• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.251-258
• /
• 2021

In this paper, we proposed an encoder-decoder model utilizing residual learning to improve the accuracy of the U-Net-based semantic segmentation method. U-Net is a deep learning-based semantic segmentation method and is mainly used in applications such as autonomous vehicles and medical image analysis. The conventional U-Net occurs loss in feature compression process due to the shallow structure of the encoder. The loss of features causes a lack of context information necessary for classifying objects and has a problem of reducing segmentation accuracy. To improve this, The proposed method efficiently extracted context information through an encoder using residual learning, which is effective in preventing feature loss and gradient vanishing problems in the conventional U-Net. Furthermore, we reduced down-sampling operations in the encoder to reduce the loss of spatial information included in the feature maps. The proposed method showed an improved segmentation result of about 12% compared to the conventional U-Net in the Cityscapes dataset experiment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.1539-1542
• /
• 2012

고정된 컴퓨터에서 학습하는 e-learning에서 탈피하여 이동 중에도 학습이 가능한 u-learning이 필요하여 u-learning의 한부분인 스마트러닝은 급변하는 정보화시대의 교육경향이 매우 빠르게 변화하고 있는 상황을 그대로 반영해주는 결과물이라고 할 수 있다. 스마트 러닝이 학습향상에 얼마나 영향을 미치는가를 분석하고 스마트 러닝 기능을 최대한 활용하여 최대의 학습 효과를 얻을 수 있는 방법을 제시하며 스마트기기를 이용해 실제 학습하는 사례를 적용한 동영상 강의 애플리케이션의 효율적인 관리 시스템을 분석 설계한다. 각종 콘텐츠를 비롯하여 동영상강의 어플리케이션을 통한 여러 학습수단을 배경으로 전체적인 면에서 학습 환경을 살펴봄으로써 학습효과에 보다 나은 방안을 제시하고자 한다.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_3
• /
• pp.1095-1107
• /
• 2020

Flood monitoring using satellite data has been constrained by obtaining satellite images for flood peak and accurately extracting flooded areas from satellite data. Deep learning is a promising method for satellite image classification, yet the potential of deep learning-based flooded area extraction using SAR data remained uncertain, which has advantages in obtaining data, comparing to optical satellite data. This research explores the performance of SegNet and U-Net on image segmentation by extracting flooded areas in the Khorat basin, Mekong river basin, and Cagayan river basin in Thailand, Laos, and the Philippines from Sentinel-1 A/B satellite data. Results show that Global Accuracy, Mean IoU, and Mean BF Score of SegNet are 0.9847, 0.6016, and 0.6467 respectively, whereas those of U-Net are 0.9937, 0.7022, 0.7125. Visual interpretation shows that the classification accuracy of U-Net is higher than SegNet, but overall processing time of SegNet is around three times faster than that of U-Net. It is anticipated that the results of this research could be used when developing deep learning-based flood monitoring models and presenting fully automated flooded area extraction models.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.37-47
• /
• 2021

In this paper, we propose a new deep learning model for tongue segmentation with improved accuracy compared to the existing model by diversifying the receptive field in the U-net. Methods such as parallel convolution, dilated convolution, and constant channel increase were used to diversify the receptive field. For the proposed deep learning model, a tongue region segmentation experiment was performed on two test datasets. The training image and the test image are similar in TestSet1 and they are not in TestSet2. Experimental results show that segmentation performance improved as the receptive field was diversified. The mIoU value of the proposed method was 98.14% for TestSet1 and 91.90% for TestSet2 which was higher than the result of existing models such as U-net, DeepTongue, and TongueNet.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.686-688
• /
• 2020

본 논문에서는 U-Net 모델을 이용하여 정교하고 반복되는 패턴을 가진 인쇄물에 대한 비지도 학습을 통한 딥러닝 기반 이상치탐지(Anomaly Detection) 방법을 제안하였다. 인쇄물(카드)의 비정상 패턴 검출을 위하여 촬영한 영상으로부터 카드 영역을 분리한 이미지로 구성된 Dataset을 구축하였고 정상 이미지와 동일한 이미지를 출력하기 위해, 정상 이미지와 마스크 이미지 쌍의 Training dataset을 U-Net으로 학습하였다. Test dataset의 이미지를 입력으로 넣어 생성된 마스크 결과를 원본 마스크 이미지와 비교하여 이상 여부를 판단하는 본 논문의 방법이 정상, 비정상 인쇄물을 잘 구분하는 것을 확인하였다. 또한 정상과 비정상 이미지 각각을 학습한 지도학습 기반 CNN 분류 방법을 입력 영상과 복원 영상 간의 복원 오차를 비교하여 객체의 이상 여부를 판별하는 본 논문의 방법과 비교 평가하였다. 본 논문을 통해 U-Net을 사용하여 별도로 데이터에 대한 label 취득 없이 이상치를 검출할 수 있음을 확인할 수 있었다.

• Korean Journal of Comparative Education
• /
• v.18 no.4
• /
• pp.141-162
• /
• 2008

Many e-learning programs in Korea use lecture as a main instructional method. A meta-analysis study reports that e-learning programs using lectures were the most ineffective. In addition, many researchers in the field of distance education contend that the active participation of learners is the key to the success of e-learning. These imply why we can easily find many people who don't have good impression about e-learning. The quality of e-learning depends on the application of appropriate pedagogy. This study aims to present the implications for the improvement of e-learning programs in the Republic of Korea by analyzing the psychological characteristics reflected on the e-learning programs in the U. S. that have been improved through design research for a long time. The result shows that the e-learning programs in the U. S. have five major psychological aspects, i.e., reflective thinking, collaborative interaction, knowledge construction, situated action, and utilizing multiple representations. Consequently, this study suggests that e-learning programs in the Republic of Korea need to reflect learning principles such as learning by doing, situated learning, collaborative learning, learning with multiple representations in order to improve the quality.

• Journal of the Korea Computer Industry Society
• /
• v.6 no.5
• /
• pp.749-756
• /
• 2005

In the near future, we can access the information whenever we want, wherever we use because almost devices in ubiquitous environment are connected by either wired or wirelss networks. Especially, u-Learning which emphasizes on pedagogical property is enable to improve learning abilities. As researches of the previous u-Learning, there have been learning by mobile devices such as PDAs as well as the smart classroom which makes the remote students participate in the existing class. However, these researches have not satisfied pedagogical, cooperative and ubiquitous properties yet. Thus we suggest the framework for both local and mobile classroom, which can make the properties easy to satisfy.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.3 no.1
• /
• pp.69-75
• /
• 2011

This paper presents a model of e-learning based on ubiquitous computing configuration. First of all, we survey the advanced e-learning systems for foreign and domestic universities. Next we propose the optimal e-learning model based on ubiquitous computing configuration. The proposed e-learning model as following. we propose the e-learning system's hardware and software configurations, that are server and networking systems. Also, we construct the proposed e-learning systems's services. There are attendance and absence service, class management service, common knowledge service, score processing service, facilities management service, personal management service, personal authorization issue management service, campus guide service, lecture-hall management service. Then we propose the laboratory equipment management service, experimental materials management service etc. The proposed model of e-learning based on ubiquitous computing configuration will be able to contribute to the next generation university educational paradigm.

• The Journal of the Korea Contents Association
• /
• v.7 no.12
• /
• pp.283-291
• /
• 2007

In the age of ubiquitous computing, computer systems will be seamlessly integrated into our everyday life, providing services and information to us in an anywhere, anytime fashion. This ubiquitous computing can be used for developing a ubiquitous learning (U-learning). In this paper, we present a framework for U-school in which ubiquitous computing technologies are applied to advance the existing ERSS (Korea's Educational Resources Sharing System). Our framework applies mobile, sensor, and context-aware technologies to the existing ERSS. This framework presents a user-centric learning environment, using user-centric scenario. The U-school with context-aware services therefore can lead to the just-in-time learning or learner-led learning based on dynamic contexts acquired from learners, teachers and computing entities.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06d
• /
• pp.35-37
• /
• 2012

원격교육과 e-러닝의 차세대 형태로 모바일 교육에 대한 관심이 급증하고 있다. 이러한 모바일 교육은 스마트폰을 중심으로 전개되고 있으며 사이버 대학교뿐만 아니라 일반 오프라인 대학에서도 적극적인 움직임을 보이고 있다. 본 논문에서는 u-캠퍼스 환경기반에서의 모바일 교육 서비스 시스템을 설계하였다. 모바일 교육 서비스 시스템은 u-캠퍼스 환경기반에서 교육 수요자들인 학생들에게 시공간의 제약 및 디바이스에 제약이 없는 학습 환경 시스템을 제공하고 모바일 캠퍼스 플랫폼 기반의 m-러닝 시스템을 설계한 것이다.