• The Journal of Sustainable Design and Educational Environment Research
• /
• v.9 no.3
• /
• pp.49-58
• /
• 2010

The Ministry of educational science and technology is about to conduct its 7th &8th curriculum. However, there are some problems in achieving its goals under the current class model system in both educational and architectural. This study finds the characteristics of the arrangements and architectural planning in the departmental system - designed high schools. As a result, the arrangement was tend to be 'overall type' or 'central type' depending on the teaching-learning efficiency. Liberal arts and science&technology groups were placed close, and foreign languages and general cultural studies were arranged close as well. Importantly, there were supporting facilities such as a gymnasium, a cafeteria, a library, a computer lab, and an all-purpose-room, and this arrangement provided convenience. It is for the better learning effect and the high efficiency. It is worthy noticing that the placement and formation of individual or study space is regarded importantly. In flow planning, it seemed that it was designed to reduce the users' movement to a minimum. However, there are still some problems compared to Japan or the States, who already has an established departmental system. I think that the government should enforce its necessity of planning to schools, relevant divisions, or architects to bring it up. Furthermore, it is urgently needed a practical and future-oriented study that can forecast any changes in architectural spaces within the ever-changing teaching and learning environment in the information-oriented society.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.19-27
• /
• 2020

In this paper, we propose a machine learning method for diagnosing the failure of a gas pressure regulator. Originally, when implementing a machine learning model for detecting abnormal operation of a facility, it is common to install sensors to collect data. However, failure of a gas pressure regulator can lead to fatal safety problems, so that installing an additional sensor on a gas pressure regulator is not simple. In this paper, we propose various machine learning approach for diagnosing the abnormal operation of a gas pressure regulator with only the flow rate and gas pressure data collected from a gas pressure regulator itself. Since the fault data of a gas pressure regulator is not enough, the model is trained in all classes by applying the over-sampling method. The classification model was implemented using Gradient boosting, 1D Convolutional Neural Networks, and LSTM algorithm, and gradient boosting model showed the best performance among classification models with 99.975% accuracy.

• Journal of The Korean Association For Science Education
• /
• v.37 no.6
• /
• pp.1025-1035
• /
• 2017

The purposes of this study are to analyze the merits and limits of flipped learning by suggesting the ALP model for efficient application and to test the effects of the new ALP model. The process of new model and program development is based on ADDIE in this study. This study consists of two steps. First through literature research on the difficulties of the flipped learning, the elements are extracted to develop new model. Second, these elements were placed according to the teaching and learning flow, which resulted in the procedures. As a result, the ALP model was developed. The ALP model is a new model for applying teaching and learning methods for efficient application of the flipped learning. This model was applied to elementary science classes to test its effects in scientific communication skill. Interviews and cognitive survey were also conducted to collect additional information. The results of this study are as follows: There were various difficulties in flipped learning. Based on literature research results, the ALP model and the science programs for elementary students have been developed. The experimental group showed statistically meaningful improvement in scientific communication skill. The scientific communication skill has two subcategories: the forms and the types. According to the form analysis results, the experimental group showed a statistically meaningful improvement in the form of Table and Picture, but not in the form of Writing and Number. With the same reason given previously, this study confirmed that the application of ALP model improves the students' visual form communication skills such as Table and Picture better than reading form communication skills such as Writing and Number. According to the type analysis results, the experimental group showed a statistically meaningful improvement in "the scientific insistence" type, and "the justification" which is the sub element of "the scientific insistence" type. With this reason, this study suggests that the class applied ALP model gives students more time and opportunities to learn. Though the survey and interviews about the student's awareness of the class with applied the ALP model, this study showed that students actively exchanged their opinions in the class with applied ALP model.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1403-1413
• /
• 2021

In this paper, we investigate automated data validation techniques for artificial intelligence training, and also disclose open-source frameworks, such as Google's TensorFlow Data Validation (TFDV), that support automated data validation in the AI model development process. We also introduce an experimental study using public data sets to demonstrate the effectiveness of the open-source data validation framework. In particular, we presents experimental results of the data validation functions for schema testing and discuss the limitations of the current open-source frameworks for semantic data. Last, we introduce the latest studies for the semantic data validation using machine learning techniques.

• Journal of The Korean Association For Science Education
• /
• v.32 no.5
• /
• pp.1007-1026
• /
• 2012

The purpose of this study was to develop analytic framework for dialogic argumentation to show the context and flow visualizing interactions of argumentation, to be able to present quality of argumentation specifically. For this, we formulated a method of the argumentation diagram using feature of diagram simple and structurally visualizing interrelation between argument components, and then quantified quality of argumentation to argument level score on this basis. We have developed the learning material for argumentation about a vertical circular motion and used the obtained translations from applying it in developing the framework. We chose argument statements among full transcript and then coded as Toulmin's argument components, and these codes was effectively arranged and linked to show argumentation diagram. Results by argumentation diagram could be useful understanding of interactive argumentation context and the flow and present frequency, the combination of argument elements, rough qualitative level of argumentation. To quantify argumentation quality, we gave different scores to different link lines reflecting indication of argumentation quality like that diversity of argument component, justification, presence or absence of rebuttals. The process of identification of argument level is very simple, qualitative level of argumentation represented as concrete score could present various and concrete argument level. Developed analytic framework might contribute to argumentation research field, because it can present effectively dialogic argumentation result. Also, various analysis cases might guide designing an effective argumentation practice and circular motion learning.

• Journal of Korea Multimedia Society
• /
• v.24 no.1
• /
• pp.21-29
• /
• 2021

With the recent increase in the number of households raising pets, various engineering studies have been underway for pets. The final purpose of this study is to automatically generate situation-sensitive captions that can express implicit intentions based on the behavior and sound of cats by embedding the already mature behavioral detection technology of pets as basic element technology in the video capturing research. As a pilot project to this end, this paper proposes a high-level capturing system using optical-flow, RGB, and sound information of cat videos. That is, the proposed system uses video datasets collected in an actual breeding environment to extract feature vectors from the video and sound, then through hierarchical LSTM encoder and decoder, to identify the cat's behavior and its implicit intentions, and to perform learning to create context-sensitive captions. The performance of the proposed system was verified experimentally by utilizing video data collected in the environment where actual cats are raised.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.177-185
• /
• 2024

Web science, a general discipline of learning is presently at high demand of expertise with ideas to develop software-based WebApps and MobileApps to facilitate user or customer demand e.g. shopping etc. electronically with the access at their smartphones benefitting the business enterprise as well. A worldwide-computerized reservation network is used as a single point of access for reserving airline seats, hotel rooms, rental cars, and other travel related items directly or via web-based travel agents or via online reservation sites with the advent of social-web, e-commerce, e-business, from anywhere-on-earth (AoE). This results in the accumulation of large and diverse distributed databases known as big data. This paper describes a novel intelligent web-based electronic booking framework for e-business with distributed computing and data mining support with the detail of e-business system flow for e-Booking application architecture design using the approaches for distributed computing and data mining tools support. Further, the importance of business intelligence and data analytics with issues and challenges are also discussed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.419-422
• /
• 2019

The recent increase in single-person households and family income has led to an increase in the number of pet owners. However, due to the owners' difficulty to communicate with them for 24 hours, pets, and especially dogs, tend to display unwanted behavior that can be harmful to themselves and their environment when left alone. Therefore, detecting those behaviors when the owner is absent is necessary to suppress them and prevent any damage. In this paper, we propose a camera-based system that detects a set of normal and unwanted behaviors using deep learning algorithms to monitor dogs when left alone at home. The frames collected from the camera are arranged into sequences of RGB frames and their corresponding optical flow sequences, and then features are extracted from each data flow using pre-trained VGG-16 models. The extracted features from each sequence are concatenated and input to a bi-directional LSTM network that classifies the dog action into one of the targeted classes. The experimental results show that our method achieves a good performance exceeding 0.9 in precision, recall and f-1 score.

• The Journal of the Korea Contents Association
• /
• v.8 no.12
• /
• pp.457-464
• /
• 2008

This study is to design, develope, and deploy of e-learning inquiry based content in elementary science class. First, this study analyzed related literature review, case studies, and inquiry based class models for seeking better applicable design and development modes. From focus group meeting, experts discussed the inquiry content design ideas for elementary students for science class. This study finally established its own inquiry design mode for online science class with the flow of understanding of problem, sep up hypothesis, problem solving, and solution analysis. The developed content was deployed in real classroom setting to see how students received the contents and how well they processed the learning activities. We found that inquiry based online content, especially when applied to science subject, can be effective in students interests and their motivations. We also observed that there were a few managerial errors such as detailed lesson guidance and tutor support for students activities. This study concluded that inquiry based online contents should be designed considering students interests based on learning subjects and also developed in terms of students interests and strong motivation as well. We suggest that related research should be expanded toward to other subject than science and various students age groups.

• Journal of The Korean Association of Information Education
• /
• v.6 no.2
• /
• pp.234-245
• /
• 2002

A new era has come where high quality educational materials can be acquired easily through the World Wide Web. These materials, however, need to be refined and streamlined to maximize their effect on education. In order to provide such a streamlined flow, we need to be able to re-organize documents, which exist independent of each other on the Web, in a way that maintains their appropriate order in the right context to satisfy educational purposes. In addition, we should be able to provide supplementary explanations or missing information to the organized materials for smooth connections among them. In order to meet the requirements, we employed the virtual document concept that allows us to reuse existing documents for educational purposes. By providing a retrieval engine for virtual documents, we attempt to induce self-directed learning based on document retrieval, suitable for the level and purpose of students.