• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2011.11a
• /
• pp.23-26
• /
• 2011

U-러닝은 유비쿼터스러닝(Ubiquitous Learning)의 약자로 개방적 학습자원을 학습자의 필요에 따른 선택에 의해 활용하는 통합적 학습체제 의미한다. 국내에서의 소방교육은 다양한 소방교육 컨텐츠부족 및 시간적 공간적 제약으로 인해 소방안전에 대한 교육이 원활히 이루어지지 못하고 있는 실정이다. U-Learning 구성하여 다양한 컨텐츠를 거주자, 근무자, 방화관리자에게 제공하여 자기주도적인 학습을 통해 평상시 거주자 및 근무자에게 소방시설의 이해 및 사용방법을 교육하고, 방화관리자에게는 소방시설의 관리 및 점검방법을 교육함으로써 화재 및 재난으로 인한 피해를 최소화 할 수 있다.

• Communications of the Korean Institute of Information Scientists and Engineers
• /
• v.24 no.2 s.201
• /
• pp.51-55
• /
• 2006

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.565-568
• /
• 2008

우리나라의 경우에서처럼 인터넷 인프라 환경을 이용한 e-러닝은 교육인적자원부의 사이버가정학습을 시작하여, 사설 학원에서 수익모델로 많은 e-러닝 콘텐츠가 개발되어 상용화 되고 있다. 대학에서는 사이버 대학 및 사이버 과목을 수강하여 공식적인 학점으로 인정을 받은 단계는 정착화 되고 있는 실정이지만, 아직 활용도 차원에서는 활발한 활동이 이루어지지는 않는 것으로 본문의 'e-러닝학습의 문제점'을 보면서 알 수 있다. 본 논문에서는 특히 대학교육의 유비쿼터스 컴퓨팅 환경에서 e-러닝을 접목하여 새로운 교육의 패러다임을 적용한 u-러닝 활용방안을 연구하고 앞으로 e-러닝의 발전방향을 연구하고자 한다.

• Information Systems Review
• /
• v.17 no.2
• /
• pp.101-132
• /
• 2015

National technical qualifications to enhance an individual's vocational skills, the competitiveness of companies and countries have an important function to improve. Especially 'qualifications' will have a signal function to show objectively measure an individual's ability with the 'Education' The "knowledge necessary for the performance of their duties. Technology will gain knowledge about such assessment or recognition is based on certain criteria and procedures." Learning to qualify are being made through a smart learning a lot. Due to the revolution of the Internet in recent years with the development of information and communication technologies are entering into a knowledge society, the importance of information and knowledge. This contemporary smart learning education system is continuing to rapidly growing in pace with the changing time and space constraints, without teaching and learning is taking place. The purpose of this study is the ARCS motivation theory can determine a representative theory of human motivation factors and basic psychological needs dealing with the human nature of the psychological needs Interactivity and immersive learning, and to validate the empirical causality Affecting the continued use of smart learning through fun. Specifically, attention, relevance, confidence in the ARCS motivation, see their effect on the learning flow through the satisfaction we analyze empirically. Through this national technical qualifications smart learner's learning by supporting the implicit synchronization of students in learning are the degree of continued use. Therefore, to achieve the objectives of national technical qualifications and skills through a smart learning can contribute to the activation of the development and certification of course industry.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.329-331
• /
• 2018

지속적인 딥러닝 기반의 영상처리 기술의 발전으로 객체분류나 객체검출 문제에 대해서 뛰어난 성능 보이고 있다. 하지만 객체추적 문제에서는 성능이 좋은 추적기는 실시간 동작이 불가능하고 딥러닝 기반의 객체추적도 단일 객체에만 고려한 기법이 많기 때문에 개선할 필요가 있다. 전처리로 검출된 객체영역과 kalman filter를 통해 예측된 추적영역 간의 embedding feature 비교를 통해 동일인물인지 판단하여 고유 ID를 부여하고 추적한다. 객체끼리 교차하거나 가려지는 상황에서 추적을 실패하게 되는데 이 후에 지속적인 추적을 위해 IoU 비교를 통해 후보 추적기로 남겨두는 과정을 거친다. 실험 결과 실시간 동작여부와 객체끼리 교차하거나 프레임 밖으로 나갔다가 다시 나타나는 경우에도 추적이 가능함을 확인하였다.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.45-52
• /
• 2021

In this paper, we proposed an Atrous Residual U-Net (AR-UNet) to improve the segmentation accuracy of semantic segmentation method based on U-Net. The U-Net is mainly used in fields such as medical image analysis, autonomous vehicles, and remote sensing images. The conventional U-Net lacks extracted features due to the small number of convolution layers in the encoder part. The extracted features are essential for classifying object categories, and if they are insufficient, it causes a problem of lowering the segmentation accuracy. Therefore, to improve this problem, we proposed the AR-UNet using residual learning and ASPP in the encoder. Residual learning improves feature extraction ability and is effective in preventing feature loss and vanishing gradient problems caused by continuous convolutions. In addition, ASPP enables additional feature extraction without reducing the resolution of the feature map. Experiments verified the effectiveness of the AR-UNet with Cityscapes dataset. The experimental results showed that the AR-UNet showed improved segmentation results compared to the conventional U-Net. In this way, AR-UNet can contribute to the advancement of many applications where accuracy is important.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.603-605
• /
• 2018

최근 대두되고 있는 딥 러닝은 학습을 통해 사물이나 데이터를 군집화하거나 분류하는 데 사용하는 기술이다. 본 논문은 딥 러닝에 활용하기 위해 개발된 오픈소스 소프트웨어인 텐서플로 Inception V3을 사용해 연구를 진행했다. 딥 러닝을 활용한 씨앗 발아 확인 시스템은 기존의 영상 처리를 활용한 시스템에서 고안했으며, 씨앗 발아 여부의 정확성이 떨어지는 단점을 개선하고, 모든 종자들의 발아 여부를 확인할 수 있도록 구현해 사용자가 효과적으로 연구를 수행할 수 있도록 하는 목적에 있다.

• Journal of Digital Contents Society
• /
• v.9 no.2
• /
• pp.225-233
• /
• 2008

Rapid advancement information and communication technologies has introduced various dimension of e-Learning environment such as u-learning(ubiquitous learning), m-learning(mobile learning) and t-learning(television learning). These technologies enabled learners to access learning contents through variety of devices with more flexibility and consistency. In order to implement learning through these multiple environments, basically it is necessary to acquire and process the platform information that contains properties and status of the web-accessing devices. In this study, we introduce the design and implementation of a Platform Analyzer Model which is essential for learning systems that support multi-platform environment. We also present a Interactive DTV-Centered multi-platform learning environment framework using PC, PDA or Mobile phone. Finally, we will discuss the possibility of the multi-platform learning environment with sample scenario and contents.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.169-175
• /
• 2021

Recently, an ultrasound hologram and its applications have gained attention in the ultrasound research field. However, the determination technique of transmit signal phases, which generate a hologram, has not been significantly advanced from the previous algorithms which are time-consuming iterative methods. Thus, we applied the deep learning technique, which has been previously adopted to generate an optical hologram, to generate an ultrasound hologram. We further examined the Deep learning-based Holographic Ultrasound Generation algorithm (Deep-HUG). We implement the U-Net-based algorithm and examine its generalizability by training on a dataset, which consists of randomly distributed disks, and testing on the alphabets (A-Z). Furthermore, we compare the Deep-HUG with the previous algorithm in terms of computation time, accuracy, and uniformity. It was found that the accuracy and uniformity of the Deep-HUG are somewhat lower than those of the previous algorithm whereas the computation time is 190 times faster than that of the previous algorithm, demonstrating that Deep-HUG has potential as a useful technique to rapidly generate an ultrasound hologram for various applications.

• Management & Information Systems Review
• /
• v.34 no.5
• /
• pp.127-148
• /
• 2015

The results indicate that direction of online reviews have a significant effect on both information reliability and product attitude. In addition, consumers' shopping experience also shows a moderating effect between the direction of online reviews and the dependent variables. Furthermore, product type also shows a moderating effect on the information reliability, yet not on the product attitude. In clarify the relationship between the satisfaction and success of smart-learning smart learning and learner analyzes the main factors that affect the learning flow results, The smart learning variety of properties, personalization, complexity affects the learning flow variety, personalization, ubiquity affects the interaction, It was analyzed by a useful impact on the learner interactivity and immersive learning outcomes. This gives the implications of the smart learning attributes are important in order to maximize the learning experience for smart learning.