• The Magazine of the IEIE
• /
• v.17 no.3
• /
• pp.28-36
• /
• 1990

제6세대 컴퓨터로 불리는 신경컴퓨터는 학습과 병렬처리에 의해 인간의 지능을 모방한다. 따라서 지능과 빠른 계산을 요하는 여러 분야에 응용되고 있으며 실제 로봇의 제어나 sensor에 의거한 제어에 응용하여 좋은 결과를 내고 있다. 신경회로의 로봇나 공정제어(process control)응용은 학술적인 측면에서는 복잡한 비선형 시스템의 지능제어(intelligent control)연구이며 산업적 측면에서 보면 산업 자동화라는 막대한 시장을 뒤로 하고 있어 우리나라도 활발한 연구를 절실히 필요로 하고 있다. 본 해설에서는 신경회로를 간단히 소개한 후 로봇 제어 응용을 다루기로 한다. 신경회로의 응용분야중 보고된 결과가 비교적 적은 제어분야를 소개함으로써 독자들에게 연구 자료들을 제공하고 또한 흩어져 있는 신경회로의 제어응용 논문들을 분류 통일함으로써 이 분야를 조감할 수 있게 한다. 또한 로봇을 하나의 복잡하고 비선형적 plant로 보았을 때 로봇의 신경제어는 곧 산업공정의 신경제어에도 그대로 응용되리라 믿는다. 신경제어는 plant의 모델없이도 학습에 의하여 고속 정확한 제어가 가능하고 또 plant 특성변화에 잘 적응하며 병렬성으로 인하여 실시간 제어도 가능하다는 점에서 무한한 잠재력이 있으나 전세계적인 연구는 아직도 크게 미흡한 편이다. 더욱 많은 연구가 절실히 필요하다고 본다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.627-629
• /
• 2023

생체 신호를 분석하여 사용자의 건강과 정신 상태를 예측하고, 관련 질병에 관해 예방하는 연구가 늘어나고 있다. 생체 신호 중 심박은 사람의 육체, 정신적인 상태를 반영하는 대표적인 신호이지만 기존의 접촉 패드를 통한 ECG나 광학 센서를 통한 PPG로 심박을 예측할 때는 구속적인 환경이 필요하여 일상적인 상황 속에 적용하기 어려웠다. 이러한 단점을 해결하고자 본 논문은 UBFC-RPPG 데이터셋의 동영상 프레임을 RGB 채널마다 다른 가중치를 적용하는 전처리를 하여 학습 데이터의 크기를 줄이면서 정확도를 높이고, 3D-CNN을 활용한 딥러닝으로 순간적인 영상에서도 PPG 신호를 예측할 수 있도록 1초 전처리 영상을 학습한 후, 신호를 예측하는 것을 목표로 한다. 이렇게 비접촉식으로 취득된 신호는 더 다양한 환경에서의 감정분류, 우울증 진단, 질병 감지 등 다양한 분야에 활용될 수 있다.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.10
• /
• pp.155-164
• /
• 2011

As Information & Communication Technology is developed in fast speed, the educational field undertakes many changes in utilizing Information Technology(IT). As the smart phone's educational utilization brings many positive effects, so many people are interested in such educational application programs. The e-textbooks or learning contents based on the web have shown some limits in being utilized as main learning materials in school field. So this study identified such limits, and suggested a new direction for professional education by integrating mobile and QR code technologies with existing textbooks to realize a new book-type E-Textbook model. And this study purposed for students to participate in their classes more easily through making open-education environment for students studying specialized subjects and by applying new teaching-learning methods inducing more interest in them. Of course, this study's ultimate purpose is to raise students' learning ability about specialized subjects, and further, to improve their self-directed learning abilities with increased interests in classes. As the result operating this model, it was found that this model had enough learning effect.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.11
• /
• pp.3470-3478
• /
• 2000

The rapidly developing World Wide Web technology provides new opportunities for distance education over the internet. Several successful experiments about cyber educationor distance leanning have been reported. The Web when combined with other network tools can be used to create a virtual classroom to bring together a community of learners for interactive education. Requrements for standard tools for distance. Iearning, such as an electionic mail, a multiparheipant bcard newsgroup service and video conference tools have been investigated and implemented based on the object modeling technique useing java programming language. The object onented programming helps the developed codes maintain learning with allowed interactions either between instroctors and students or between students.

• 한국정보교육학회:학술대회논문집
• /
• 2008.01a
• /
• pp.206-210
• /
• 2008

오늘날 세계 시장 개방에 대비한 우리 전통 문화 기틀 마련을 위한 대책이 시급히 요구되고 있다. 이에 제도적인 대책뿐만 아니라 우리나라의 핵심 경쟁 요소인 최신 정보기술을 이용한 경쟁력 기반 확보가 절대적으로 필요한 상황이다. 본 논문에서는 다가오는 유비쿼터스 환경에서 전통문화 체험 학습자들이 학교 교과과정에서 배운 주제와 연관된 현장을 직접 방문하여 보고 듣고 체험할 수 있는 기회를 제공해 줌으로써 학교에서 배운 지식을 실제적 경험으로 승화시킬 수 있는 체험학습 교수 학습 모형을 개발하였다. 개발된 모형은 체험학습자의 수준별 학습 선호도에 따라 각기 다른 내용을 제공한다.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.3
• /
• pp.241-250
• /
• 2019

The study aims to investigate how international students with over the TOPIK level 3 recognize Korean proverbs. Among the 53 students, 45 students had the qualification of the TOPIK levels. Research results are as follows: 80.0 percentages of those students have studied Korean languages in the language institutes in Korea or their homelands. Only 57.8 percentages of them have learned Korean proverbs. Despite the high interest of foreign students on Korean proverbs, education on their expectations has not been achieved. And they had difficulty recognizing the circumstantial expression of the Korean proverb. Their degree of understanding of Korean proverbs is lower, compared to their TOPIK levels. The absence of systemic education on Korean proverbs makes international students difficult to understand the figurative expression of Korean proverbs. Since many international students want to become Korean language teachers after their studying, the education of proverbs needs to be conducted systematically rather than individually.

• The KIPS Transactions:PartA
• /
• v.10A no.5
• /
• pp.571-578
• /
• 2003

The appearnace of web technology has accelerated the development of the multimedia technology, the computer communication technology and the multimedia application contents. Researches on WBI(Web-based Instruction) system have combined the technology of the digital library and LOD,. REcently WBI(Web-based Instruction) model which is based on web has been proposed in the part of the new activity model of teaching-learning. As the demand of the customized coursewares from the lwarners is increased, the needs of the efficient and automated education agents in the web-based instruction are recognized. In this paper we propose a system monitors learner's behaviors constantly, evaluates them, and calculates his accomplishment. And the system offers suitable course to learner applying this accomplishment degree to agent's schedules. Therefore, the learner achieves an active and complete learning from the repeated and suitable course semantic-based retrieval.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.5
• /
• pp.83-87
• /
• 2011

Naive Bayesian learning has been widely used in machine learning. However, in traditional naive Bayesian learning, we make two assumptions: (1) each attribute is independent of each other (2) each attribute has same importance in terms of learning. However, in reality, not all attributes are the same with respect to their importance. In this paper, we propose a new paradigm of calculating the importance of attributes for naive Bayesian learning. The performance of the proposed methods has been compared with those of other methods including SBC and general naive Bayesian. The proposed method shows better performance in most cases.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.1
• /
• pp.20-27
• /
• 2007

In this paper, we presents virtual lecture contents to study educational robots assembling focused on the beginners with little or no background about electronics. Considering the target students, we developed 'virtual laboratory' using flash animation and the students can assemble the robots virtually with mouse and keyboard. Also, the contents includes lectures about some basic electronics theories. electronic devices, and the electronics tools for the beginners. With the features described above, this contents would be useful for the beginners and elementary school students who want to assembling their own robots.

• Journal of Broadcast Engineering
• /
• v.27 no.6
• /
• pp.897-905
• /
• 2022

Research for video key frame detection has been actively conducted in the fields of computer vision. Recently with the advances on deep learning techniques, performance of key frame detection has been improved, but the various type of video content and complicated background are still a problem for efficient learning. In this paper, we propose a novel method for key frame detection, witch utilizes contrastive learning and memory bank module. The proposed method trains the feature extracting network based on the difference between neighboring frames and frames from separate videos. Founded on the contrastive learning, the method saves and updates key frames in the memory bank, witch efficiently reduce redundancy from the video. Experimental results on video dataset show the effectiveness of the proposed method for key frame detection.