• 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.

• Journal of Fashion Business
• /
• v.16 no.2
• /
• pp.1-11
• /
• 2012

The purpose of this study was to examine the effects of UBL (Ubiquitous basedlearning) on fashion and consumer behavior course. Thirty-one undergraduate university students completed a 15-week capstone course in a clothing and textiles department. About sixteen percent students were majoring in liberal arts and sixty-three percent of the participants were majoring in the clothing and textiles. Mainly, the participants were junior and senior undergraduate students. The participants demonstrated positive attitude toward the UBL (Ubiquitous based-learning) on fashion and consumer behavior course. The results showed that seventy-seven percent of the participants have more opportunities to handle multi-media resources using social network and social media. Eighty percent of the participants have been developed of communication skills. Seventy-one percent of the participants were helped to learn foreign language skills. Overall, most of the participants were satisfied that their presentation skill was improved in class and they had willing to recommend the class to other students for the future.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1358-1361
• /
• 1993

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.788-791
• /
• 2009

유비쿼터스 환경에서 러닝 서비스는 언제, 어디서, 어떠한 물리적 장치에 구애받지 않고 사용자에게 적절한 서비스를 제공할 수 있어야 한다. 그러한 u-러닝 서비스를 제공하기 위해서는 학습자 수준을 정확히 판단할 수 있는 진단 기법이 필요하다. 또한 u-러닝 서비스에서 학습자의 학습 환경을 정확히 파악하여 이에 적절한 형태의 학습 컨텐츠를 제공하는 학습 컨텐츠 적응화 기술도 요구된다. 따라서 본 논문에서는 온톨로지 모델링을 이용하여 학습자의 프로파일과 학습 컨텐츠를 모델링하고, 모델링된 프로파일 정보와 컨텐츠 정보를 온톨로지 추론 규칙을 정의함으로서 학습자의 학습 정보를 정확히 파악하고 학습자에게 적절한 학습 컨텐츠를 제공할 수 있는 온톨로지 모델링과 추론을 기반으로 유비쿼터스 환경에서 학습자의 정보와 각 이종 디바이스에 대해 적합한 학습 컨텐츠를 제공할 수 있는 u-러닝 시스템을 제안한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.719-720
• /
• 2015

This paper propose the method of U-learning system which is the $21^{th}$ core IT fields of the knowledge based information-oriented society, which is digital convergenced ubiquitous with e-learning. Specially, for the future it will be expected and prospected new media core in digital life age using DMB smart phone.

• 한국IT서비스학회:학술대회논문집
• /
• 2007.05a
• /
• pp.391-395
• /
• 2007

다가오는 유비쿼터스시대를 맞이하여 IT가 급속히 확산되고 있다. 그중에서도 컴퓨터환경은 계속발전되어 초등학생의 93.3%, 중, 고등, 대학생의 97.3%가 컴퓨터를 사용하고 있다. 이 논문은 5년동안 산학연구프로젝트로 진행된 u-learning 시스템 개발을 토대로 일부적용한 결과를 기술하였다. 일부 보완점이 필요하지만 긍정적인 결과가 나왔다. 그러나 컴퓨터의 보급이나 인터넷 및 IT 같은 정보기술이 곧 u-learning 교육발전과 직결되지는 않는다. 교육정보화는 전통적인 시각을 뛰어넘어 유비쿼터스시대의 새로운 단계로 발전해야만 한다. 이런 가운데 유비쿼터스 컴퓨팅과 네트워크 패러다임은 미래교육 시스템이 나아가야 할 새로운 방향을 제시한다.

• Proceedings of the KIEE Conference
• /
• 1998.11b
• /
• pp.407-409
• /
• 1998

This paper deals with temporal-difference learning that is a method for approximating long-term future cost as a function of current state in knowlege-poor environment, a function approximator is used to approximate the mapping from state to future cost, a linear function approximator is limited because mapping from state to future cost has a nonlinear characteristic, so a nonlinear function approximator is used to approximate the mapping from state to future cost in this paper, and that TD learning using a nonlinear function approximator is stable is proved.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.12 no.12
• /
• pp.5564-5569
• /
• 2011

In this paper we introduced Augmented Reality (AR) on Android platform for ubiquitous learning (u-learning). Android is breaking new ground for mobile computing and open technologies. Android is versatile as it is not limited only to mobile phones, but it can be installed on various devices. Android gives developers the opportunity to leverage their development skills, while also building an exciting and active community. Augmented Reality (AR) is going to be the future of most apps; all it takes is a decent processor, a camera, a compass and a GPS, all of which are becoming increasingly common on smart phones. Through AR we can have educational tools that provide individuals with total flexibility to receive, send, and review training and detailed product information through an increasingly ubiquitous web-enabled communication device. In this paper, we proposed Augmented Reality for Species Identification using Android Smartphone with augmented reality in species determination. This study is appropriate in the field of Biology. This is useful in outdoor experimental activities of the students. Like for example while they are visiting the zoo, botanical garden and etc.

• 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 Biomedical Engineering Research
• /
• v.42 no.3
• /
• pp.100-106
• /
• 2021

Measuring Intima-media thickness (IMT) with ultrasound images can help early detection of coronary artery disease. As a result, numerous machine learning studies have been conducted to measure IMT. However, most of these studies require several steps of pre-treatment to extract the boundary, and some require manual intervention, so they are not suitable for on-site treatment in urgent situations. in this paper, we propose to use deep learning networks U-Net, Attention U-Net, and Pretrained U-Net to automatically segment the intima-media complex. This study also applied the HE, HS, and CLAHE preprocessing technique to wireless portable ultrasound diagnostic device images. As a result, The average dice coefficient of HE applied Models is 71% and CLAHE applied Models is 70%, while the HS applied Models have improved as 72% dice coefficient. Among them, Pretrained U-Net showed the highest performance with an average of 74%. When comparing this with the mean value of IMT measured by Conventional wired ultrasound equipment, the highest correlation coefficient value was shown in the HS applied pretrained U-Net.