• Proceedings of The KACE
• /
• 2017.08a
• /
• pp.125-127
• /
• 2017

학습이 진행될 때 주어지는 학습자 맞춤형 피드백은 학습자의 성취도를 높이는 부분에서 중요한 요소 중 하나이다. 많은 연구가 맞춤형 피드백에 관련되어 진행되었지만, 각 연구 결과는 특정 도메인과 시스템에만 적합하도록 연구되었다. 따라서, 본 논문에서는 프로그래밍 교육을 위한 데이터 기반의 학습자 맞춤형 문제 제공 및 피드백 방법을 연구하고 지능형 코딩 학습 시스템 Everycoding에 적용하였다.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.51-57
• /
• 2021

Quite a few elementary school teachers began to utilize AI technology in order to provide students with customized, intelligent information services in recent years. However, learning principles of AI may be as important as utilizing AI in everyday life because understanding principles of AI can empower them to buildup adaptability to changes in highly technological world. In the paper, 'Linear Regression Algorithm' is selected for teaching AI-based prediction system to solve real world problems suitable for elementary students. A simulation program written in Scratch was developed so that students can find a solution of linear regression model using the program. The paper shows that students have learned analyzing data as well as comparing the accuracy of the prediction model. Also, they have shown the ability to solve real world problems by finding suitable prediction models.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.8
• /
• pp.191-200
• /
• 2024

The rapid advancement of computer technology and artificial intelligence has significantly impacted software education in Korea. Consequently, the 2022 revised curriculum demands personalized education. However, implementing personalized education in schools is challenging. This study aims to facilitate personalized education by utilizing incorrect codes and error information submitted by beginners to construct prompts. And the difference in the frequency of correct feedback generated by the generative AI model and the prompts was examined. The results indicated that providing appropriate error information in the prompts yields better performance than relying solely on the excellence of the generative AI model itself. Through this research, we hope to establish a foundation for the realization of personalized education in programming education in Korea.

• 대한공업교육학회지
• /
• v.33 no.1
• /
• pp.265-281
• /
• 2008

The objective of this study is to show practice example let student experience about concurrent servers based multi-processes and multi-thread among the principles of data communication in ICT(information and communications technology). For this, we first implement multi-process server(fork server) and multi-thread server(thread server), and multi-thread client(thread client), Secondly, for experimental environment, we developed small ethernet networks and measure data transfer time with relation to the number of users. Experimental results show that mean transfer time of thread server is less than that of fork server by 20~61 % on average. Furthermore, it is found that the difference of data transfer time between fork server and thread server is proportional to that of the number of users. Main reason of performance difference dues to the difference between process forking time and thread creation time. We can also find that context switching for process and thread affects the load of web server. Our presentation and experimental results can be applied to used as the educational practice materials with which student can experience data communication principles.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.455-460
• /
• 2023

Text augmentation is a methodology that creates new augmented texts by transforming or generating original texts for the purpose of improving the performance of NLP models. However existing text augmentation techniques have limitations such as lack of expressive diversity semantic distortion and limited number of augmented texts. Recently text augmentation using large language models and few-shot learning can overcome these limitations but there is also a risk of noise generation due to incorrect generation. In this paper, we propose a text augmentation method called TAGS that generates multiple candidate texts and selects the appropriate text as the augmented text. TAGS generates various expressions using few-shot learning while effectively selecting suitable data even with a small amount of original text by using contrastive learning and similarity comparison. We applied this method to task-oriented chatbot data and achieved more than sixty times quantitative improvement. We also analyzed the generated texts to confirm that they produced semantically and expressively diverse texts compared to the original texts. Moreover, we trained and evaluated a classification model using the augmented texts and showed that it improved the performance by more than 0.1915, confirming that it helps to improve the actual model performance.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.12
• /
• pp.115-125
• /
• 2018

The one of goals of the 2015 revised national curriculum is the successful application of achievement standards-based assessment, which assesses both the results and process of learning, ensuring that all students have achieved the educational objectives, to schools. Therefore, an achievement standards and evaluation support system is required to manage a whole process of teaching and learning based on achievement standards and provide the personalized assessment feedback to students to improve their achievement levels. In this paper, we perform a design of integrated data model and system of teaching plan, subject content, assessment plan, assessment result, and feedback data is required based on an achievement standards repository. In addition, we create a student's dashboard webpage, which representing different types of achievement of the student, and perform the comparative analysis of data models to evaluate the quality of the proposed model.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.633-634
• /
• 2020

본 논문에서는 소외계층 초등정보영재를 위한 온라인 머신러닝 교육 프로그램을 개발하였다. 교육 프로그램은 초등정보영재 전문가가 개발하였으며, 인공지능 교육 전문가가 검증하였다. 교육 프로그램은 15차시로 구성하였으며, 인공지능에 대한 이해, 데이터 수집 및 표현, 모델 선택, 훈련, 평가, 실생활 사례 제작, 예측으로 내용을 구성하였다. 교육 프로그램에서 학습 모형은 이재호와 홍창의(2009)의 문제 중심형 e-PBL 학습 모형을 본 연구에 맞게 수정하여 활용하였다. 향후 연구에서는 개발한 교육 프로그램을 소외계층 초등 정보영재에 적용하고, 교육 프로그램을 통한 소외계층 초등정보 영재의 변화를 분석하고자 한다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.147-149
• /
• 2021

Recently, the rapid growth of the media market and the expectations of users have been increasing. In this research, tags are extracted through media-derived audio and classified into specific categories using artificial intelligence. This category is a type of emotion including joy, anger, sadness, love, hatred, desire, etc. We use JupyterNotebook to conduct the corresponding study, analyze voice data using the LiBROSA library within JupyterNotebook, and use Neural Network using keras and layer models.

• Archives of design research
• /
• v.17 no.3
• /
• pp.101-110
• /
• 2004

The purpose of this study is to draw a distinction between general computer graphics courses and game development ones and to find out making various improvements in game graphics courses. In addition to general hand-drawing skills and computer graphics technology which are essential for the students who major in game graphics; however, the special classes should be required for them to comprehend the work process of game development and to produce the game graphics data. This necessity of the discriminative education is going to be an identification of game development department. Although loading game data onto a game engine and finding out the solution to problems of data is one of the excellent settlement for educating game graphics students, it is not possible to purchase the commercial game engine such as Quake or Lithtech and to analyze the commercial program libraries. For this reason, this research presents the replacement of commercial game engine with VRML97 for the academic purpose and shows what effect upon education will be. It is expected that the VRML97 can be a substitute of the game engine for the effectiveness of game graphics education with more active study and verification of game fields.

• 한국정보교육학회:학술대회논문집
• /
• 2004.01a
• /
• pp.413-421
• /
• 2004

지식 정보화 시대의 새로운 교육 패러다임의 변화에 따라 웹을 통하여 정보와 아이디어를 서로 공유할 수 있는 사회적 상호작용이 요구되고 있다. 이러한 사회적 상호작용을 증진시키기 위해서는 다양한 사회적 상호작용 도구를 제공할 수 있는 웹 기반협동학습 시스템이 필요하다. 따라서 이 논문에서는 사회적 상호작용을 증진시키기 위해서 웹 기반 협동학습 환경을 쉽게 구성할 수 있도록 재사용 가능한 협동학습객체 모형을 SCORM을 기반으로 설계하였다. 협동학습객체 모형을 필드와 메소드, 속성으로 구성하였다. 필드는 상호작용을 통해 발생된 상호작용 결과를 저장하기 위해 데이터 모델로 구현하였으며, 메소드는 상호작용 결과를 LMS에 전달하는 방법을 제공하기 위해 API 함수로 구현하였다. 또한 협동학습객체의 속성은 접근성, 다형성, 포장성, 제어성으로 구분하여 각각 베타데이터, 계열화, 패키지, 런치를 통해 구현하였다. 이러한 협동학습객체는 학습 내용과 결합하여 하나의 협동학습 활동을 구성하게 되고, 이렇게 구성된 협동학습 활동을 계열화함으로써 교수 학습 설계가 이루어진다.