에 IoT 장치를 부착하여 행동 데이터를 클라우드에 업로드하고, 딥러닝을 통해 작업자 위험행동 여부를 분석한다. 분석한 결과를 관리자가 쉽게 모니터링 할 수 있도록 하여, 안전사고를 예방하도록 하는 시스템을 설계하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.253-254
• /
• 2019

본 논문에서는 딥러닝과 OpenCV를 이용해서 사람의 얼굴에서 나이 성별을 추출하고 추출된 데이터를 기반으로 야외에 설치된 디스플레이 광고를 맞춤형으로 제공한다 이를 통해 광고를 좀 더 효과적으로 사용할 수 있는 방안을 제공한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.15-16
• /
• 2020

본 논문에서는 산업 현장에서 사용되는 기계들의 건전성을 유지하고 예측하는 시스템을 개선할 수 있는 연구 결과를 비교하고 설명한다. 이번 연구에서는 딥러닝 기술을 이용함으로서 특정장치에 종속되지 않고 범용적으로 수집된 소음데이터를 사용하여 현장 적용의 유연성을 높이고, 딥러닝 모델 중 GRU를 이용하여 기존 연구 결과와 비교 실험을 하여 더 우수한 결과를 얻었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.59-60
• /
• 2022

본 논문에서는 유아 영어 단어 학습 애플리케이션을 설계하고 구현한다. 이 애플리케이션은 키넥트 센서의 음성 인식 기능을 활용하여 동물과 음식 분야의 단어 학습 기능을 제공한다. 화면에 출력된 이미지에 해당하는 영어 단어를 말하면 키넥트 센서에서 그 음성을 인식하여 해당 단어의 발음이 정확한지 판별한다. 주어진 시간 내에 다양한 단어를 정확하게 발음함으로써 높은 점수를 취득하도록 구현한다.

• Journal of information and communication convergence engineering
• /
• v.19 no.4
• /
• pp.248-256
• /
• 2021

The purpose of this study was to introduce an application as a learning medium that can be used by students to prepare Solo bridal paes. This application can be used by make-up beginners who are learning about Solo bridal paes. This study used a quasi-experimental method with a randomized pretest-posttest control group. The paes application can be used as a medium in Solo bridal makeup learning, because it is highly effective in helping students prepare Solo bridal paes. This application is also considerably practical because it can be installed on smartphones. Experimental results revealed a difference between the control and experimental classes. Students in the experimental class could prepare paes neatly, and their shapes were proportional to the face of the model. The use of augmented reality as a medium to teach Solo bridal makeup, especially for making paes, is an innovation in the world of education. This application can help students make paes.

• 대한공업교육학회지
• /
• v.31 no.1
• /
• pp.23-45
• /
• 2006

The purpose of this study is to develop a instructive strategy model of cooperative learning for practical class in technical high school. To achieve this purpose, this study has conducted related literature investigation and interviewed with professionals for reconstruction of practice contents. As a result, 15 steps instructional strategy model of cooperative learning was designed and this model based on traditional 4 steps model, Jigsaw and STAD model which have been verified as effect. To complete the final project, all the team members must cooperate themselves and tutor their peers with learning guides which are constructed as a modular system. This instructional strategy model which is correlated with modular instruction, peer tutoring and cooperative learning is expected to enhance students' school work of psychomotor domain as well as cognitive domain and affective domain.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.49-66
• /
• 2015

The increase of social interest for the e-Learning industry leads to the increase of e-learning contents and the system providers which are targeted at private education companies and public institutions. As the e-Learning is used in various areas, the evaluation for evaluation criteria and suitability are needed to provide a high-quality service and reliability. Previous works suggested the evaluation criteria for quality certification, however, the technical evaluation criteria are not provided. In this paper, we suggest the technical evaluation criteria for quality certification of e-Learning contents and describe the detailed features. Through the proposed work, we can establish the technical evaluation criteria and suggest detailed evaluation items for them by providing examples. It is expected that the proposed study is able to be utilized in e-Learning industry, if the policy is reflected and notified according to the feedback of the results of the trial service.