• Smart Media Journal
• /
• v.8 no.1
• /
• pp.67-73
• /
• 2019

This study investigates Active Learning and Facilitation Convergence Education Program which can improve core competency to cope with vocational education in the fourth industrial revolution era. I applied the integrated advantages of Active Learning which enhances 'problem solving skill' and those of Facilitation for creative thinking idea to application design process coursework and verified the effectiveness of such education method through student satisfaction survey. I also designed application contents for the students who are familiar with the mobile environments and UI contents for data visualization which can help those students to improve their skills in software. Every coursework was conducted as a team project. As a result, Active Learning and Facilitation Convergence Education Program is found to be helpful in improving the basic skills and competencies required in college education. I hope this work helps to reduce the educational gap between industry and professional colleges.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.425-431
• /
• 2023

음성 어시스턴트 시스템에서 발화의 의도를 분류하고 새로운 의도를 탐지하는 것은 매우 중요한 작업이다. 끊임없이 인입되는 새로운 발화로 인해 기존에 학습된 모델의 의도 분류 성능은 시간이 지남에 따라 점차 낮아진다. 기존 연구들에서 새로운 의도 발견을 위해 제안되었던 클러스터링 방법은 최적의 클러스터 수 결정과 명명에 어려움이 있다. 이러한 제한 사항을 보완하기 위해, 본 연구에서는 대규모 언어 모델 기반의 효과적인 의도 발견 방법을 제안한다. 이 방법은 기존 의도 분류기로 판단하기 어려운 발화에 새로운 의도 레이블을 할당하는 방법이다. 새롭게 인입되는 OOD(Out-of-Domain) 발화 내에서 오분류를 찾아 기존에 정의된 의도를 탐지하고, 새로운 의도를 발견하는 효율적인 프롬프팅 방법도 분석한다. 이를 액티브 러닝 전략과 결합할 경우, 분류 가능한 의도의 개수를 지속 증가시면서도 모델의 성능 하락을 방지할 수 있고, 동시에 새로운 의도 발견을 자동화 할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.712-715
• /
• 2023

딥러닝 기술의 발전은 고품질의 대규모 데이터에 크게 의존한다. 그러나, 데이터의 품질과 일관성을 유지하는 것은 상당한 비용과 시간이 소요된다. 이러한 문제를 해결하기 위해 최근 연구에서 최소한의 비용으로 최대의 성능을 추구하는 액티브 러닝(active learning) 기법이 주목받고 있는데, 액티브 러닝은 모델 관점에서 불확실성(uncertainty)이 높은 데이터들을 샘플링 하는데 중점을 둔다. 하지만, 레이블 생성에 있어서 여전히 많은 시간적, 자원적 비용이 불가피한 점을 고려할 때 보완이 불가피 하다. 본 논문에서는 의사-라벨링(pseudo labeling)을 활용한 준지도학습(semi-supervised learning) 방식과 학습 손실을 동시에 사용하여 모델의 불확실성(uncertainty)을 측정하는 방법론을 제안한다. 제안 방식은 레이블의 신뢰도(confidence)와 학습 손실의 최적화를 통해 비용 효율적인 데이터 레이블 생성 방식을 제안한다. 특히, 레이블 데이터의 품질(quality) 및 일관성(consistency) 측면에서 딥러닝 모델의 정확도 성능을 높임과 동시에 적은 데이터만으로도 효과적인 학습이 가능할 수 있는 메커니즘을 제안한다.

• 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.

• Review of Korea Contents Association
• /
• v.2 no.1
• /
• pp.73-79
• /
• 2004

인터넷의 발달로 인하여 다양한 기술 또는 제품들이 쏟아져 나오면서 새롭게 떠오르는 분야 중 사이버 교육은 성장 가능성이 매우 큰 시장이다. 2000년 국내에 사이버교육이 본격적으로 도입됨에 따라 세계적으로 높은 우리나라의 교육열과 교육수준에 힘입어 기업, 대학, 공공기관, 초중고 등에 사이버 교육시스템이 구축되었으며, 강의 컨텐츠를 제작하기 위한 e러닝 저작툴이 개발되어지기 시작하였다.(중략)

• Journal of Practical Engineering Education
• /
• v.5 no.2
• /
• pp.101-107
• /
• 2013

Clickers that are personal response systems are a technology used to promote active learning and most research on the benefits of using clickers has shown that students become engaged and enjoy using them. But, existing clickers consisting of hardware devices and aggregation software provide simple response and aggregation function and it costs a lot. In this paper, in order to resolve the limitation of the existing clickers, we've designed and implemented the Smart Clicker consisting of a smartphone application for students and a web application & a MFC program for professors. Students can answer professor's questions with O/X or numbers or text and even ask questions with text messaging by using Smart Clicker in the classroom. Professors can see students' answers or questions immediately and check up students' response participation rate on the web page. Besides, the Smart Clicker will help professors actively engage students during the entire class period and gauge their level of understanding of the material being presented, and provide prompt feedback to student questions. As a result, we expect that quality of education will be increased.

• The Korean Journal of Emergency Medical Services
• /
• v.23 no.2
• /
• pp.61-73
• /
• 2019

Purpose: This study aimed to introduce active learning methods, including flipped, case-based, and team-based learning in an electrocardiography (ECG) course and to investigate outcomes and satisfaction with these methods. Methods: To identify the learning effect of active learning, pre-and post-academic self-efficacy was compared between the experimental and control groups. In the experimental group, pre-and post-knowledge and clinical performance regarding ECG were also assessed. In addition, class satisfaction was investigated after application of active learning methods in the experimental group. Data were collected from 84 paramedic students and analyzed using SPSS 22.0 (IBM, Armonk, NY, USA). Results: The experimental group showed significant improvement in post-academic self-efficacy and knowledge. The experimental group also showed high clinical performance (9.83 out of 10 in ECG checking ability and 9.63 out of 10 in ECG reading ability). The mean satisfaction score was 4.23 out of 5 (responses based on a Likert scale) in the experimental group. Conclusion: Active learning in an ECG course was found to be highly effective and satisfactory. Furthermore, paramedic students can enhance their accountability and judgement with team-based learning through free engagement in discussion.