• Journal of KIISE
• /
• v.43 no.12
• /
• pp.1376-1384
• /
• 2016

Computers require analytic and processing capability for all possibilities of human expression in order to process sentences like human beings. Linguistic information processing thus forms the initial basis. When analyzing a sentence syntactically, it is necessary to divide the sentence into components, find obligatory arguments focusing on predicates, identify the sentence core, and understand semantic relations between the arguments and predicates. In this study, the method applied a case frame dictionary based on The Korean Standard Dictionary of The National Institute of the Korean Language; in addition, we used a CRF Model that constructed subcategorization of predicates as featured in Korean Lexical Semantic Network (UWordMap) for semantic role labeling. Automatically tagged semantic roles based on the CRF model, which established the information of words, predicates, the case-frame dictionary and hypernyms of words as features, were used. This method demonstrated higher performance in comparison with the existing method, with accuracy rate of 83.13% as compared to 81.2%, respectively.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• The KIPS Transactions:PartD
• /
• v.13D no.3 s.106
• /
• pp.299-308
• /
• 2006

As recently XML is becoming the standard of exchanging web documents and public documentations, XML data are increasing in many areas. To retrieve the information about XML documents efficiently, the semantic web based on the ontology is appearing. The existing ontology has been constructed manually and it was time and cost consuming. Therefore in this paper, we propose the semi-automatic ontology generation technique using the data mining technique, the association rules. The proposed method solves what type and how many conceptual relationships and determines the ontology domain level for the automatic ontology generation, using the data mining algorithm. Appying the association rules to the XML documents, we intend to find out the conceptual relationships to construct the ontology, finding the frequent patterns of XML tags in the XML documents. Using the conceptual ontology domain level extracted from the data mining, we implemented the semantic web based on the ontology by XML Topic Maps (XTM) and the topic map engine, TM4J.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06a
• /
• pp.325-327
• /
• 2012

스마트 홈은 단순한 가정 내 네트워크 연결이 아닌 주택(건물)내의 정보 기술 요소를 구현하는 토털 홈 정보 제어 시스템 서비스, 솔루션을 총칭한다. 현재는 언제, 어디서, 어떤 기기로건 인터넷에 접속할 수 있는 유비쿼터스(Ubiquitous) 시대이자, 개별 사물들이 인터넷에 연결되어 스스로 필요한 정보를 주고받게 될 시대가 도래함에 따라 사람들의 주요 생활공간에서도 활용도가 점차 커지는 것이다. 수시로 변화하는 상황에 적응하며 정확도가 높은 스마트 서비스의 제공을 위해서는 사용자의 의도에 부합하는 Semantic-Context 정보생성을 위한 SOM(Self-Organizing Map)추론 방식의 알고리즘과 정보의 의미화로 다양한 서비스를 지원할 수 있는 인프라 대비 최대 서비스가 요구된다. 이에 따라 본 논문에서는 스마트 홈에서 이종 가전기기들의 상황정보를 센서 데이터로부터 추출하여 사용자 맞춤형 서비스를 제공하기 위한 SOM 추론 기반의 스마트 홈을 설계한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.8
• /
• pp.1637-1646
• /
• 2009

Recently many researchers have been studying various methods for data integration. Among the integration methods that the researchers have studied, there are a method using metadata repository, and Topic Map which identifies the relationships between the data. This study suggests Meta-Topic Map to create Topic Map about search keyword by applying metadata and Topic Map, and the XMDR as a way to connect Meta-Topic Map with metadata in the legacy system. Considering the semantic relationship of user's keyword in the legacy system, the Meta-Topic Map provides the Topic Map format and generates the Topic Map about user's keyword. The XMDR performs structural integration through solving the problem of heterogeneity among metadata in the legacy system. The suggested svides isproves the interoperability among existing Relational Database constructed in the legacy system and the search efficiency and is efficient in expanding the system.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.2
• /
• pp.49-59
• /
• 2007

This paper is about an system which can perform automatic semantic annotation to actualize "Semantic Web." Since it is impossible to tag numerous documents manually in the web, it is necessary to gather large Korean web documents as training data, and extract features by using natural language techniques and a thesaurus. After doing these, we constructed concept classifiers through the SVM (support vector machine) teaming algorithm. According to the characteristics of Korean language, morphological analysis and syntax analysis were used in this system to extract feature information. Based on these analyses, the concept code is mapped with Kadokawa thesaurus, which made it possible to map similar words and phrase to one concept code, to make training vectors. This contributed to rise the recall of our system. Results of the experiment show the system has a some possibility of semantic annotation.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.45-52
• /
• 2021

In this paper, we proposed an Atrous Residual U-Net (AR-UNet) to improve the segmentation accuracy of semantic segmentation method based on U-Net. The U-Net is mainly used in fields such as medical image analysis, autonomous vehicles, and remote sensing images. The conventional U-Net lacks extracted features due to the small number of convolution layers in the encoder part. The extracted features are essential for classifying object categories, and if they are insufficient, it causes a problem of lowering the segmentation accuracy. Therefore, to improve this problem, we proposed the AR-UNet using residual learning and ASPP in the encoder. Residual learning improves feature extraction ability and is effective in preventing feature loss and vanishing gradient problems caused by continuous convolutions. In addition, ASPP enables additional feature extraction without reducing the resolution of the feature map. Experiments verified the effectiveness of the AR-UNet with Cityscapes dataset. The experimental results showed that the AR-UNet showed improved segmentation results compared to the conventional U-Net. In this way, AR-UNet can contribute to the advancement of many applications where accuracy is important.

• Journal of KIISE:Computing Practices and Letters
• /
• v.10 no.3
• /
• pp.282-291
• /
• 2004

There has been many researches in TopicMap and RDF which are approach to handle data efficiently with metadata. However, No researches has been performed to service and implement except for presentation and description. In this paper, We suggest the caching mechanism to support an efficient access of knowledgemap and practical knowledgemap service with implementation of TopicMap system. First, We propose a method to navigate Knowledgemap efficiently that includes advantage of former methods. Then, To transmit TopicMap efficiently, We suggest caching mechanism for knowledgemap. This method is that user will be able to navigate knowledgemap efficiently in the viewpoint of human, not application. Therefor the mechanism doesn't cash topics by logical or physical locality but clustering by information and characteristic value of TopicMap. Lastly, we suggest replace mechanism by using graph structure of TopicMap for efficiency of transmission.

• The Korean Journal of Archival Studies
• /
• no.19
• /
• pp.57-102
• /
• 2009

Recently, distribution of record via web and coefficient of utilization are increase. so, Archival information service using website becomes essential part of record center. The main point of archival information service by website is making record information retrieval easy. It has need of matching user's request and representation of record resources correctly to making archival information retrieval easy. Archivist and record manager have used various information representation tools from taxonomy to recent thesaurus, still, the accuracy of information retrieval has not solved. This study constructed record retrieval system based on Topic Map by modeling record resources which focusing on description metadata of the records to improve this problem. The target user of the system is general web users and its range is limited to the president related sources in the National Archives Portal Service. The procedure is as follows; 1) Design an ontology model for archival information service based on topic map which focusing on description metadata of the records. 2) Buildpractical record retrieval system with topic map that received information source list, which extracted from the National Archives Portal Service, by editor. 3) Check and assess features of record retrieval system based on topic map through user interface. Through the practice, relevance navigation to other record sources by semantic inference of description metadata is confirmed. And also, records could be built up as knowledge with result of scattered archival sources.

• The Journal of Korea Robotics Society
• /
• v.7 no.2
• /
• pp.92-100
• /
• 2012

A map of complex environment can be generated using a robot carrying sensors. However, representation of environments directly using the integration of sensor data tells only spatial existence. In order to execute high-level applications, robots need semantic knowledge of the environments. This research investigates the design of a system for recognizing objects in 3D point clouds of urban environments. The proposed system is decomposed into five steps: sequential LIDAR scan, point classification, ground detection and elimination, segmentation, and object classification. This method could classify the various objects in urban environment, such as cars, trees, buildings, posts, etc. The simple methods minimizing time-consuming process are developed to guarantee real-time performance and to perform data classification on-the-fly as data is being acquired. To evaluate performance of the proposed methods, computation time and recognition rate are analyzed. Experimental results demonstrate that the proposed algorithm has efficiency in fast understanding the semantic knowledge of a dynamic urban environment.