• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.6
• /
• pp.235-242
• /
• 2021

In this work, we develop a Korean dependency parser based on a stack-pointer network that consists of a pointer network and an internal stack. The parser has an encoder and decoder and builds a dependency tree for an input sentence in a depth-first manner. The encoder of the parser encodes an input sentence, and the decoder selects a child for the word at the top of the stack at each step. Since the parser has the internal stack where a search path is stored, the parser can utilize information of previously derived subtrees when selecting a child node. Previous studies used only a grandparent and the most recently visited sibling without considering a subtree structure. In this paper, we introduce graph attention networks that can represent a previously derived subtree. Then we modify our parser based on the stack-pointer network to utilize subtree information produced by the graph attention networks. After training the dependency parser using Sejong and Everyone's corpus, we evaluate the parser's performance. Experimental results show that the proposed parser achieves better performance than the previous approaches at sentence-level accuracies when adopting 2-depth graph attention networks.

• Convergence Security Journal
• /
• v.23 no.2
• /
• pp.47-54
• /
• 2023

The global popularity of K-content(Korean Wave) has led to a continuous increase in copyright infringement cases involving domestic works, not only within the country but also overseas. In response to this trend, there is active research on technologies for detecting illegal distribution sites of domestic copyrighted materials, with recent studies utilizing the characteristics of domestic illegal distribution sites that often include a significant number of advertising banners. However, the application of detection techniques similar to those used domestically is limited for overseas illegal distribution sites. These sites may not include advertising banners or may have significantly fewer ads compared to domestic sites, making the application of detection technologies used domestically challenging. In this study, we propose a detection technique based on the similarity comparison of links and text trees, leveraging the characteristic of including illegal sharing posts and images of copyrighted materials in a similar hierarchical structure. Additionally, to accurately compare the similarity of large-scale trees composed of a massive number of links, we utilize Graph Neural Network (GNN). The experiments conducted in this study demonstrated a high accuracy rate of over 95% in classifying regular sites and sites involved in the illegal distribution of copyrighted materials. Applying this algorithm to automate the detection of illegal distribution sites is expected to enable swift responses to copyright infringements.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.9A
• /
• pp.1434-1441
• /
• 1999

This paper presents an equivalent circuit of the hairpin line filter for accurate analysis and design. Its validity was verified by computer simulations and filter design experiments. Though the various design equations for a hairpin line filter have been proposed, there has not been a practically simplified equivalent circuit because it is hard to effectively represent interconnection effects between non-adjacent elements. In this paper, all the open ports of the hairpin line filter circuit are changed to the short ports using circuit duality, and the resulting circuits are transformed to graph model. The further simplified circuit model is obtained from boundary conditions, and then the final equivalent circuit of the hairpin line filter is derived in a dual structure of the filter.

• The Journal of Korean Association of Computer Education
• /
• v.3 no.1
• /
• pp.51-63
• /
• 2000

All learners can selection of their work through hypermedia technology in the area provided by usual WBI. Also, it provides learner with individual teaching-learning environment and estimation. RC2 System has the fundamental client/server model, and provides the learning, evaluation algorithms based on the LCPG(Learning Contents Problem Graph) model, the dynamic re-learning mechanism in according to the property of individual. Moreover, it support learning editor to provide interface, which is convenient for teacher, Courseware writer, on the Web

• Journal of KIISE:Databases
• /
• v.28 no.4
• /
• pp.723-731
• /
• 2001

As XML has become and emerging standard for information exchange on the World Wide Web it has gained attention in database communities of extract information from XML seen as a database model. Data in XML can be mapped to semistructured dta model based on edge-labeled graph and queries can be processed against it Here we propose new query optimization techniques using DTDs(Document Type Definitions) which have the schema information about XML data. Our techniques reduce traditional index techniques Also, as they preserve source database structure, they can process many kinds of complex queries. we implemented our techniques and provided preliminary performance results.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.6
• /
• pp.41-51
• /
• 2006

Educators have recognized the usefulness of the e-BBS(electronic-Bulletin Board System) as an asynchronous communication medium for collaborative learning. However, theoretical outcomes to understand the structural analysis of thc e-BBS are not adequate enough. As a consequence, we are left with inadequate supportive tools to understand complex communication phenomena and to assist teachers to guide students to educational purposes. This can cause teachers to have a laissez-faire approach using BBS as a communication medium for education due to the lack of understanding the structural and overall situation. To address this issue, this paper presents a theoretical foundation to help understand the structure of discussion activities via the e-BBS and then presents a computational model, based on the structural analysis, for the behavioral analysis of participants. The formal representation of bi-directional discussion activities is realized by devising two graphs - the reply graph and the connection graph. Various measurements and statistics for the analysis are presented in the paper. To clarify the analysis, we classify the results produced through the analysis of discussion activities and participants' behaviors.

• Steel and Composite Structures
• /
• v.23 no.3
• /
• pp.273-283
• /
• 2017

In this paper, it is aimed to present a detail investigation related to structural behavior of laterally unrestrained steel cantilever roof of tribune with slender cross section. The structure is located in Tutak town in $A{\breve{g}}r{{\i}}$ and collapsed on October 25, 2015 at eastern part of Turkey is considered as a case study. This mild sloped roof structure was built from a variable I beam, and supported on steel columns of 5.5 m height covering totally $240m^2$ closed area in plan. The roof of tribune collapsed completely without any indication during first snowfall after construction at midnight a winter day, fortunately before the opening hours. The meteorological records and observations of local persons are combined together to estimate the intensity of snow load in the region and it is compared with the code specified values. Also, the wide/thickness and height/thickness ratios for flange and web are evaluated according to the design codes. Three dimensional finite element model of the existing steel tribune roof is generated considering project drawings and site investigations using commercially available software ANSYS. The displacements, principal stresses and strains along to the cantilever length and column height are given as contour diagrams and graph format. In addition to site investigation, the numerical and analytical works conducted in this study indicate that the unequivocal reasons of the collapse are overloading action of snow load intensity, some mistakes made in the design of steel cantilever beams, insufficient strength and rigidity of the main structural elements, and construction workmanship errors.

• Journal of The Korean Digital Architecture Interior Association
• /
• v.9 no.3
• /
• pp.95-102
• /
• 2009

An architectural space can be considered a life form that interconnects a number of architectural elements such as the humans who live in it. It is difficult to understand and evaluate the complexity of the interrelation between each element, but there have been various attempts to understand and evaluate this architectural space. The Space Syntax that emerged in 1980s has been studied and used more frequently than other methods. Space Syntax is the space analysis tool that analyzes the physical structure of space and represents it as a graph. Space syntax enables its various applications in space analysis by quantifying each spatial property of a whole structure, analyzing it systemically and objectively based on mathematical logic, and representing the results as a quantitative value. Integration of Space Syntax, a widely used index, reflects human behavior in spatial configuration. Meanwhile, there have been various studies in the field of architectural environmental psychology about the relationships between space and human behavior by applying behavioral science to architectural plan. One of the most widely used one is spatial behavior simulation which uses models and simulates the behavioral characteristics to anticipate practical situations and investigate the behavior related spatial problems. In this study, which focuses on the accessibility of the space syntax model, the usefulness of space will be analyzed through the simulation of human behavior that moves through each space. Furthermore, the validity of index will be verified by displaying several examples and compared with integration in space syntax, which represents the usefulness of space.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.163-170
• /
• 2023

This paper introduces the semantic modeling technology for autonomous control of manufacturing facilities and status definition algorithm. With the development of digital twin technology and various ICT technologies of the smart factory, a new production management model is being built in the manufacturing industry. Based on the advanced smart manufacturing technology, the status determination algorithm was presented as a methodology to quickly identify and respond to problems with autonomous control and facilities in the factory. But the existing status determination algorithm informs the user or administrator of error information through the grid map and is presented as a model for coping with it. However, the advancement and direction of smart manufacturing technology is diversifying into flexible production and production tailored to consumer needs. Accordingly, in this paper, a technology that can design and build a factory using a semantic-based Linked List data structure and provide only necessary information to users or managers through graph-based information is introduced to improve management efficiency. This methodology can be used as a structure suitable for flexible production and small-volume production of various types.

• Journal of KIISE:Databases
• /
• v.27 no.2
• /
• pp.227-237
• /
• 2000

A Web database System is a large-scaled multimedia application system that has multimedia processing facilities and cooperates with relational/Object-Oriented DBMS. Conventional hypertext modeling methods and DB gateway have limitations for Web database because of their restricted versatile presentation abilities and inefficient concurrency control caused by bottleneck in cooperation processing. Thus, we suggest a Dynamic Navigation Model & Virtual Graph Structure. The Dynamic Navigation Model supports implicit query processing and dynamic creation of navigation spaces, and introduce node-link creation rule considering navigation styles. We propose a mapping methodology between the suggested hypertext model and the relational data model, and suggest a dynamic allocation scheduling technique for query processing server based on weighted value. We show that the proposed technique enhances the retrieval performance of Web database systems in processing complex queries concurrently.