• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.207-208
• /
• 2018

본 논문에서는 기계학습의 하나인 Learning Vector Quantization 알고리즘을 이용하여 컨트롤러 순서를 정하는 모델을 제안하였다. 제안한 모델은 모든 컨트롤러 정보를 수집하여 Learning Vector Quantization의 LVQ1와 LVQ2 기법을 이용하여 컨트롤러의 순서를 정한다. 이를 통해, 효율적인 컨트롤러 동기화가 이뤄질 것으로 기대된다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.709-711
• /
• 2002

웹 기반의 교육의 활성화로 이를 학습에 응용하기 위한 노력으로 GVA(Global Virtual Academy) 등과 같은 학습 보조 도구가 많이 발표하고 있는 설정이다. 대부분의 학습 보조 도구들은 각각의 특성들만 제시할 뿐 통합된 표준호가 되어 있지 않다. 최근 가상교육에서 학습기술이 상호운용성에 기반한 표준화의 일반적인 필요성을 인식하게 됨에 다라 가상교육의 국제표준을 소개하고 체계적으로 AICC(Aviation Industry CBT Committee), IMS Global Learning Consortium, ADL(Advanced Distributed Learning)을 중심으로 진행되어 오고 있다. 웹 기반의 교육을 통한 질의 응답의 학습방법을 고려한 도구가 없으므로 질의 응답 학습 도구(QALT)지원을 위한 표준화된 LTSA(Learning Technology Standard Architecture) 기반 시스템을 학습 객체에 대한 질의 응답과 개방형 단순 질의 응답 측면으로 구현한다. 그러므로 개방형 단순 질의 응답 측면을 구현하기 위해 학습 기술의 표준화로 제시되어 있는 LOM(Learning Object Metadata)을 통해 설계 자체를 체계화하고 전체적으로 명세 작업을 가능하게 하여 일관성을 유지하는 정련화된 문서로 질의 응답할 수 있도록 한다. 또한, Web 상에서의 Network delivery와 DTD(Document Type Definition)와 Stylesheet를 사용자가 쉽게 수정 가능하며 다양한 Linking Type을 제공하므로 단순 질의 응답 문서의 형식을 XML로 한다

• ETRI Journal
• /
• v.45 no.5
• /
• pp.735-745
• /
• 2023

This paper surveys recent multiagent reinforcement learning and neural Myerson auction deep learning efforts to improve mobility control and resource management in autonomous ground and aerial vehicles. The multiagent reinforcement learning communication network (CommNet) was introduced to enable multiple agents to perform actions in a distributed manner to achieve shared goals by training all agents' states and actions in a single neural network. Additionally, the Myerson auction method guarantees trustworthiness among multiple agents to optimize rewards in highly dynamic systems. Our findings suggest that the integration of MARL CommNet and Myerson techniques is very much needed for improved efficiency and trustworthiness.

• Composites Research
• /
• v.32 no.5
• /
• pp.216-221
• /
• 2019

Piecewise integrated composite (PIC) beam has different stacking sequences for several regions with respect to their superior load-resisting capabilities. On the interest of current research is to improve bending characteristics of PIC beam, with assigning specific stacking sequence to a specific region with the help of machine learning techniques. 240 elements of from the FE model were chosen to be reference points. Preliminary FE analysis revealed triaxialities at those regularly distributed reference points to obtain learning data creation of machine learning. Triaxiality values catagorise the type of loading i.e. tension, compression or shear. Machine learning model was formulated by learning data as well as hyperparameters and proper load fidelity was suggested by tuned values of hyperparameters, however, comparatively higher nonlinearity intensive region, such as side face of the beam showed poor load fidelity. Therefore, irregular distribution of reference points, i.e., dense reference points were distributed in the severe changes of loading, on the contrary, coarse distribution for rare changes of loading, was prepared for machine learning model. FE model with irregularly distributed reference points showed better load fidelity compared to the results from the model with regular distribution of reference points.

• Journal of Korea Multimedia Society
• /
• v.10 no.12
• /
• pp.1679-1686
• /
• 2007

In this paper, we introduce the sharable and reusable learning objects which are suitable for XML Web services in e-learning systems. These objects are extracted from the principles of pedagogical paradigms for reusable learning units. We call them LIO (Learning Item Object) objects. Existing models, such as Web-hosted and ASP-oriented service model, are difficult to cooperate and integrate among the different kinds of e-learning systems. So we developed the LIO objects that are suitable for XML Web services. The reusable units that are extracted from pedagogical paradigms are tutorial item, resource, case example, simulation, problems, test, discovery and discussion. And these units correspond to the LIO objects in our learning object model. As a result, the proposed model is that learner and instruction designer should increase the power of understanding about learning contents that are based on pedagogical paradigms. By using XML Web services, this guarantees the integration and interoperation of the different kinds of e-learning systems in distributed environments and so educational organizations can expect the cost reduction in constructing e-learning systems.

• Journal of Platform Technology
• /
• v.11 no.4
• /
• pp.80-88
• /
• 2023

To construct a learning model in the field of artificial intelligence, a dataset should be collected and be delivered to the central server where the learning model is constructed. Federated learning is a machine learning method building a global learning model without transmitting data located in a client side in a collaborative manner. It can be used to protect privacy, and after constructing a local trained model on individual clients, the parameters of the local model are aggregated centrally to update the global model. In this paper, we reuse the existing learning parameter to improve federated learning, describe incremental federated learning. For this work, we do experiments using the federated learning framework named Flower, and evaluate the experiment results with regard to elapsed time and precision when executing optimization algorithms.

• Journal of Korean Elementary Science Education
• /
• v.23 no.3
• /
• pp.251-265
• /
• 2004

Conceptual teaming has been one of the important issue in science education, and its theory and method has been interacted with the studies of philosophy of science, cognitive science, and cognitive psychology. The last two decades have witnessed a remarkable growth of the study on brain-style computation, i.e. connectionism. This study aimed to investigate the properties of the connectionist views of the concept and its implications in the conceptual learning of science. In connectionist views, a concept was represented as a pattern of activity distributed over many connected units, and a kind of network composed of many sub-concept units. And the ＇distributed representation＇ had the features of the constructivity, the automatically generalization, and the tunability. On the base of these views, it was suggested that (ⅰ) ＇Typically-Perceived-Situation＇, a kind of mental representation rising spontaneously in an individual mind when someone is thinking about any object, should be highlighted, and (ⅱ) the roles of the sub-concept units in formation of concept and the resolution of concept into the sub-concept units should be highlighted. Finally the meanings of these implications in conceptual teaming of science are discussed.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.6
• /
• pp.54-61
• /
• 1995

In this paper, we implemented distributed neural network that recognizes phonemes by frame unit for the 30 Korean proverbs sentences consist of 106 isolated words. The features of speech were chosen as PLP cepstrums, energy and zero crossings, where we get those being used as inputs to the distributed neural networks in wide area for a frame to get the good temperal characteristics. A young man of twenties has produced 30 proverbs 5 times. The learning of neural network uses 4 sets of them. 1 set being unused remains for test. There exists silence between words for the easy discrimination. The ratio of frame recognition in large grouping neural network is $95.3\%$ when 4 sets were used for the learning.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.12
• /
• pp.969-976
• /
• 2020

The role of customers has changed from that of passive users to value co-creators. Therefore, it is important to understand how customer learning takes place and how it affects customer experiences with services and products. However, while past studies insist on the importance of the issues in designing customer experiences, they do not empirically address these issues. This study investigates the support processes for customer learning, and their impact on customer learning, which in turn influences customer experience. To test the hypotheses, we employed the survey method. Target informants were the actual users of Apple iPods. A total of 200 survey questionnaires were distributed and 146 were collected. Among these, seven erroneous responses were excluded, leaving 139 usable ones. The proposed model was empirically analyzed using the Covariance-based SEM (Structural Equation Modelling) technique. The findings of this study suggest that, among the three support processes in customer learning, learning-by-doing support and learning-by-investment support positively affect customer learning, which influences customer experience. This study contributes to the literature by identifying different types of support for different kinds of customer learning processes and by empirically testing the impact of the support for the process on customer learning, and in turn, its impact on customer experience.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1182-1185
• /
• 1996

The objective of this paper is to control a nonlinear dynamical systems based on Self-Organized Distributed Networks (SODN). The learning with the SODN is fast and precise. Such properties are caused from the local learning mechanism Each local network learns only data in a subregion. Methods for indirect adaptive control of nonlinear systems using the SODN is presented. Through extensive simulation, the SODN is shown to be effective for adaptive control of nonlinear dynamic systems.