• Journal of Internet Computing and Services
• /
• v.21 no.4
• /
• pp.9-16
• /
• 2020

In the Image processing and computer vision, the problem of reconstructing from one image to another or generating a new image has been steadily drawing attention as hardware advances. However, the problem of computer-generated images also continues to emerge when viewed with human eyes because it is not natural. Due to the recent active research in deep learning, image generating and improvement problem using it are also actively being studied, and among them, the network called Generative Adversarial Network(GAN) is doing well in the image generating. Various models of GAN have been presented since the proposed GAN, allowing for the generation of more natural images compared to the results of research in the image generating. Among them, pix2pix is a conditional GAN model, which is a general-purpose network that shows good performance in various datasets. pix2pix is based on U-Net, but there are many networks that show better performance among U-Net based networks. Therefore, in this study, images are generated by applying various networks to U-Net of pix2pix, and the results are compared and evaluated. The images generated through each network confirm that the pix2pix model with Attention, R2, and Attention-R2 networks shows better performance than the existing pix2pix model using U-Net, and check the limitations of the most powerful network. It is suggested as a future study.

• Fire Science and Engineering
• /
• v.33 no.6
• /
• pp.152-158
• /
• 2019

This study examined the socio-economic and clinical characteristics associated with the use of ambulance services among pregnant, childbearing, and postpartum women based on data from the 2008-2016 Korea Health Panel. The analysis revealed that among the pregnant, childbearing, and postpartum women, the proportion using all ambulance services was 18.9% whereas 12.0% used private and 119 ambulances. Moreover, among those using ambulance services, delivery was the most common reason (38.7%) followed by complications of labor and delivery (20.0%) and pregnancy with abortive outcome (17.3%). There were statistically significant differences between the users and non-users of ambulance services in terms of the average annual household income, emergency arrival time, and delayed arrival at the emergency room. As childbirth becomes more complicated due to low fertility and elderly mothers, the expansion and improvement of ambulance services as a social safety net for pregnant, childbearing, and postpartum women will become increasingly important.

• Journal of the Korean Society for information Management
• /
• v.31 no.3
• /
• pp.29-63
• /
• 2014

This study attempted to reveal the characteristics of the Y generation, to derive the services of the next generation digital library, and to compare differences between the demands of the baby boom generation and the Y generation to some extent. As a result, first, it is shown that the digital device the Y generation uses the most, was a cell phone or smartphone, followed by desktop PC, notebook PC, and digital camera. Although there were some differences, the Y generation's use ratio of digital devices was substantially similar to the baby boomers'. Second, there was a significant difference between the Y generation and baby boom generation in terms of using digital services. While the Y generation used internet portals the most, the baby boom generation used e-mail service the most. Third, we surveyed the services which the Y generation and baby boom generation require for the next generation digital libraries, by grouping as follows: the cloud service, infinite creative space (maker space), big data, augmented reality, Google Glass, context-aware technologies, semantic services, SNS service, digital textbook service, RFID and QRCode service, library space configuration, a state-of-the-art display technology, and other innovative services. While the most demanded service by the Y generation was big data service, the baby boom generation most demanded digital textbook service.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.467-471
• /
• 2010

Weblog is one of the most spread web services. The content of the weblog includes daily events and emotions. If we collect personal information using mobile devices and create a weblog, user can create their own weblog easily. Some researchers already developed systems that created weblog in mobile environment. In this paper, user's activity is inferred from personal information in mobile device. The inferred activities and story generation engine are used to generate text for creating a weblog. Finally, the text, photographs and user's movement in Google Map are integrated into a weblog.

• Journal of Internet Computing and Services
• /
• v.7 no.6
• /
• pp.11-20
• /
• 2006

One of the most important factor while developing web application is to separate presentation and business logic lowering the maintenance cost. There are various web application development tools mainly categorized as script based such as Servlet, JSP, ASP.NET techniques and dynamic server page development frameworks such as Struts, JSF (Java Server Faces), Spring MVC etc. These tools provide web tier processing solution but not the complete separation of presentation and business logic. In this paper, we developed custom tog component that separate presentation and business logic, to process them we also developed container. In addition, DOM tree is applied to the developed container to manage the presentation effectively.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.14 no.5
• /
• pp.31-39
• /
• 2018

Recently, there has been active studies to provide a user-friendly interface in a virtual reality environment by recognizing user hand gestures based on deep learning. However, most studies use separate sensors to obtain hand information or go through pre-process for efficient learning. It also fails to take into account changes in the external environment, such as changes in lighting or some of its hands being obscured. This paper proposes a hand gesture recognition method based on deep learning that is strong in external environments without the need for pre-process of RGB images obtained from general webcam. In this paper we improve the VGGNet and the GoogLeNet structures and compared the performance of each structure. The VGGNet and the GoogLeNet structures presented in this paper showed a recognition rate of 93.88% and 93.75%, respectively, based on data containing dim, partially obscured, or partially out-of-sight hand images. In terms of memory and speed, the GoogLeNet used about 3 times less memory than the VGGNet, and its processing speed was 10 times better. The results of this paper can be processed in real-time and used as a hand gesture interface in various areas such as games, education, and medical services in a virtual reality environment.

• The Korean Journal of Health Service Management
• /
• v.13 no.4
• /
• pp.19-31
• /
• 2019

Objectives: The purpose of this study was to analyze research trends in age-friendly research and suggest directions for future research. Methods: For this study, 112 articles related to age-friendly research were selected, from 605 published articles in The Korean Journal of Health Service Management (2007-2018). Content analysis and text network analysis were conducted using SPSS 23.0 and NetMiner 4. Results: First, 2 authors (30.4%) and 4 keywords (45.5%) were the most studied. Most of the studies used quantitative research (93.8%). Primary data (61.9%) and SPSS (77.7%) were the most used for analysis. Second, there were seven common keywords in the top 10 in all the centralities. They were Elderly, Geriatric Hospital, Depression, Care Workers, Long-Term Care Facilities, Experience, and Attitude. Conclusions: This study shows the need for diversity of research topics, subjects, research methods, and analytical tools in future age-friendly related studies. In addition, it suggests activating convergence research in this field linked to various industries and services.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.25 no.2
• /
• pp.80-98
• /
• 2023

This study explores the effectiveness of various data preprocessing algorithms for improving subseasonal to seasonal (S2S) climate predictions from six climate forecast models and their Multi-Model Ensemble (MME) using a deep learning-based postprocessing model. A pipeline of data transformation algorithms was constructed to convert raw S2S prediction data into the training data processed with several statistical distribution. A dimensionality reduction algorithm for selecting features through rankings of correlation coefficients between the observed and the input data. The training model in the study was designed with TimeDistributed wrapper applied to all convolutional layers of U-Net: The TimeDistributed wrapper allows a U-Net convolutional layer to be directly applied to 5-dimensional time series data while maintaining the time axis of data, but every input should be at least 3D in U-Net. We found that Robust and Standard transformation algorithms are most suitable for improving S2S predictions. The dimensionality reduction based on feature selections did not significantly improve predictions of daily precipitation for six climate models and even worsened predictions of daily maximum and minimum temperatures. While deep learning-based postprocessing was also improved MME S2S precipitation predictions, it did not have a significant effect on temperature predictions, particularly for the lead time of weeks 1 and 2. Further research is needed to develop an optimal deep learning model for improving S2S temperature predictions by testing various models and parameters.

• Journal of Information Technology Services
• /
• v.12 no.4
• /
• pp.349-367
• /
• 2013

In MANET, the AODV routing protocol with on-demand method has a problem in large control packet overhead. In order to improve this, we first need a comprehensive analysis of correlation between performance metrics and factors affecting the performance of AODV. Selected parameters based on this analysis make it enable to be a more accurate and fair performance analysis, as well as to reduce the time and effort when constructing a scenario for performance analysis. In this paper, various scenarios are configured to apply AODV by varying the values of factors affecting the performance with network simulator QualNet 5.0, and then the results are analysed using performance metrics proposed by IETF MANET working group. This paper also founds a correlation between performance metrics and factors affecting the performance for AODV routing protocol, choosing the values of factors that represent many of the most maximum and minimum values of each performance metrics, and proposes optimal simulation parameters for a more accurate performance evaluation of routing protocols with minimal scenario in experiments. Next, performance comparison of AODV, DSR and DYMO routing protocols based on the proposed simulation parameters is shown which provides a comparative analysis on the performance of on-demand routing protocols. Results of this paper could be very useful for the researcher or service provider who wants to find nice simulation environment or select a proper routing protocol.

• Convergence Security Journal
• /
• v.17 no.3
• /
• pp.3-9
• /
• 2017

NFV is a technology that allows network services to be controlled and managed in software by separating various net work functions (NFs) from hardware devices in dedicated network equipment and implementing them in a high-performance general-purpose server. Therefore, standardized virtualization of network functions is one of the most important factors. However, until the introduction of NFV to provide commercial services, there are many technical issues to be solved such as guaranteeing performance, stability, support for multi-vendor environment, ensuring perfect interoperability, and linking existing virtual and non-virtual resources. In this paper, we propose a method to provide an end-to-end network virtualization service based on OSM R2 in KREONET.