• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.295-302
• /
• 2010

Example-based super resolution(EBSR) is a method to reconstruct high-resolution images by learning patch-wise correspondence between high-resolution and low-resolution images. It can reconstruct a high-resolution from just a single low-resolution image. However, when it is applied to a text image whose font type and size are different from those of training images, it often produces lots of noise. The primary reason is that, in the patch matching step of the reconstruction process, input patches can be inappropriately matched to the high-resolution patches in the patch dictionary. In this paper, we propose a new patch matching method to overcome this problem. Using an image observation model, it preserves the correlation between the input and the output images. Therefore, it effectively suppresses spurious noise caused by inappropriately matched patches. This does not only improve the quality of the output image but also allows the system to use a huge dictionary containing a variety of font types and sizes, which significantly improves the adaptability to variation in font type and size. In experiments, the proposed method outperformed conventional methods in reconstruction of multi-font and multi-size images. Moreover, it improved recognition performance from 88.58% to 93.54%, which confirms the practical effect of the proposed method on recognition performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.4
• /
• pp.765-773
• /
• 2009

Currently Telematics traffic information services have been various because we can collect real-time traffic information through Intelligent Transport System. In this paper, we proposed and implemented a short-term traffic information prediction model for giving to guarantee the traffic information with high quality in the near future. A Short-term prediction model is for forecasting traffic flows of each segment in the near future. Our prediction model gives an average speed on the each segment from 5 minutes later to 60 minutes later. We designed a Bayesian network for each segment with some casual nodes which makes an impact to the road situation in the future and found out its joint probability density function on the supposition of GMM(Gaussian Mixture Model) using EM(Expectation Maximization) algorithm with training real-time traffic data. To validate the precision of our prediction model we had conducted various experiments with real-time traffic data and computed RMSE(Root Mean Square Error) between a real speed and its prediction speed. As the result, our model gave 4.5, 4.8, 5.2 as an average value of RMSE about 10, 30, 60 minutes later, respectively.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.11-19
• /
• 2021

A software system is required to change during its life cycle due to various requirements such as adding functionalities, fixing bugs, and adjusting to new computing environments. Such program code modification should be considered as carefully as a new system development becase unexpected software errors could be introduced. In addition, when reusing open source programs, we can expect higher quality software if code changes of the open source program are predicted in advance. This paper proposes a Convolutional Neural Network (CNN)-based deep learning model to predict source code changes. In this paper, the prediction of code changes is considered as a kind of a binary classification problem in deep learning and labeled datasets are used for supervised learning. Java projects and code change logs are collected from GitHub for training and testing datasets. Software metrics are computed from the collected Java source code and they are used as input data for the proposed model to detect code changes. The performance of the proposed model has been measured by using evaluation metrics such as precision, recall, F1-score, and accuracy. The experimental results show the proposed CNN model has achieved 95% in terms of F1-Score and outperformed the multilayer percept-based DNN model whose F1-Score is 92%.

• Journal of Korea Water Resources Association
• /
• v.54 no.12
• /
• pp.1255-1263
• /
• 2021

While it could become an alternative water resource, fog could undermine traffic safety and operational performance of infrastructures. To reduce such adverse impacts, it is necessary to have spatially continuous fog risk information. In this work, tree-based machine-learning models were developed in order to quantify fog risks with routine meteorological observations alone. The Extreme Gradient Boosting (XGB), Light Gradient Boosting (LGB), and Random Forests (RF) were chosen for the regional fog models using operational weather and visibility observations within the Jeollabuk-do province. Results showed that RF seemed to show the most robust performance to categorize between fog and non-fog situations during the training and evaluation period of 2017-2019. While the LGB performed better than in predicting fog occurrences than the others, its false alarm ratio was the highest (0.695) among the three models. The predictability of the three models considerably declined when applying them for an independent period of 2020, potentially due to the distinctively enhanced air quality in the year under the global lockdown. Nonetheless, even in 2020, the three models were all able to produce fog risk information consistent with the spatial variation of observed fog occurrences. This work suggests that the tree-based machine learning models could be used as tools to find locations with relatively high fog risks.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.6
• /
• pp.124-131
• /
• 2017

Recently, drone is extending its range of usability. For example, the delivery, agriculture, industry, and entertainment area take advantage of drone mobilities. To control real drones, it needs huge amount of drone control training steps. However, it is risky; falling down, missing, destroying. The virtual drone system can avoid such risks. We reason that what kinds of technologies are required for building the virtual drone system. First, it needs that the virtual drone authoring tool that can assemble drones with the physical restriction in the virtual environment. We suggest that the drone assembly method that can fulfill physical restrictions in the virtual environment. Next, we introduce the virtual drone simulator that can simulate the assembled drone moves physically right in the virtual environment. The simulator produces a high quality rendering results more than 60 frames per second. In addition, we develop the physics engine based on SILS(Software in the loop simulation) framework to perform more realistic drone movement. Last, we suggest the virtual drone controller that can interact with real drone controllers which are commonly used to control real drones. Our virtual drone system earns 7.64/10.0 user satisfaction points on human test: the test is done by one hundred persons.

• Journal of National Security and Military Science
• /
• s.7
• /
• pp.271-303
• /
• 2009

"Ubiquitous sensor network" definition is this-Someone attaches electro-magnetic tag everything which needs communication between man to man, man to material and material to material(Ubiquitous). By using attached every electro-magnetic tag, someone detects it's native information as well as environmental information such as temperature, humidity, pollution and infiltration information(Sensor). someone connects it realtime network and manage generated information(Network). 21st century's war is joint combined operation connecting with ground, sea and air smoothly in digitalized war field, and is systematic war provided realtime information from sensor to shooter. So, it needs dramatic development on watch reconnaissance, command and control, pinpoint strike etc. Ubiquitous computing and network technologies are essential in national defense to operate 21st century style war. It is possible to use many parts such as USN combined smart dust and sensor network to protect friend unit as well as to watch enemy's deep area by unmanned reconnaissance, wearable computer upgrading soldier's operational ability and combat power dramatically, RFID which can be used material management as well as on time support. Especially, unmanned watch system using USN is core part to transit network centric military service and to get national defense efficiency which overcome the dilemma of national defense person resource reducing, and upgrade guard quality level, and improve combat power by normalizing guardian's bio rhythm. According to the test result of sensor network unmanned watch system, it needs more effort and time to stabilize because of low USN technology maturity and using maturity. In the future, USN unmanned watch system project must be decided the application scope such as application area and starting point by evaluating technology maturity and using maturity. And when you decide application scope, you must consider not only short period goal as cost reduction, soldier decrease and guard power upgrade but also long period goal as advanced defense ability strength. You must build basic infra in advance such as light cable network, frequency allocation and power facility etc. First of all, it must get budget guarantee and driving force for USN unmanned watch system project related to defense policy. You must forwarded the USN project assuming posses of operation skill as procedure, system, standard, training in advance. Operational skill posses is come from step by step application strategy such as test phase, introduction phase, spread phase, stabilization phase and also repeated test application taking example project.

• School Mathematics
• /
• v.16 no.4
• /
• pp.691-708
• /
• 2014

In general, the intuitive knowledge that can use in mathematics problem solving is one of the important knowledge to teachers as well as students. So, this study is aimed to analyze the elementary preservice teachers' intuitive knowledge in relation to intuitive and counter-intuitive problem solving. For this, I performed survey to use questionnaire consisting of problems that can solve in intuitive methods and cause the errors by counter-intuitive methods. 161 preservice teachers participated in this study. I got the conclusion as follows. preservice teachers' intuitive problem solving ability is very low. I special, many preservice teachers preferred algorithmic problem solving to intuitive problem solving. So, it's needed to try to improve preservice teachers' problem solving ability via ensuring both the quality and quantity of problem solving education during preservice training courses. Many preservice teachers showed errors with incomplete knowledges or intuitive judges in counter-intuitive problem solving process. For improving preservice teachers' intuitive problem solving ability, we have to develop the teacher education curriculum and materials for preservice teachers to go through intuitive mathematical problem solving. Add to this, we will strive to improve preservice teachers' interest about mathematics itself and value of mathematics.

• Journal of The Korean Association For Science Education
• /
• v.42 no.2
• /
• pp.277-287
• /
• 2022

This study aims to investigate the main effects and interaction effects of individual variables on the epistemological beliefs of elementary school science teachers. For this purpose, a survey was conducted on 338 elementary science teachers in the metropolitan area on gender, teaching career, and epistemological beliefs. Epistemological beliefs show significant differences not only in gender and teaching career, but also in the interaction between gender and teaching career. Depending on gender, female teachers are more integrated in knowledge than male teachers, and process is more important than outcome in learning. Depending on the teaching career, it was found that high-career teachers generally value the process rather than the results, as knowledge is integrated and constantly evolving, knowledge is acquired by individual reasoning and justified through external interaction. On the other hand, teachers with low career perceive that efforts are indispensable in learning compared to other groups. Depending on the interaction between gender and teaching career, elementary school teachers believe that the higher the teaching career, the more integrated and constantly evolved, but low-career male teachers believed that learning ability was born with experience, while high-career male teachers value the learning process. Based on this study, it is expected that many training sessions aimed at improving the quality of teaching and learning will provide more effective opportunities to develop elementary science teachers' epistemological beliefs, considering teachers' personal characteristics.

• Korean Journal of Comparative Education
• /
• v.20 no.3
• /
• pp.75-96
• /
• 2010

In Korea school-based management has been introduced for upgrading the quality of education from mid 1990's. Due to the change schools began to seek educational consulting services. However, educational consultancy still lies in the rudimentary stage. Recognizing the problems, it compares educational consultancy between Korea and United Kingdom. The study utilizes diverse methods such as literature review, interviews, document analysis. It covered the issues such as history and background, consultants, clients, tasks and processes, and support system for consultancy in both countries. The major findings are as follows. First, they had similar origin and motive for educational consultancy, but differences in the government's approach. Second, educational consultants in both countries have similar backgrounds and qualifications. But there are big differences in consulting firms and agencies. Third, there are also big differences in terms of clients. Fourth, there are differences in terms of consultancy tasks, but similar in consultancy process. Fifth, there are also big differences in service fees and incentives. However, there are similar problems in terms of consultancy training program and professional association of educational consultants. Based upon the findings it could draw implications such as providing more financial resources for Korean schools to purchase consultancy services.

• The Journal of the Korea Contents Association
• /
• v.12 no.4
• /
• pp.438-447
• /
• 2012

The objectives of this research are: to provide fundamental data for tourism policy and investigate medical tourism attributes by IPA(Importance-Performance Analysis) to attract Japanese medical tourists to Korea. Utilizing Japanese medical tourists as subjects of inquiry, this study evaluated the importance of medical tourism selection attributes and the rate at which these attributes were performed. Consequently, this study deduced 'convenience, service quality, differentiation, approximation' factors by factor analysis as well as the ranking among each selection attributes using T-test. The importance-performance analysis showed 'Concentrate Here' in quadrant I, 'Keep up the Good Work' in quadrant II, 'Low Priority' in quadrant III and 'Possible Overkill' in quadrant IV. The results show that "Concentrate Here" part in quadrant I is reservation procedure rapidity and information system simplicity. This means that these attributes are very important but they indicate low performance. Thus, concentration among tourism managers should be focused along these attributes. The study, then, suggests that employee who speaks Japanese fluently should be arranged during reservation procedure. Furthermore, Japanese class should become mandatory during basic employee training to improve reservation procedure rapidity. Moreover, clinic websites should concentrate on accessibility of Japanese users in such a way that they can consult their needs on line. Finally, managers should find diverse ways to bring about good service rapidly and conveniently.