• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.9
• /
• pp.1865-1872
• /
• 2009

This study suggests a method for extending XMDR to integrate and search legacy system. This extension blends MSO(Meta Semantic Ontology) for the management of metadata, ML(Meta Location) for the management of location information, and Topic Map which is the standard language used to represent semantic web. This study refers to it as TMDR(Topic Map MetaData Registry). As an intelligent layer, Topic Map functions like an index. However, if the data frequently changes, the efficiency of Topic Map may drop. To solve this problem, the proposed system represents the relation among metadata, the relation among real data, and the relation between metadata and real data as Topic Map. The represented Topic Map proposes a method to reduce the changing relation among real data caused by the relation among metadata.

• Annual Conference on Human and Language Technology
• /
• 2015.10a
• /
• pp.198-201
• /
• 2015

의미역 결정은 문장의 서술어와 그 서술어에 속하는 논항들 사이의 의미관계를 결정하는 문제이다. 본 논문에서는 UPropBank 격틀 사전과 UWordMap의 용언의 하위 범주 정보를 이용하여 의미역을 부착하였다. 실험 결과 80.125%의 정확률로 의미역을 부착하는 성능을 보였다.

• Journal of Korea Multimedia Society
• /
• v.13 no.5
• /
• pp.730-739
• /
• 2010

One of core technology in Web 2.0 is tagging, which is applied to multimedia data such as web document of blog, image and video etc widely. But unlike expectation that the tags will be reused in information retrieval and then maximize the retrieval efficiency, unacceptable retrieval results appear owing to toot limitation of tag. In this paper, in the base of preceding research about image retrieval through tag clustering, we design and implement a topic map generation system which is a semantic knowledge system. Finally, tag information in cluster were generated automatically with topics of topic map. The generated topics of topic map are endowed with mean relationship by use of WordNet. Also the topics are endowed with occurrence information suitable for topic pair, and then a topic map with semantic knowledge system can be generated. As the result, the topic map preposed in this paper can be used in not only user's information retrieval demand with semantic navigation but alse convenient and abundant information service.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.609-610
• /
• 2006

This paper introduces a methodology for construction of ontology-based product knowledge Map. For CPC(Collaborative Product Commerce) environment, engineering application of ontology has been studied . However, there are no generic and comprehensive methodologies for ontology construction yet because of such problems: dependency on experience of ontologist and domain experts and insufficiency of detail stages or rules. To solve those problems, we propose a methodology to construct ontology from engineering documents in semi-automatic. We use middle-out strategy and term's axioms, sub-definitions, to build ontology map. 5-turple ontology structure, semantic network and First order logic (FOL) are used for ontology definition in this study.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.834-851
• /
• 2017

The amount of sources of information available on the web using ontologies as support continues to increase and is often heterogeneous and distributed. Ontology alignment is the solution to ensure semantic interoperability. In this paper, we describe a new ontology alignment approach, which consists of combining structure-based and reasoning-based approaches in order to discover new semantic correspondences between entities of different ontologies. We used the biblio test of the benchmark series and anatomy series of the Ontology Alignment Evaluation Initiative (OAEI) 2012 evaluation campaign to evaluate the performance of our approach. We compared our approach successively with LogMap and YAM++ systems. We also analyzed the contribution of our method compared to structural and semantic methods. The results obtained show that our performance provides good performance. Indeed, these results are better than those of the LogMap system in terms of precision, recall, and F-measure. Our approach has also been proven to be more relevant than YAM++ for certain types of ontologies and significantly improves the structure-based and reasoningbased methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.1996-2015
• /
• 2023

High-definition (HD) maps can provide precise road information that enables an autonomous driving system to effectively navigate a vehicle. Recent research has focused on leveraging semantic segmentation to achieve automatic annotation of HD maps. However, the existing methods suffer from low recognition accuracy in automatic driving scenarios, leading to inefficient annotation processes. In this paper, we propose a novel semantic segmentation method for automatic HD map annotation. Our approach introduces a new encoder, known as the convolutional transformer hybrid encoder, to enhance the model's feature extraction capabilities. Additionally, we propose a multi-level fusion module that enables the model to aggregate different levels of detail and semantic information. Furthermore, we present a novel decoupled boundary joint decoder to improve the model's ability to handle the boundary between categories. To evaluate our method, we conducted experiments using the Bird's Eye View point cloud images dataset and Cityscapes dataset. Comparative analysis against stateof-the-art methods demonstrates that our model achieves the highest performance. Specifically, our model achieves an mIoU of 56.26%, surpassing the results of SegFormer with an mIoU of 1.47%. This innovative promises to significantly enhance the efficiency of HD map automatic annotation.

• Journal of Korean Society for Geospatial Information Science
• /
• v.17 no.1
• /
• pp.121-129
• /
• 2009

Today, it is difficult to re-use and share spatial information, because of the explosive growth of heterogeneous information and specific characters of spatial information accumulated by diverse local agency. A spatial analysis of subsurface spatial informa-tion, one of the National Spatial Data Infrastructure, needs related spatial information such as, topographical map, geologic map, underground facility map, etc. However, current methods using standard format or spatial datawarehouse cannot consider a se-mantic hetergenity. In this paper, the layered ontology model which consists of generic concept, measuremnt scale, spatial model, and subsurface spatial information has developed. Also, the current ontology building method pertained to human experts is a expensive and time-consuming process. We have developed the MDA-based metamodel(UML Profile) of ontology that can be a easy under-standing and flexiblity of environment change. The semantic quality of devleoped ontology model has evaluated by reasoning engine, Pellet. We expect to improve a semantic sharing, and strengthen capacities for developing GIS experts system using knowledge representation ability of ontology.

• The Journal of Korean Institute of Information Technology
• /
• v.17 no.5
• /
• pp.1-12
• /
• 2019

Unlike existing Open APIs, Linked Data are made as a huge intelligent base to perform high-level SPARQL queries, and it is possible to create efficiently a new content by mashuping different information from various datasets. This paper implements a responsive web application for location-based semantic search. We mashup DBpedia, a kind of Linked Data, and GoogleMap API provided by Google, and provide a semantic browser function to confirm detail information regarding retrieved objects. Our system can be used in various access environments such as PC and mobile by applying responsive web design idea. The system implemented in this paper compares functional specifications with existing systems with similar functions. The comparison results show the superiority of our system in various aspects such as using semantic, linked-based browser, and mashup function.

• Journal of information and communication convergence engineering
• /
• v.5 no.3
• /
• pp.249-253
• /
• 2007

The Research on the ICT(Information & Communication Technology) is proposed the category to IT839 strategy by Government. Government is driving to researching on technology about IT839 Strategy. By transforming this category and research information into Semantic Web environment, it is possible to search function utilizing knowledge base and information object by use of TBox and ABox. In this regard, this study proposes technology for generation of Semantic Web Document about ICT Research Information. The ontology is constructed by using category to IT839 Strategy. The features of framework proposed in this study is to have used a skill to directly map Ontology instance and in case of inability of direct mapping, proposed a skill to establish reliable Semantic Web Document by suggesting indirect mapping skill using mechanical study. In addition, it is possible to establish low cost/high quality Semantic Web Document about ICT research information.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1000-1010
• /
• 2019

Image semantic segmentation and dehazing are key tasks in the computer vision. In recent years, researches in both tasks have achieved substantial improvements in performance with the development of Convolutional Neural Network (CNN). However, most of the previous works for semantic segmentation assume the images are captured in clear weather and show degraded performance under hazy images with low contrast and faded color. Meanwhile, dehazing aims to recover clear image given observed hazy image, which is an ill-posed problem and can be alleviated with additional information about the image. In this work, we propose a deep multi-task network for simultaneous semantic segmentation and dehazing. The proposed network takes single haze image as input and predicts dense semantic segmentation map and clear image. The visual information getting refined during the dehazing process can help the recognition task of semantic segmentation. On the other hand, semantic features obtained during the semantic segmentation process can provide cues for color priors for objects, which can help dehazing process. Experimental results demonstrate the effectiveness of the proposed multi-task approach, showing improved performance compared to the separate networks.