• The Journal of the Korea Contents Association
• /
• v.17 no.11
• /
• pp.389-397
• /
• 2017

Recently semantic web document is produced and added in repository in a cloud computing environment and requires an intelligent semantic agent for analytical classification of documents and information retrieval. The traditional methods of information retrieval uses keyword for query and delivers a document list returned by the search. Users carry a heavy workload for examination of contents because a former method of the information retrieval don't provide a lot of semantic similarity information. To solve these problems, we suggest a key word frequency and concept matching based semantic clustering model using hadoop and NoSQL to improve classification accuracy of the similarity. Implementation of our suggested technique in a cloud computing environment offers the ability to classify and discover similar document with improved accuracy of the classification. This suggested model is expected to be use in the semantic web retrieval system construction that can make it more flexible in retrieving proper document.

• Journal of Intelligence and Information Systems
• /
• v.10 no.1
• /
• pp.13-25
• /
• 2004

In the online shopping environment, consumers suffer from the process of selecting an optimal supplier. Although comparison shopping agent-based web sites and consumers' online community sites support the selection process, they have limitations when considering diverse and dynamic purchase conditions as a whole, which is the cause of additional consumer effort for optimal supplier selection. This study provides a decision support model with a sensitivity analysis for selecting an optimal supplier considering purchase conditions as a whole. It screens suppliers with filtering factors and provides optimal suppliers through a sensitivity analysis from a Quadratic Programming model. We implemented a prototype system and showed that it could be an effective decision support system for selecting the optimal supplier in the online shopping environment.

• Korean Journal of Veterinary Service
• /
• v.26 no.4
• /
• pp.345-359
• /
• 2003

A number of toxicants have been incriminated as a causing hepatic disease. Among many detrimental injury, alcohol has been noted for hepatitis, fatty liver, fibrosis, and hepatic cirrhosis. The purpose of this study was to develop animal model for hepatic fibrosis in pigs fed ethanol, and to search for a new anti-fibrogenic agent via this model. Twelve male Landrace pigs were divided into 3 groups of 4 animals each. Group 1, 2 and 3 were fed with active ceramic water only, ceramic water + liquid diet containing 15% ethanol and normal tap water + liquid diet containing 15% ethanol for 12 weeks, respectively. At week 12, all pigs were immediately sacrificed for collection each tissue and blood. Serologically, serum ALT and AST levels were significantly reversed in group 2, as compared to group 3. They were normal range in pigs of group 1. Microscopically, macrovesicular lipid droplets and moderate hepatocellular necrosis were evident in the tap water + ethanol fed group 3. However, the active ceramic water treated group 1 showed normal architecture. Moreover, in group 2, mild fatty changes and necrosis were observed in hepatocytes. Collagen fibers were increased in spaces surrounding periportal and interlobular connective tissues in the group 3 of tap water + ethanol, but collagen synthesis and its thickness of fibrotic septa connecting portal tracts were markedly reduced in the group 2 of ceramic water + ethanol. Myofibroblasts were detected mainly in the interlobular connective tissues of pig liver of group 3 treated ethanol and tap water. Few to no myofibroblasts were observed in groups 1 and 2. CYP2E1 was not or rarely detected in group 1 fed ceramic water. However, group 2 showed slightly activation of CYP2E1 in the area of pericentral vein, while CYP2E1 was significantly activated in group 3 fed tap water and ethanol. Based on the above data, we believe that we have developed a unique alcohol induced fibrosis model in pig, which will be useful in developing anti-fibrotic agents and drugs. Furthermore, the active ceramic water used in our study had an inhibitory and may be protective against ethanol induced hepatic toxicity and fibrosis.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.205-212
• /
• 2019

Scene graph is a kind of knowledge graph that represents both objects and their relationships found in a image. This paper proposes a 3D scene graph generation model for three-dimensional indoor environments. An 3D scene graph includes not only object types, their positions and attributes, but also three-dimensional spatial relationships between them, An 3D scene graph can be viewed as a prior knowledge base describing the given environment within that the agent will be deployed later. Therefore, 3D scene graphs can be used in many useful applications, such as visual question answering (VQA) and service robots. This proposed 3D scene graph generation model consists of four sub-networks: object detection network (ObjNet), attribute prediction network (AttNet), transfer network (TransNet), relationship prediction network (RelNet). Conducting several experiments with 3D simulated indoor environments provided by AI2-THOR, we confirmed that the proposed model shows high performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.474-476
• /
• 2021

Glioblastoma is the most common brain malignancies arising from glial cells. Early diagnosis and treatment plan establishment are important, and cancer is diagnosed mainly through T1CE imaging through injection of a contrast agent. However, the risk of injection of gadolinium-based contrast agents is increasing recently. Region segmentation that marks cancer regions in medical images plays a key role in CAD systems, and deep neural network models for synthesizing new images are also being studied. In this study, we propose a model that simultaneously learns the generation of T1CE images and segmentation of cancer regions. The performance of the proposed model is evaluated using similarity measurements including mean square error and peak signal-to-noise ratio, and shows average result values of 21 and 39 dB.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.5
• /
• pp.495-503
• /
• 2014

In recent days, a study of the intrusion detection system collecting and analyzing network data, packet or logs, has been actively performed to response the network threats in computer security fields. In particular, Bayesian network has advantage of the inference functionality which can infer with only some of provided data, so studies of the intrusion system based on Bayesian network have been conducted in the prior. However, there were some limitations to calculate high detection performance because it didn't consider the problems as like complexity of the relation among network packets or continuos input data processing. Therefore, in this paper we proposed two methodologies based on K-menas clustering to improve detection rate by reforming the problems of prior models. At first, it can be improved by sophisticatedly setting interval range of nodes based on K-means clustering. And for the second, it can be improved by calculating robust CPT through applying weighted-leaning based on K-means clustering, too. We conducted the experiments to prove performance of our proposed methodologies by comparing K_WTAN_EM applied to proposed two methodologies with prior models. As the results of experiment, the detection rate of proposed model is higher about 7.78% than existing NBN(Naive Bayesian Network) IDS model, and is higher about 5.24% than TAN(Tree Augmented Bayesian Network) IDS mode and then we could prove excellence our proposing ideas.

• Cartoon and Animation Studies
• /
• s.36
• /
• pp.121-145
• /
• 2014

Operating under the principle of user-benefit maximization and democratic user-control, cooperatives are being spot-lighted as a business model satisfying the various social, financial needs. In Korea, the Law of Cooperative was enacted as of December 2012, which has enabled the establishment of cooperatives in variety of industry fields. This study is to discuss the expected effect and validity of marketing cooperative as a solution for insufficient sales revenue in international distribution of Korean animation. The interviews with Korean animation studios found out the key problems of overseas distribution, which are; 1) lack of marketing expertise and weak organization, 2) lack of ancillary rights exploitation due to the deals based upon all rights package with the broadcasters who are not interested in ancillary business, 3) lack of localized marketing support in each territory. The solution for these problems takes large and long-term marketing investment and it is far beyond the capabilities of small Korean animation studios. Marketing cooperative can provide services not available otherwise such as in-depth market research which will help the improvement of international marketing expertise. Also. as the cooperative carries enough volume of animation catalogue, it can increase negotiation power satisfying the various needs of buyers. Also, it can provide the precise marketing support for each territory by integrating every process of value chain, from TV broadcasting, merchandising, and digital media platform. Above all, a clear benefit of marketing cooperative is that, because of its user-benefit and user-control principle, the principal-agent problem can be minimized while it maximizes the profit for member studios.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.932-939
• /
• 2009

This paper implements the graphic service template authoring tool based on the service template object model of describing the meta information of the services for early childhood education in the semantic web service environment. Our proposed system provides the robot services by constructing web services automatically and making the appropriate service plans. Moreover, it can create, append, delete, and update the service templates of URC based on STDL, and provide the graphic function on service template resources. In order to provide the user friendly environment in the service template phase, we implement the various editing environment : flow view style, grid view style, and text view style. We also provide the easy editing function by realizing abstract service block based on the robot API. Finally we can offer the intelligent and autonomous service of service agent based on semantic information.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.211-223
• /
• 2005

The current software development type is based on CBD (Component Based Development). However, it requires a new component model that can support rapid and accurate component information on the web due to the cost increase of building new components using CBD. The purposed of this paper is to promptly develop an application on the web which fulfills users' demand and to provide specific interface regarding the small scales of distributed component in business domains. The e-BCOS(e-Business Component System) is the agent system for the users to register distributed components and to search component information, which would increase reusability through the e-business component development of distributed components in business domains and help the users understand the information about the component. Moreover, XML is employed for specification which allows smooth specification sharing and delivery to satisfy users' variable demands.

• Journal of The Korea Institute of Healthcare Architecture
• /
• v.24 no.2
• /
• pp.15-25
• /
• 2018

Purpose: The important things in space plan of a screening center are improving the spatial awareness by space systemization and minimizing the examination time for customers, and reducing the required time of screening work and maximizing the capacity for the screening center. Therefore, we tried to solve the problem of improving spatial awareness and reducing the examination time by using the pedestrian based discrete event simulation at the minimum cost. Methods: We have analyzed the drawbacks and the supplement points by comparing the floor plan at the time of opening and the current floor plan. Based on the analysis, we propose an improved plan which changes the location of the examination rooms and the number of services, and we also verify the improved plan based on simulation analyses. Results: 1) Through the analyses, we derived the drawbacks of the floor plan at the time of opening, and we realized that the current floor plan reflects the drawbacks. 2) The major reasons of the long examination time are the human traffic jam and the occurrence of queues due to unreasonable allocation of services. 3) Through the discrete event simulation analyses, it was possible to specify the place of the queues manually so as to use the given space fairly. 4) Using the discrete event simulation, it was possible to reduce the examination time and to improve the spatial awareness effectively at the minimum cost. Implications: Although the proposed simulation methodology in this paper is an analysis of the existing screening center, we expect that the proposed methodology will be used to develop a more efficient architectural design process by pre-applying the method to the course of designing a screening center and finding the suitability of the proposed method with the matched number of services.