• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06b
• /
• pp.211-213
• /
• 2006

시맨틱 웹과 에이전트 시스템을 위한 지식 기반(Knowledge Base)을 구축하기 위해 W3C의 RDF와 ISO의 토픽맵(Topic Maps)이 사용되고 있다. 이 두 표준은 표현력 상에서 중복되는 부분이 많음에도 불구하고 서로 다른 방면을 추구하였지만, 최근 W3C에서는 Task Force 팀을 구성하여 둘 사이의 상호운용성을 확보하려는 시도를 보이고 있다. 이에 따라 단순히 자원에 대한 메타 데이터를 구축하는 RDF에 semantic을 부여하는 RDF Vocabulary인 OWL과 토픽맵 간의 상호운용도 관심을 받기 시작하였다. 본 논문에서는 이러한 OWL과 토픽맵의 상호운용 가능성을 확인하기 위해 두 표준을 지원하는 각 저작 도구를 활용하여 표현력과 기능적 비교를 수행하고 이를 통하여 둘 사이에 어떠한 차이점이 있는가와 기능적인 극복을 위한 대안을 제시한다.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.15 no.2
• /
• pp.71-96
• /
• 2004

The purpose of this study is to describe major concepts related to W3C OWL and ISO Topic Maps and to provide the result of comparison and analysis regarding semantic expression power between two ontology languages. This paper is comprised of the following parts: 1) describing URI and namespace concepts that are fundamental building block of effective ontology construction; 2) offering detailed explanation of major Topic Map concepts such as topics, associations, and occurrences; 3) providing how to accomplish the second purpose of cataloging(grouping related items when displaying the search result) using Topic Map; and 4) finally explaining the difference between two ontology languages in terms of semantic expression power.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.05a
• /
• pp.1128-1135
• /
• 2003

e-Transformation of an enterprise requires the collaboration of business processes to be suited to the business participants' purpose. To realize this collaboration, business processes should be implemented as components and the system developers could be able to reuse the components for their specific purpose. The first step of this collaboration is the discovery of exact components for business processes. A dilemma, however, is the fact that there are thousands or even millions of business processes which vary from one enterprise to another. Moreover, business processes could be decomposed into multiple levels of semantics and classified into several process areas. In general, discovery of exact business processes requires understanding of widely adopted classification schemes such as CBPC, OAGIS, or SCOR. To cope with this obstacle, business process metadata should be defined and managed regardless of specific classification schemes to support effective discovery and reuse of business processes components. In this paper, a methodology to discover business process components published in different semantic levels is proposed. The proposed methodology represents the metadata of business process components as topic maps stored in a registry and utilizes the powerful features of topic maps for process discovery. TM4J, an open-source topic map engine, is modified to support concept matching and navigation. With the implemented tool, application system developers can discover and publish the business process components effectively.

• Journal of Broadcast Engineering
• /
• v.28 no.2
• /
• pp.230-237
• /
• 2023

Self-driving is a key technology of the fourth industry and can be applied to various places such as cars, drones, cars, and robots. Among them, localiztion is one of the key technologies for implementing autonomous driving as a technology that identifies the location of objects or users using GPS, sensors, and maps. Locilization can be made using GPS or LIDAR, but it is very expensive and heavy equipment must be mounted, and precise location estimation is difficult for places with radio interference such as underground or tunnels. In this paper, to compensate for this, we proposes an image retrieval using attention module and image segmentation maps using color images acquired with low-cost vision cameras as an input.

• Korean Journal of Remote Sensing
• /
• v.39 no.3
• /
• pp.269-282
• /
• 2023

The purpose of this study was to construct land cover maps using a deep learning model and to select the optimal deep learning model for land cover classification by adjusting the dataset such as input image size and Stride application. Two types of deep learning models, the U-net model and the DeeplabV3+ model with an Encoder-Decoder network, were utilized. Also, the combination of the two deep learning models, which is an Ensemble model, was used in this study. The dataset utilized RapidEye satellite images as input images and the label images used Raster images based on the six categories of the land use of Intergovernmental Panel on Climate Change as true value. This study focused on the problem of the quality improvement of the dataset to enhance the accuracy of deep learning model and constructed twelve land cover maps using the combination of three deep learning models (U-net, DeeplabV3+, and Ensemble), two input image sizes (64 × 64 pixel and 256 × 256 pixel), and two Stride application rates (50% and 100%). The evaluation of the accuracy of the label images and the deep learning-based land cover maps showed that the U-net and DeeplabV3+ models had high accuracy, with overall accuracy values of approximately 87.9% and 89.8%, and kappa coefficients of over 72%. In addition, applying the Ensemble and Stride to the deep learning models resulted in a maximum increase of approximately 3% in accuracy and an improvement in the issue of boundary inconsistency, which is a problem associated with Semantic Segmentation based deep learning models.

• The KIPS Transactions:PartD
• /
• v.13D no.4 s.107
• /
• pp.525-534
• /
• 2006

Ontology specifies the knowledge in a specific domain and defines the concepts of knowledge and the relationships between concepts. It is possible to provide the service based on the semantic web through the ontology. Therefore, to specify and define the knowledge in a specific domain, it is required to generate the ontology which conceptualizes the knowledge. Accordingly, to search the information of potential customers for home-delivery marketing of post office, we design the specific domain to generate the ontology based on the semantic web in this paper. And we propose how to retrieve the information, using the generated ontology. We implement the data search robot which collects the information based on the generated ontology. Also, we confirm that the ontology and the search robot perform the information retrieval exactly.

• Journal of the Korea Safety Management & Science
• /
• v.13 no.1
• /
• pp.81-89
• /
• 2011

It is presumable that properly designed earcons given simultaneously with visual information could enhance the situation awareness of operators when they are involving in highly complicate process control activities. In this study, population stereotypes of earcons with respect to process control information were identified using 60 Korean subjects. To do this, 11 most distinctive earcons were selected from various earcons having different pitch, rhythm, and timbre. Associations between the selected earcons and 40 pairs of adjectives used to describe the state of control in process were gathered from 37 subjects using a semantic differential method. Based on the results from multivariate analyses, the 40 pairs of adjectives were aggregated into three distinctive semantic dimensions. The emotional maps of the 11 earcons matched with the semantic dimensions were presented in this study. On the basis of these results, a general guideline was suggested for designing earcons to deliver process control information.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.251-258
• /
• 2021

In this paper, we proposed an encoder-decoder model utilizing residual learning to improve the accuracy of the U-Net-based semantic segmentation method. U-Net is a deep learning-based semantic segmentation method and is mainly used in applications such as autonomous vehicles and medical image analysis. The conventional U-Net occurs loss in feature compression process due to the shallow structure of the encoder. The loss of features causes a lack of context information necessary for classifying objects and has a problem of reducing segmentation accuracy. To improve this, The proposed method efficiently extracted context information through an encoder using residual learning, which is effective in preventing feature loss and gradient vanishing problems in the conventional U-Net. Furthermore, we reduced down-sampling operations in the encoder to reduce the loss of spatial information included in the feature maps. The proposed method showed an improved segmentation result of about 12% compared to the conventional U-Net in the Cityscapes dataset experiment.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.730-733
• /
• 2004

Recently XML (eXtensible Markup Language) is becoming the standard for exchanging the documents on the web. And as the amount of information is increasing because of the development of the technique in the Internet, semantic web is becoming to appear for more exact result of information retrieval than the existing one on the web. Ontology which is the basis of the semantic web provides the basic knowledge system to express a particular knowledge. So it can show the exact result of the information retrieval. Ontology defines the particular concepts and the relationships between the concepts about specific domain and it has the hierarchy similar to the taxonomy. In this paper, we propose the generation of semi-automatic ontology based on XML documents that are interesting to many researchers as the means of knowledge expression. To construct the ontology in a particular domain, we suggest the algorithm to determine the domain. So we determined that the domain of ontology is to extract the information of movie on the web. And we used the generalized association rules, one of data mining methods, to generate the ontology, using the tag and contents of XML documents. And XTM (XML Topic Maps), ISO Standard, is used to construct the ontology as an ontology language. The advantage of this method is that because we construct the ontology based on the terms frequently used documents related in the domain, it is useful to query and retrieve the related domain.

• Journal of the Korea Safety Management & Science
• /
• v.6 no.1
• /
• pp.187-199
• /
• 2004

To suggest a more efficient way of delivering information for process control under computerized environment, population stereotypes of colors were tested with 57 Korean subjects. The subjects were asked to associate 11 colors salient at electronic video displays with 55 pairs of adjectives that might be used when they explain the current state of process. The levels of association were evaluated with semantic differential methods by 7 point scales. Based on the multivariate analyses, the 55 pairs of adjectives were grouped into three distinct dimensions. The emotional maps of the 11 colors with respect to each dimension were presented. The Quantitative relationships between the colors and subjective impressions were also calculated by quantification theory I. On the basis of these color associations, it was suggested a general guideline for color coding when delivering process information