• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.223-238
• /
• 2023

This research presents the actual situation analysis and suggestions for the changes, experiences, and process of adaptation that college students have experienced throughout their studies and life over the past two years and more. In-depth interviews were conducted with university students, who are educational objects, and qualitative analysis methods were used to explore the overall living experiences under the pandemic situation. The interview questions were composed to cover classes, life, and emotional experiences after COVID-19, and the result of analyzing the responses boiled down to four super-categories of 'adaptation process to a new system, daily incontinence, struggle for health, and longing for connection.' This study is significant in that it analyzed the experiences and intimate changes of individual college students in unexpected and challenging situations, and urged the myriad aspects that universities, society, and the government should illuminate and respond to.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.3
• /
• pp.879-886
• /
• 2018

The basic search engine on Twitter shows not only tweets that contain search keywords, but also all articles written by users with nicknames containing search keywords. Since the tweets unrelated to the search keyword are exposed as search results, it is inconvenient to many users who want to search only tweets that include the keyword. To solve this inconvenience, this study improved the search function of Twitter by developing an algorithm that searches only tweets that contain search keywords. The improved functionality is implemented as a Web service using ASP.NET MVC5 and is available to many users. We used a powerful collection method in C# to retrieve the results of an object, and it was also possible to output them according to the number of 'retweets' or 'favorites'. If the number of retrieved numbers is less than a given number, we also added an exclusion filter function. Thus, sorting search results by the number of retweets or favorites, user can quickly search for opinions that are of interest to many users. It is expected that many users and data analysts will find the developed function convenient to search on Twitter.

• Journal of Broadcast Engineering
• /
• v.19 no.5
• /
• pp.640-655
• /
• 2014

Many of today's video systems have additional depth camera to provide extra features such as 3D support. Thanks to these changes made in multimedia system, it is now much easier to obtain depth information of the video. Depth information can be used in various areas such as object classification, background area recognition, and so on. With depth information, we can achieve even higher coding efficiency compared to only using conventional method. Thus, in this paper, we propose the 2D video coding algorithm which uses depth information on top of the next generation 2D video codec HEVC. Background area can be recognized with depth information and by performing HEVC with it, coding complexity can be reduced. If current CU is background area, we propose the following three methods, 1) Earlier stop split structure of CU with PU SKIP mode, 2) Limiting split structure of CU with CU information in temporal position, 3) Limiting the range of motion searching. We implement our proposal using HEVC HM 12.0 reference software. With these methods results shows that encoding complexity is reduced more than 40% with only 0.5% BD-Bitrate loss. Especially, in case of video acquired through the Kinect developed by Microsoft Corp., encoding complexity is reduced by max 53% without a loss of quality. So, it is expected that these techniques can apply real-time online communication, mobile or handheld video service and so on.

• Journal of The Korean Association For Science Education
• /
• v.40 no.2
• /
• pp.191-201
• /
• 2020

This study investigated verbal and physical interactions which appeared in collaborative science concept learning using augmented reality. Twelve 10th grade students participated in this study. After being organized into three four-member small groups, they participated in classes using smart device-based augmented reality application developed for the understanding of the chemical bonding concept. Their class activities were audio- and video-taped. Semi-structured interviews were also conducted. The results revealed that within individual statement units of verbal interaction, the proportions of information question/explanation and direction question/explanation were found to be high. Within interaction units, the proportions of reformative and cumulative interaction were relatively high. The proportions of progress were also found to be high within both individual statement units and interaction units of verbal interaction. Students' physical interactions were mainly conducted without meaningful verbal interactions. When their physical interactions were accompanied by knowledge construction-related verbal interactions, the proportions of gazing virtual objects and worksheet-related interactions were high. In contrast, various exploratory activities related to the manipulation of markers mainly appeared when they conducted physical interactions only, or when their physical interactions were accompanied by management-related verbal interactions. On the bases of the results, effective methods for collaborative concept learning using augmented reality in science education are discussed.

• Science of Emotion and Sensibility
• /
• v.9 no.spc3
• /
• pp.209-224
• /
• 2006

Hierarchy which is often named as the tree-structure is used to reduce complexity and show primitive structures of complicated information. This paper aims at explaining information-visualization methods using hierarchies in multimedia domains and prospecting the possible applications by examining how they affect the user's tasks involved in information-seeking activities. As a result, four types of information visualization methods named Treemap, Hyperbolic, Cone Tree and DOI Tree employed in multimedia domain, are presented and pros and cons of each method are explained in this paper. Another important part is defining the core tasks and other related-tasks in information-seeking activities, such as, overview, zoom, filter, details-on-demand, relate, history, and extract. Followings are major findings. Treemap uses 'overview' as the core task, which makes user to gain a overall meaning of the whole information cluster. Hyperbolic and DOI Tree apply 'Boom' task through the function of focus+context or by the function of meaningful scaling to magnify or downsize each node. Cone Tree, also, makes the information organizer to classify the patterns of information acquired in the process of users' information-seeking activities by using 'extract' task. Through this study, it is finally found out that the information-visualization methods using hierarchies in multimedia domains should incorporate the wide variety of functional needs related to users' information-seeking behaviors beyond the visual representation of information.

• The KIPS Transactions:PartA
• /
• v.15A no.3
• /
• pp.141-149
• /
• 2008

In this research we present a novel method which combines and visualizes the design model and the FDM-based simulation result of solidification. Moreover we employ VR displays and visualize stereoscopic images to provide an effective analysis environment. First we reconstruct the solidification simulation result to a rectangular mesh model using a conventional simulation software. Then each point color of the reconstructed model represents a temperature value of its position. Next we map the two models by finding the nearest point of the reconstructed model for each point of the design model and then assign the point color of the design model as that of the reconstructed model. Before this mapping we apply mesh subdivision because the design model is composed of minimum number of points and that makes the point distribution of the design model not uniform compared with the reconstructed model. In this process the original shape is preserved in the manner that points are added to the mesh edge which length is longer than a predefined threshold value. The implemented system visualizes the solidification simulation data on the design model, which allows the user to understand the object geometry precisely. The immersive and realistic working environment constructed with use of VR display can support the user to discover the defect occurrence faster and more effectively.

• Information Systems Review
• /
• v.10 no.2
• /
• pp.211-234
• /
• 2008

The history of information system (IS) development methodology in Korea is less than 30 years. Korea introduced the structured development methodology in the public fields in 1980s, introduced the information engineering methodology in 1990s, and accepted and developed the objected oriented development methodology and the component based development methodology in 2000s. The history of IS development methodology in Korea is shorter than that of the world. Korea's IS development methodology started 10 year later compared with the world level. But it developed rapidly in 1990s and then grew to the world level in 2000s. This paper is the first research that it investigated the history of IS development methodology in Korea. This paper will give the people of IT industry the historical insights about IS development methodology and will help make a current and future strategic plan for IS development methodology. And it will provide researchers and policy makers with the insights and research ideas of future direction of information system development.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.23 no.3
• /
• pp.233-238
• /
• 2005

3-D virtual city model is becoming increasingly important for a number of GIS applications. For reconstruction of 3D building in urban area aerial images, satellite images, LIDAR data have been used mainly and most of researches related to 3-D reconstruction focus on development of method for extraction of building height and reconstruction of building. In case of automatically extracting and reconstructing of building height using only aerial images or satellite images, there are a lot of problems, such as mismatching that result from a geometric distortion of optical images. Therefore, researches of integrating optical images and existing digital map (1/1,000) has been in progress. In this paper, we focused on extracting of building height by means of interest points and vertical line locus method for reducing matching points. Also we used digital plotter in order to validate for the results in this study using aerial images (1/5,000) and existing digital map (1/1,000).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.4
• /
• pp.387-394
• /
• 2016

A stereo matching method is one of the ways to obtain a depth value from two dimensional images. This method estimates the depth value of target images using stereo images which have two different viewpoints. In the result of stereo matching, the depth value is represented by a disparity value. The disparity means a distance difference between a current pixel in one side of stereo images and its corresponding point in the other side of stereo images. The stereo matching in a homogeneous region is always difficult to find corresponding points because there are no textures in that region. In this paper, we propose a novel matching equation using the distance transform to estimate accurate disparity values in the homogeneous region. The distance transform calculates pixel distances from the edge region. For this reason, pixels in the homogeneous region have specific values when we apply this transform to pixels in that region. Therefore, the stereo matching method using the distance transform improves the matching accuracy in the homogeneous regions. In addition, we also propose an adaptive matching cost computation using a kernel of one dimensional array depending on the characteristic of regions in the image. In order to aggregate the matching cost, we apply a cross-scale cost aggregation method to our proposed method. As a result, the proposed method has a lower average error rate than that of the conventional method in all regions.