• 한국정보통신학회논문지
• /
• 제19권4호
• /
• pp.991-1000
• /
• 2015

본 논문은 스마트시대의 온라인 학습에 대한 논문으로, 새로운 모델을 제안하고 실증하는데 초점을 두었다. 온라인 학습 클래스 운영에 있어 각 학습 요인들을 통해서 최종 성취도를 예측하는 연구를 진행하였다. 이에 학습 운영 요인 7가지를 정하고 학습자들의 데이터를 수집한 후 의사결정나무방법을 통한 예측 모델을 완성한다. 모델을 통한 예측성을 확인한 후, 일반성 확보를 위해 다른 교과목에도 모델을 적용시켜 예측성을 확인하였다. 결과적으로 기존의 온라인 클래스의 정적인 학습 모델을 넘어 객관적인 지표를 이용한 학업성취도를 상시적으로 확인할 수 있게 하였다. 학습자와 교수자 모두가 학습 중 유용하게 활용할 수 있는 스마트시대 새로운 패러다임의 학습 모델을 제안한다.

• 한국HCI학회논문지
• /
• 제12권3호
• /
• pp.5-11
• /
• 2017

한국 전통춤은 인류의 문화적 자산으로 문화적 활용가치를 가지고 있지만 전수희망자의 부족과 대중적인 무관심으로 소멸의 위기에 처해 있다. 네트워크 기술과 영상매체 기술을 활용한 전통춤의 이러닝(E-Learning)은 위에서 제기한 문제점들을 해결하기 위한 방법이 될 수 있다. 이 연구는 전통춤 교육에 활용될 수 있는 이러닝 교육과정 및 실시간 이러닝 교육시스템들을 제안하였다. 시스템들은 일반인을 대상으로 HCI(Human Computer Interaction) 사용자 평가법에 따라 비교평가하고 피드백 및 교육경험 인터뷰를 실시하였다. 본 연구는 전통춤의 실시간 이러닝 교육시스템을 제안함으로써 공간적 제약을 극복하고 새로운 매체 경험을 통해 무형문화재로서 전통춤을 전승, 보급하는데 기여할 수 있다.

• 감성과학
• /
• 제14권2호
• /
• pp.197-206
• /
• 2011

본 논문에서는 신경망 SOM학습을 이용하여 피험자의 각성수준을 높은각성과 낮은각성으로 자동인식하는 것을 제안한다. 각성수준의 자동인식 단계는 세 단계로 구성된다 첫 번째는 ECG 측정 및 분석단계로 슈팅게임을 플레이하는 피험자를 ECG로 측정하고, SOM 학습을 하기 위해 특징을 추출한다. 두 번째는 SOM 학습 단계로 특징이 추출된 입력벡터들을 학습한다. 마지막으로 각성인식 단계는 SOM 학습이 완료된 후에 새로운 입력벡터가 들어왔을 때, 피험자의 각성수준을 인식한다. 실험결과는 각성수준의 SOM 학습결과와 새로운 입력벡터가 들어왔을 때 각성수준의 인식결과, 그리고 각성수준을 수치와 그래프로 보여준다. 마지막으로 SOM의 평가는 기존연구의 감성평가 결과와 SOM의 자동인식 결과를 순차적으로 비교하여 평균 86%로 분석되었다. 본 연구를 통해서 SOM을 이용하여 피험자마다 다른 각성수준을 자동인식 할 수 있었다.

• 스마트미디어저널
• /
• 제5권2호
• /
• pp.24-32
• /
• 2016

Recently, the development of electronic teaching materials and the demand of digital learners have led the needs on the education contents that replace learning from character information and the change of an information design method for this. Chinese character education in the traditional schooling mainly focuses on writing and memorization (semantic memory). This way that the stories do not exist has brought the learners' recognition that Chinese character is difficult to learn. Meanwhile, for a language study such as English, cross-media development between printed materials and audio-visual materials has been actively introduced. The method that extends episode memories along with memorization through a story is widely used. Therefore, this content suggests a prototype, which is broken away from an existing way of learning Chinese character that mainly focuses on writing, one sided instruction and information cramming. This makes learners learn through a story from printed materials and animation. Furthermore, it suggests a method that extends episode memories through Chinese education contents based on IoT explaining the principle of Chinese character by combining IT technology (information and communications, IoT) and education contents on block toys.

• 의학교육논단
• /
• 제19권3호
• /
• pp.158-168
• /
• 2017

There is a more urgent call for educational methods of machine learning in medical education, and therefore, new approaches of teaching and researching machine learning in medicine are needed. This paper presents a case using machine learning through text analysis. Topic modeling of news articles with the keyword 'asbestos' were examined. Two hypotheses were tested using this method, and the process of machine learning of texts is illustrated through this example. Using an automated text analysis method, all the news articles published from January 1, 1990 to November 15, 2016 in South Korea which included 'asbestos' in the title and the body were collected by web scraping. Differences in topics were analyzed by structured topic modelling (STM) and compared by press companies and periods. More articles were found in liberal media outlets. Differences were found in the number and types of topics in the articles according to the partisanship and period. STM showed that the conservative press views asbestos as a personal problem, while the progressive press views asbestos as a social problem. A divergence in the perspective for emphasizing the issues of asbestos between the conservative press and progressive press was also found. Social perspective influences the main topics of news stories. Thus, the patients' uneasiness and pain are not presented by both sources of media. In addition, topics differ between news media sources based on partisanship, and therefore cause divergence in readers' framing. The method of text analysis and its strengths and weaknesses are explained, and an application for the teaching and researching of machine learning in medical education using the methodology of text analysis is considered. An educational method of machine learning in medical education is urgent for future generations.

• Journal of information and communication convergence engineering
• /
• 제20권4호
• /
• pp.288-294
• /
• 2022

The media content market has been growing, as various types of content are being mass-produced owing to the recent proliferation of the Internet and digital media. In addition, platforms that provide personalized services for content consumption are emerging and competing with each other to recommend personalized content. Existing platforms use a method in which a user directly inputs video metadata. Consequently, significant amounts of time and cost are consumed in processing large amounts of data. In this study, keyframes and audio spectra based on the YCbCr color model of a movie trailer were extracted for the automatic generation of metadata. The extracted audio spectra and image keyframes were used as learning data for genre recognition in deep learning. Deep learning was implemented to determine genres among the video metadata, and suggestions for utilization were proposed. A system that can automatically generate metadata established through the results of this study will be helpful for studying recommendation systems for media super-personalization.

• 한국농촌건축학회논문집
• /
• 제13권2호
• /
• pp.47-54
• /
• 2011

According to the master plan of the Ministry of Education, Science and Technology, departmentalized class system will be extended to all general middle & high schools by 2014 with the exception only of those having less than 6 classes located in small cities in rural areas. Under departmentalized class system, according to class timetable, students need to move from classroom to another classroom and areas where homebases, lounges, media spaces, rest places, and etc. This study has been undertaken to provide architectural data required in planning for student & learning support space for schools operating departmentalized class system, by investigating and analyzing cases in use at schools operating the system in Chungbuk area. As departmentalized class system is increasingly introduced, student & learning support space should be understood newly as spaces indispensable for students.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 춘계학술발표대회
• /
• pp.783-786
• /
• 2016

E-learning is a new teaching model nowadays, and Virtual Reality (VR) technology is reported that the use of virtual reality as an education tool can increase student interests, understanding, and creative learning because of encouraging students to learn by exploring and interacting with the information on the virtual environment. Besides that, LEGOs have long been the favorite of many children. LEGOs provide a mechanism to understand and do for many concepts from spatial relationships to robotics platforms. In this paper, we present a virtual reality application based on the assembly of LEGO-Like bricks to increase math and science learning by improving spatial thinking. It not only encourages students to pursue careers in science, technology, engineering, or mathematics but also enhances learner's ability to analyze and solve problems. The application is built by Processing 2.0 as the easier programming language which is a top-down approach to build the 3D interactive program.

• 스마트미디어저널
• /
• 제10권2호
• /
• pp.48-54
• /
• 2021

Sepsis is one of the leading causes of mortality globally, and it costs billions of dollars annually. However, treating septic patients is currently highly challenging, and more research is needed into a general treatment method for sepsis. Therefore, in this work, we propose a reinforcement learning method for learning the optimal treatment strategies for septic patients. We model the patient physiological time series data as the input for a deep recurrent Q-network that learns reliable treatment policies. We evaluate our model using an off-policy evaluation method, and the experimental results indicate that it outperforms the physicians' policy, reducing patient mortality up to 3.04%. Thus, our model can be used as a tool to reduce patient mortality by supporting clinicians in making dynamic decisions.

• 한국컴퓨터정보학회논문지
• /
• 제18권9호
• /
• pp.91-99
• /
• 2013

스마트 디바이스의 개발과 발달, 그리고 스마트 디바이스의 보편화에 따라 사용자들은 한 개 이상의 스마트 디바이스를 소지하게 되었다. 기존의 온라인 학습 서비스는 하나의 스크린을 분할시켜 다양한 정보를 제공해 왔다. 그러나 기존의 PC환경과 다르게 스마트 디바이스가 발달되고 보편화됨에 따라, 사용자의 학습공간은 하나의 스크린 환경에서 다중스크린 환경으로 변화할 것이다. 본 논문에서는 다중스크린을 기반으로 한 스마트 학습공간을 구성하고, 스마트 학습공간에서 미디어 콘텐츠를 융합하여 서비스하는 시스템을 제고하고자 한다. 이에 다중스크린 관련연구 분야와 다중스크린 환경에 합당한 온라인 학습 서비스를 분석 설계하여 Timed Button이라는 스마트 디바이스 간의 동기화 기법을 제시한다.