• Journal of KIISE
• /
• v.42 no.6
• /
• pp.817-822
• /
• 2015

Relation extraction is an important information extraction technique that can be widely used in areas such as question-answering and knowledge population. Previous studies on relation extraction have been based on supervised machine learning models that need a large amount of training data manually annotated with relation categories. Recently, to reduce the manual annotation efforts for constructing training data, distant supervision methods have been proposed. However, these methods suffer from a drawback: it is difficult to use these methods for collecting negative training data that are necessary for resolving classification problems. To overcome this drawback, we propose a one-class classification model that can be trained without using negative data. The proposed model determines whether an input data item is included in an inner category by using a similarity measure based on lexical information and syntactic patterns in a vector space. In the experiments conducted in this study, the proposed model showed higher performance (an F1-score of 0.6509 and an accuracy of 0.6833) than a representative one-class classification model, one-class SVM(Support Vector Machine).

• Journal of KIISE:Software and Applications
• /
• v.29 no.10
• /
• pp.755-765
• /
• 2002

In this paper, we observe various syntactic information for Korean parsing and propose a method to learn constraints and improve the efficiency of a parsing model by using the constraints. The proposed method has the following three characteristics. First, it improves the parsing efficiency since we use constraints that can prevent the parser from generating unsuitable candidates. Second, it is robust on a given Korean sentence because the attributes for the constraints are selected based on the syntactic and lexical idiosyncrasy of Korean. Third, it is easy to acquire constraints automatically from a treebank by using a decision tree learning algorithm. The experimental results show that the parser using acquired constraints can reduce the number of overgenerated candidates up to 1/2~1/3 of candidates and it runs 2~3 times faster than the one without any constraints.

• The Journal of the Korea Contents Association
• /
• v.18 no.3
• /
• pp.41-51
• /
• 2018

This research discusses the necessity for change in the domestic digital cultural heritage education. In following, this research analyzes definition and categories of digital cultural heritage education alongside with several case studies of global institutions and their characteristics. Throughout the analysis, this research suggests a direction of domestic digital cultural heriage which has limitations. Currently domestic use of digital cultural heritage education is currently limited to applying digital technology. Analysing literature review and case studies, this research found that digital cultural heritage education can make learners be mature in perspective of historical thinking and digital literacy simultaneously. In other words, digital cultural heritage education should not aim at pursuing education via digital platform simply, but rather fundamental cultural heritage education based on understanding of digital technology and future trend of education such as informal learning. Throughout the analysis of current cases and suggestion for future direction, the research aims at being a fundamental study of digital cultural heritage.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.4
• /
• pp.427-431
• /
• 2010

Multidimensional scaling (MDS) is a widely used method for dimensionality reduction, of which purpose is to represent high-dimensional data in a low-dimensional space while preserving distances among objects as much as possible. MDS has mainly been applied to data visualization and feature selection. Among various MDS methods, the classical MDS is not readily applicable to data which has large numbers of objects, on normal desktop computers due to its computational complexity. More precisely, it needs to solve eigenpair problems on dissimilarity matrices based on Euclidean distance. Thus, running time and required memory of the classical MDS highly increase as n (the number of objects) grows up, restricting its use in large-scale domains. In this paper, we propose an efficient approximation algorithm for the classical MDS based on divide-and-conquer and CUDA. Through a set of experiments, we show that our approach is highly efficient and effective for analysis and visualization of data consisting of several thousands of objects.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.34-40
• /
• 2018

This paper presents a new method to estimate the pose of a moving object accurately using a monocular camera and a low-end GPS+IMU sensor system. For this goal, we adopted a deep neural network for the semantic segmentation of input images and compared the results with a semantic map of a neighborhood. In this map matching, we use weight tables to deal with label inconsistency effectively. Signals from a low-end GPS+IMU sensor system are used to limit search spaces and minimize the proposed function. For the evaluation, we added noise to the signals from a high-end GPS-IMU system. The results show that the pose can be recovered from the noisy signals. We also show that the proposed method is effective in handling non-open-sky situations.

• The korean journal of orthodontics
• /
• v.41 no.2
• /
• pp.138-146
• /
• 2011

The purpose of this article is to introduce a new virtual orthodontic treatment (VOT) system, which can be used to construct three-dimensional (3D) virtual models, establish a 3D virtual setup, enable the placement of the virtual brackets at the predetermined position, and fabricate the transfer jig with a customized bracket base for indirect bonding (IDB) using the stereolithographic technique. A 26-year-old woman presented with anterior openbite, crowding in the upper and lower arches, and narrow and tapered upper arch, despite having an acceptable profile and balanced facial proportion. The treatment plan was rapid palatal expansion (RPE) without extraction. After 10 days of RPE, sufficient space was obtained for decrowding. After a 10-week retention period, accurate pretreatment plaster models were obtained using silicone rubber impression. IDB was performed according to the protocol of the VOT system. Crowding of the upper and lower arches was effectively resolved, and anterior openbite was corrected to normal overbite. Superimposition of the 3D virtual setup models (3D-VSM) and post-treatment 3D virtual models showed that the latter deviated only slightly from the former. Thus, the use of the VOT system helped obtain an acceptable outcome in this case of mild crowding treated without extraction. More cases should be treated using this system, and the pre- and post-treatment virtual models should be compared to obtain feedback regarding the procedure; this will support doctors and dental laboratory technicians during the learning curve.

• The Journal of Korean Institute for Practical Engineering Education
• /
• v.5 no.1
• /
• pp.52-57
• /
• 2013

Because of rapid spread of the PC, many users have been enjoying a variety of content as PC. Especially in recent years, young people has increased dramatically PC usage. Young people get more easily information using a PC. Especially they relieve their stress through online games and feel another fun of virtual reality. It is obviously a good effect that they contact IT culture with rapidly developed. But young people's perspective with world is narrow because of doing more indoor activities than outdoor. Therefore we built Spot experience voucher system using smart phone application. We hope that many young people act outdoor activities. And Our product offer hybrid device by developing HTML5-based app. Thus this app will give interest of spot-experience to young-people. So If young people use this app, they can have many experience and see diverse aspects.

• Journal of Korea Game Society
• /
• v.8 no.2
• /
• pp.25-35
• /
• 2008

Seunglamdonoli was a traditional board game played during the Chosun Dynasty. In this article, I interpret its features as a board game and discuss the possibility of turning it into a mass market game like Milton Bradley's 'The Game of Life' in the U.S. Seunglamdonoli uses the dice to determine movements around a board shaped like Korea, teaching players about important geographic locations, and traditional characters in a game that relies on strategy as well as luck. With appropriate changes such as introducing a standardized game board or digitalization for use on computers, Seunglamdonoli has potential to again become a popular pastime as well as become tool for learning about Korean history, geography, and society. Furthermore it can be adapted as an educational game for any location with minimal changes.

• The Journal of the Korea Contents Association
• /
• v.15 no.10
• /
• pp.561-569
• /
• 2015

Many start-ups have many realistic hardships in getting management diagnosis about whether their business model are properly going. For this reason, there is the need for an easy and simple method that makes it possible to conduct a strategic management through the analysis and management diagnosis of the business model. The Business Model Canvas(BMC) has been popularized as a tool to help entrepreneurs describe, design, challenge, invent and pivot their business model. This model gives a framework to describe the most important building blocks(9 blocks) of existing business. Entrepreneurs can make their own business analyses and craft their own solutions through using this model. In this study, we conducted consulting by using the BMC on the NARUATO which is a small start-up in the healthy food industry. This case study can use as a learning material for entrepreneurship education.

• The Journal of Korean Association of Computer Education
• /
• v.12 no.1
• /
• pp.57-69
• /
• 2009

Generally, teaching in computer Labs is more difficult than teaching in a normal class for teachers to give students systematic learning. One of the reasons is that the students who participate in the class tend to use the programs that are not related to the practice included in the curriculum. Therefore, the students cannot focus on the subjects that they should do. To solve this problem, there are many kinds of systems that can control the students' computers. However, they cannot help teachers to manage the students and computers due to the inconvenience of usage and the lack of functions. In this study, we analyzed the problems in the computer-practice classwork and designed a new system to support that the students can participate in the computer classes with more attention. In addition, it is offered that the computer teachers can manage the classes and the students more efficiently with this new system. For these purposes, the effects mentioned were approved before in the real lab situations. Experimental results showed that the proposed system can improve the rate of the students attention, leading them to get better grades on the achievement test.