• 인터넷정보학회논문지
• /
• 제20권5호
• /
• pp.79-86
• /
• 2019

This paper is an overview of key elements of Korea National Open University's smart mobile learning system, and an attempt to evaluate its main services relative to the FRAME model and the Mobile Learning Development Model for distance learning in higher education. KNOU improved its system architecture to one based on xMOOC e-learning content delivery while also upgrading its PC-based online/mobile learning services to facilitate an easier and more convenient access to lectures and for better interactivity. From the users' viewpoint, the upgraded 'U-KNOU Campus' allows for a more integrated search capability coupled with better course recommendations and a customized notification service. Using the new system, the students can access not only the school- and peer-issued messages via online bulletin boards but also share information and pose questions to others including to the school faculty/officials and system administrators. Additionally, a new mobile payment method has been incorporated into the system so that the students can select and pay for additional courses from anywhere. In spite of these advances, the issue of device usability and content development remain; specifically U-KNOU Campus needs to improve its instructor-learner and learner-to-learner interactivity and mobile evaluation interface.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권3호
• /
• pp.792-812
• /
• 2022

Multi-agent systems often need to achieve the goal of learning more effectively for a task through coordination. Although the introduction of deep learning has addressed the state space problems, multi-agent learning remains infeasible because of the joint action spaces. Large-scale joint action spaces can be sparse according to implicit or explicit coordination structure, which can ensure reasonable coordination action through the coordination structure. In general, the multi-agent system is dynamic, which makes the relations among agents and the coordination structure are dynamic. Therefore, the explicit coordination structure can better represent the coordinative relationship among agents and achieve better coordination between agents. Inspired by the maximization of social group utility, we dynamically construct a factor graph as an explicit coordination structure to express the coordinative relationship according to the utility among agents and estimate the joint action values based on the local utility transfer among factor graphs. We present the application of such techniques in the scenario of multiple intelligent vehicle systems, where state space and action space are a problem and have too many interactions among agents. The results on the multiple intelligent vehicle systems demonstrate the efficiency and effectiveness of our proposed methods.

• 한국인터넷방송통신학회논문지
• /
• 제22권4호
• /
• pp.195-201
• /
• 2022

학습자 주도의 지속적 원격교육 환경을 위하여 학습자의 정확한 학습 패턴을 고려한 올바른 문제 추천 가이드에 대한 필요성이 증대하고 있다. 본 논문에서는 원격교육환경에서 수집되는 학습자의 문제패턴에 대하여 상황별 가중치를 부여하여 해당 데이터를 기반의 개별 학습자의 최적 문제추천 경로를 제시하는 방법으로 블록체인 기반 스마트 컨트랙트 기술을 연구하였다. 본 연구의 성능평가를 위하여 기존 유사 학습 환경과의 학습만족도 및 문제추천가이드의 유용성과 학습자 데이터 처리속도를 분석하였으며 본 연구를 통하여 15% 이상 학습 만족도 향상과 기존 학습 환경 대비 20% 이상의 학습데이터 처리속도향상을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.576-590
• /
• 2023

Machine learning is widely used in various academic fields, and recently it has been actively applied in the medical research. In the medical field, machine learning is used in a variety of ways, such as speeding up diagnosis, discovering new biomarkers, or discovering latent traits of a disease. In the respiratory field, a relative regional air volume change (RRAVC) map based on quantitative inspiratory and expiratory computed tomography (CT) imaging can be used as a useful functional imaging biomarker for characterizing regional ventilation. In this study, we seek to predict RRAVC using various regular machine learning models such as extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and multi-layer perceptron (MLP). We experimentally show that MLP performs best, followed by XGBoost. We also propose several relative coordinate systems to minimize intersubjective variability. We confirm a significant experimental performance improvement when we apply a subject's relative proportion coordinates over conventional absolute coordinates.

• 인터넷정보학회논문지
• /
• 제24권6호
• /
• pp.1-11
• /
• 2023

Federated learning (FL) is a ground breaking machine learning paradigm that allow smultiple participants to collaboratively train models in a cloud environment, all while maintaining the privacy of their raw data. This approach is in valuable in applications involving sensitive or geographically distributed data. However, one of the challenges in FL is dealing with heterogeneous and non-independent and identically distributed (non-IID) data across participants, which can result in suboptimal model performance compared to traditionalmachine learning methods. To tackle this, we introduce FedGCD, a novel FL algorithm that employs Graph Neural Network (GNN)-based community detection to enhance model convergence in federated settings. In our experiments, FedGCD consistently outperformed existing FL algorithms in various scenarios: for instance, in a non-IID environment, it achieved an accuracy of 0.9113, a precision of 0.8798,and an F1-Score of 0.8972. In a semi-IID setting, it demonstrated the highest accuracy at 0.9315 and an impressive F1-Score of 0.9312. We also introduce a new metric, nonIIDness, to quantitatively measure the degree of data heterogeneity. Our results indicate that FedGCD not only addresses the challenges of data heterogeneity and non-IIDness but also sets new benchmarks for FL algorithms. The community detection approach adopted in FedGCD has broader implications, suggesting that it could be adapted for other distributed machine learning scenarios, thereby improving model performance and convergence across a range of applications.

• 한국과학교육학회지
• /
• 제22권2호
• /
• pp.299-313
• /
• 2002

본 연구에서는 제7차 교육과정의 중등 과학 생물영역 심화학습을 위한 웹 기반 학습 프로그램을 개발하였으며, 중학교 3학년을 대상으로 적용한 결과를 분석하였다. 중학교 전학년 및 고등학교 1학년 생물영역 심화과정의 5개 주제를 선정하여 의문형으로 제시했으며, 각 주제별로 4개의 하위 학습단원 '활동'을 설정. 총 20개의 '활동'을 개발하였다. 먼저 2개의 하위활동은 기본 및 심화과정 학습내용을 설명하고, 3번째 하위활동은 가상실험을, 4번째 하위활동은 평가 및 정리 문제를 제시하는 방향에서 설계하였다. 이외에 풍부한 자료와 보충 설명을 위하여 용어 사전을 4개 하위활동에 삽입하였다. 각 활동은 하이퍼링트시켜 서로 상호 연결되도록 하였으며, 학습자가 직접실험을 설계 수행하고 결과를 확인할 수 있도록 가상실험을 설계하였다. 개발된 웹 기반 학습 프로그램의 효과를 분석하기 위하여, 중학교 3학년 247명의 학생들을 대상으로 프로그램을 적용하고 설문조사를 실시하였다. 그 결과 대부분의 학생들은 가정에서 인터넷을 사용할 수 있는 것으로 나타났으며, 과제학습을 수행하기보다는 e-mail이나 정보 검색을 목적으로 인터넷을 활용하는 것으로 조사되었다. 프로그램을 학습한 67명의 학생들은 프로그램을 학습하지 않은 학생들에 비해 '생식과 발생'단원의 학습성취도에서 유의미하게 높은 점수를 얻었다. 또한, 학생들은 웹 기반 학습 프로그램의 가상실험과 애니메이션 효과를 선호하였으며, 프로그램이 다른 웹 기반 프로그램에 비해 우수하다고 평가하였다. 반면, 웹 기반 학습 프로그램을 학습하지 않은 학생들은 다론 웹 기반학습 프로그램에 관심이 없으며, 과학에도 흥미가 없다고 응답하였다. 최근 학생들이 가정과 학교에서 인터넷을 활용할 수 있는 여건은 조성되었으나, 학생들의 흥미와 학습효과를 신장시킬 수 있는 웹 기반 프로그램의 개발 보급은 미비한 것으로 밝혀졌다. 결론적으로 가상실험, 애니메이션, 다양한 학습자료를 제공할 수 있는 인터넷의 환경을 효율적으로 활용하여, 학생들의 과학에 대한 흥미와 학업 성취도를 높이는 과학분야의 웹 기반 학습프로그램을 개발하는 일이 시급한 것으로 밝혀졌다.

• 정보교육학회논문지
• /
• 제3권2호
• /
• pp.113-119
• /
• 2000

I studied a distance education model for English learning on the Internet. Basic WWW files, that contain courseware, are constructed with HTML, and functions, which are required in learning, are implemented with Java. Students and educators can access the preferred unit composed of the appropriate text, voice and image data by using a WWW browser at any time. The education system supports the automatic generation facility of English problems to practice reading and writing by making good use of the courseware data or various English text resources located on the Internet. Our system has functions to manage and control the flow of distance learning and to offer interaction between students and the system in a distributed environment. Educators can manage students' learning and can immediately be aware of who is attending and who is quitting the lesson in virtual space. Also, students and educators in different places can communicate and discuss a topic through the server. I implemented these functions, which are required in a client/server environment of distance education, with the use of Java. The URL for this system is "http://park.taegu-e.ac.kr" in the name of GAIA.

• 한국초등과학교육학회지:초등과학교육
• /
• 제36권4호
• /
• pp.367-378
• /
• 2017

Because the lessons of 'our body' are based on indirect experiences and simple experiments, various methods are needed to improve the learning effect. In this study, seventeen AR contents were created to be used in five subjects in the 5th grade elementary school. The learning contents implementation were made using QCAR (QualComm's Augmented Reality) and Unity 3D (Unity 3D) program, which are augmented reality software development kits (SDKs). In order to find out the applicability, we applied the developed contents to one grade 5 classroom equipped with internet environment. Participants were asked about their perception of the program and interviewed. As a result, the developed AR learning contents appeared to be available. It was expected to help improve learning and was pointed out that improvement of internet condition and development, also, was needed expansion of various contents should be complemented.

• 한국인터넷방송통신학회논문지
• /
• 제13권2호
• /
• pp.255-260
• /
• 2013

요즈음, 지능형 교육 시스템은 자기 주도적 학습 기능을 이용한 연구가 진행되고 있다. 웹 기술 기반 온라인 가상대학에 접속하면, 온라인 강의를 언제 어디서나 공부할 수 있다. 지능형 학습 시스템을 구현하기 위해서는, 취약과목과 못하는 과목을 실시간으로 판단하는 기능이 필요하다. 이러한 문제를 해결하기 위해서, 수준별 학습 능력과 보안 알고리즘을 모의실험 하였다. 뿐만 아니라, 본 논문에서는 지능형 교육시스템을 구현하기위해서, QR 코드 및 지능형 교육 학습 시스템을 제안 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권9호
• /
• pp.2942-2960
• /
• 2022

The core of cognitive radio is the problem concerning intelligent decision-making for communication parameters, the objective of which is to find the most appropriate parameter configuration to optimize transmission performance. The current algorithms have the disadvantages of high dependence on prior knowledge, large amount of calculation, and high complexity. We propose a new decision-making model by making full use of the interactivity of reinforcement learning (RL) and applying the Q-learning algorithm. By simplifying the decision-making process, we avoid large-scale RL, reduce complexity and improve timeliness. The proposed model is able to find the optimal waveform parameter configuration for the communication system in complex channels without prior knowledge. Moreover, this model is more flexible than previous decision-making models. The simulation results demonstrate the effectiveness of our model. The model not only exhibits better decision-making performance in the AWGN channels than the traditional method, but also make reasonable decisions in the fading channels.