• The Journal of the Convergence on Culture Technology
• /
• v.7 no.2
• /
• pp.437-442
• /
• 2021

In this study, a recommendation algorithm was implemented by learning a deep learning-based classification model for consumer data. For this purpose, a meaningful result is presented as a result of learning using ResNet50, which is commonly used in classification tasks by converting user data into images.

• Electronics and Telecommunications Trends
• /
• v.29 no.1
• /
• pp.41-49
• /
• 2014

최근 산업 전반에 걸쳐 가상세계와 현실세계, 방송과 통신, IT 기술과 전통산업 등 다양한 분야에서 융합연구가 진행되고 있다. 그리고 교육분야에서는 주입식 교육을 탈피하는 창의력 중심으로의 교육 패러다임의 변화를 고려하고, 교육격차 해소와 교육복지 실현을 위한 새로운 교육서비스 제공이 요구되고 있으며, 결과적으로 자기주도형 미래 인재를 육성하기 위한 고품질의 인터랙티브 교육콘텐츠 기술이 시급히 요구되고 있는 실정이다. 이에 따라 최근에는 ICT(Information & Communication Technology) 기술을 교육과 융합하여 학습자에게 실재감과 몰입감을 제공하고 학습자의 체험 기반 학습을 지향하는 이러닝 콘텐츠 기술이 개발되고 있다. 본고에서는 증강현실 기반 실감형 학습기술, 가상현실 기반 체험형 학습기술, 인터랙티브 e-book 기술 관련 신기술 개발동향에 대해 살펴보고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.383-386
• /
• 2018

Interesting and focused learners are attracting more and more interesting and efficient learning methods. Research on game-based learning that converges information and communication technology in accordance with this trend is being attempted. I want to take advantage of the characteristics of the game that enhance the concentration. However, if you play a game, you may get less exercise. Therefore, in this paper, we have designed and implemented a system that improves fitness and improves the performance by using Dance Dance Revolution (DDR) to fuse games and sports.

• Convergence Security Journal
• /
• v.18 no.3
• /
• pp.3-9
• /
• 2018

The Deep Deterministic Policy Gradient (DDPG) algorithm is an algorithm that learns by using artificial neural network s and reinforcement learning. Among the studies related to reinforcement learning, which has been recently studied, the D DPG algorithm has an advantage of preventing the cases where the wrong actions are accumulated and affecting the learn ing because it is learned by the off-policy. In this study, we experimented to control the bicycle autonomously by applyin g the DDPG algorithm. Simulation was carried out by setting various environments and it was shown that the method us ed in the experiment works stably on the simulation.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.303-308
• /
• 2007

최근에 제안된 감독 지식을 융합하는 강화 학습 기법인 potential-based RL 기법의 효용성은 이론적 최적 정책으로의 수렴성 보장으로 증명되었고, policy-reuse RL 기법의 우수성은 감독지식을 융합하지 않는 기존의 강화학습과 실험적인 비교를 통하여 증명되었지만, policy-reuse RL 기법을 potential-based RL 기법과 비교한 연구는 아직까지 제시된 바가 없었다. 본 논문에서는 potential-based RL 기법과 policy-reuse RL 기법의 실험적인 성능 비교를 통하여 기법이 policy-reuse RL 기법이 policy-reuse RL 기법에 비하여 더 빠르게 수렴한다는 것을 보이며, 또한 policy-reuse RL 기법의 성능은 재사용하는 정책의 optimality에 영향을 받는다는 것을 보인다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.205-206
• /
• 2019

본 논문에서는 오토마타를 활용한 창의 융합 교육으로 학생들에게 기술과 공학 그리고 예술의 융합적 상상력을 불어넣을 수 있는 교육과정을 제안하고 이를 통해 인지능력과 감정조절, 그리고 공감 능력을 향상시키는 것을 가능하게 하는 사회정서학습인 SEL(Social and Emotional Learning)을 수행할 수 있도록 한다. 제안하는 프로그램을 통해 학생들의 감성을 자극하고 새로운 생각을 유도함으로써 올바른 인성을 가질 수 있도록 한다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.66-71
• /
• 2023

ChatGPT가 등장한 이후 다양한 거대 언어 모델(Large Language Model, LLM)이 등장하였고, 이러한 LLM을 목적에 맞게 파인튜닝하여 사용할 수 있게 되었다. 하지만 LLM을 새로 학습하는 것은 물론이고, 단순 튜닝만 하더라도 일반인은 시도하기 어려울 정도의 많은 컴퓨팅 자원이 필요하다. 본 연구에서는 공개된 LLM을 별도의 학습 없이 사용하여 zero-shot 프롬프팅으로 이진 분류 태스크에 대한 성능을 확인하고자 했다. 학습이나 추가적인 튜닝 없이도 기존 선학습 언어 모델들에 준하는 이진 분류 성능을 확인할 수 있었고, 성능이 좋은 LLM의 경우 분류 실패율이 낮고 일관적인 성능을 보여 상당히 높은 활용성을 확인하였다.

• Journal of the Korea Convergence Society
• /
• v.10 no.2
• /
• pp.35-40
• /
• 2019

The purpose of this study was to investigate the effects of learners' academic achievement and learner interaction through project - based learning. In the case of interaction, we focused on the field of learning, that is, the learner's communication style in various technical environments. The subjects of this study were 80 learners who took a 3-hour elective English language learning course at a university in Korea. This study is to investigate the effect of learner interaction through KakaoTalk and LMS (Learning Management System). As a result of the study, it was found that there was a significant difference between learner interaction by project - based learning and communication type and kakao talk utilization group and LMS (Learning Management System) group. 1) The results of the kakao talk utilization group were significant in both the learner interaction and the learner's academic achievement according to the project - based learning and communication type. For current digital native learners, Kakao Talk is the result of the fact that it is the optimal environment for problem solving, communication, and uploading and sharing of educational activities.

• Education of Primary School Mathematics
• /
• v.20 no.3
• /
• pp.225-235
• /
• 2017

The study in this paper considers how elementary school students' interest in mathematics and STEAM literacy could be promoted by conjoining the learning of mathematics with the learning of drone topics. Survey instrument was developed to measure student attitudes toward mathematics and science subjects and to evaluate student beliefs on learning mathematics embedded in science topics. Data were collected from elementary school students by administering pre- and post-tests: students were intervened with examples of math problems embedded in certain science contexts. The findings indicate that elementary school students' experience of solving mathematics problems embedded in science contexts positively affects the promotion of their attitudes toward, beliefs on science subjects and science and engineering career path selection. We hope that the mathematics program using the drone will be used in the classroom for STEAM.

• Journal of the Korea Convergence Society
• /
• v.8 no.11
• /
• pp.1-6
• /
• 2017

This paper focuses on the development of a system that improves the convenience of foreign language learning and enhaces the learning ability of the target language through the use of IT devices. In addition to the basic grammar, the importance of pronunciation and intonation have somewhat crucial effect in everyday communication. Pronunciation and intonation of English are different according to the basic characteristics of a native language and these differences often cause problems in communication. The proposed system distinguishes acceptability in English communication process and requests the correction in realtime. The proposed system minimizes system intervention by collecting various voice signals of foreign language learners and setting that can be considered as acceptable threshold points. As a result, the learner can increase the learning efficiency with minimal interruption of the utterance caused by unnecessary system intervention.