• Journal of Internet Computing and Services
• /
• v.12 no.5
• /
• pp.73-85
• /
• 2011

Lots of valuable textual information is used to extract relations between named entities from literature. Composite kernel approach is proposed in this paper. The composite kernel approach calculates similarities based on the following information:(1) Phrase structure in convolution parse tree kernel that has shown encouraging results. (2) Predicate-argument structure patterns. In other words, the approach deals with syntactic structure as well as semantic structure using a reciprocal method. The proposed approach was evaluated using various types of test collections and it showed the better performance compared with those of previous approach using only information from syntactic structures. In addition, it showed the better performance than those of the state of the art approach.

• The KIPS Transactions:PartD
• /
• v.15D no.4
• /
• pp.541-548
• /
• 2008

Today, GIS service requires not only a simple map visualization but also geographical information of each object. However, POI service provides simply geographical naming service only because of lacking in geographical information of objects. In addition, geographical space data representation functioning that is the basis for most GIS has not been standardized yet. In this paper, it is designed that POI DB that is hierarchical and user-oriented and it is constructed that GVP(GML Viewer POI) that is the basis of GML specification to overcome difference and incompatibility of map visualization. GVP adds POI DB in a 3-Layer structure to dBase file managing the information of SHP file attributes. Therefore, POI visualization enables hierarchical search, by providing POI information in directory-type grouping. Consisting of map visualization and POI visualization, GVP regenerates attributes in the form of individual objects and responds to user events immediately.

• Journal of the Korean Society for Library and Information Science
• /
• v.50 no.2
• /
• pp.309-336
• /
• 2016

This paper introduces a relation extraction system that can be used in identifying and classifying semantic relations between biomedical entities in scientific texts using machine learning methods such as Support Vector Machines (SVM). The suggested system includes many useful functions capable of extracting various linguistic features from sentences having a pair of biomedical entities and applying them into training relation extraction models for maximizing their performance. Three globally representative collections in biomedical domains were used in the experiments which demonstrate its superiority in various biomedical domains. As a result, it is most likely that the intensive experimental study conducted in this paper will provide meaningful foundations for research on bio-text analysis based on machine learning.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.3
• /
• pp.429-442
• /
• 2020

The proportion of attacks via office documents is increasing in recent incidents. Although the security of office applications has been strengthened gradually, the attacks through the office documents are still effective due to the sophisticated use of social engineering techniques and advanced attack techniques. In this paper, we propose a method for detecting malicious OOXML(Office Open XML) documents and a framework for detection. To do this, malicious files used in the attack and benign files were collected from the malicious code repository and the search engine. By analyzing the malicious code types of collected files, we identified six "suspicious object" elements that are meaningful in determining whether they are malicious in a document. In addition, we implemented an OOXML document-based malware detection framework based on the detection method to classify the collected files and found that 98.45% of malicious filesets were detected.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.25 no.4
• /
• pp.347-354
• /
• 2007

Since large portal service providers started web services for 3D city models around the world using spatial imagery, the competition has been getting intense to provide the models with the higher quality and accuracy. The building models are the most in number among the 3D city model objects, and it takes much time and money to create realistic model due to various shapes and visual appearances of building object. The aforementioned problem is the most significant limitation for the service and the update of the 3D city model of the large area. This study proposed a method of generating realistic 3D building models with quick and economical texture mapping using multiple spatial imagery such as aerial photos or satellite images after reconstructed geometric models of buildings from building layers in digital maps. Based on the experimental results, the suggested method has effectiveness for the generation of the 3D building models using various air-borne imagery and satellite imagery quickly and economically.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.11
• /
• pp.1421-1427
• /
• 2018

Due to the rapid development of Internet-of-Things technology, different types of smart sensors are now devised and deployed widely. These smart sensors are now used in animal husbandry which was traditionally managed by the experience of farmers, such that wearable sensors for livestock, and the smart farm which is equipped with multiple sensors are utilized to increase the efficiency of livestock management. Herein, we consider a scheme in which the body temperature and the level of activity are measured by smart sensor which is attached to the neck of dairy cattle and the health condition is monitored based on collected data. Especially, we find that the estrous of dairy cattle which is one of most important metric in milk production, can be predicted with high precision using various machine learning techniques. By utilizing the proposed prediction scheme, estrous of cattle can be detected immediately and this can improve the efficiency of cattle management.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.901-904
• /
• 2014

As sensing techniques have advanced, context-aware technologies have been developed under the various domain for each different purpose. The number of services were created and are being used actually, but the services for specific spatial domain are not adequate yet. To solve this, there have been many efforts, and some of them were actually successful. Among them, the methods which used ontology-based inference were relatively reliable and appropriate for context-aware system, but not able to support contexts for individual without complex rules. In this paper, current scope of context inference is extended from user-oriented context modeling to entity-oriented. Furthermore, we used user profile and home profile to provide more specific context information of not only each individual but entity.

• The Journal of the Korea Contents Association
• /
• v.22 no.8
• /
• pp.33-43
• /
• 2022

Labeled graphs are used to represent entities, their relationships, and their structures in real data such as knowledge graphs and protein interactions. With the rapid development of IT and the explosive increase in data, there has been a need for a subgraph matching technology to provide information that the user is interested in. In this paper, we propose an approximate Top-k labeled subgraph matching scheme that considers the semantic similarity of labels and the difference in graph structure. The proposed scheme utilizes a learning model using FastText in order to consider the semantic similarity of a label. In addition, the label similarity graph(LSG) is used for approximate subgraph matching by calculating similarity values between labels in advance. Through the LSG, we can resolve the limitations of the existing schemes that subgraph expansion is possible only if the labels match exactly. It supports structural similarity for a query graph by performing searches up to 2-hop. Based on the similarity value, we provide k subgraph matching results. We conduct various performance evaluations in order to show the superiority of the proposed scheme.

• Journal of Korea Game Society
• /
• v.2 no.1
• /
• pp.42-48
• /
• 2002

Many web-based simulation environments have been proposed to create models and execute simulation through the Web. Although web-based simulation has the advantage of utilizing many computers connected to Internet, overhead of the web server and heavy traffic caused by Java RMI degrade the performance and scalability of simulation. In this paper, we design and implement web-based distributed simulator using Java for the scalability and performance. In addition, we can apply the proposed simulator to create model server and client engines in online game. We apply the proposed simulator to simulate ATM switch queueing model.

• Journal of Internet Computing and Services
• /
• v.6 no.5
• /
• pp.27-43
• /
• 2005

EAP provides authentication for each entity based on IEEE Std 802.1x Wireless lAN and RADIUS/DIAMETER protocol, and it uses certificate, dual scheme(e.g., password and token) with the authentication method. The password-based authentication scheme for authenticated key exchange is the most widely-used user authentication method due to various advantages, such as human-memorable simplicity, convenience, mobility, A specific hardware device is also unnecessary, This paper discusses user authentication via public networks and proposes the Split Password-based Authenticated Key Exchange (SPAKE), which is ideal for both authenticating users and exchanging session keys when using a subsequent secure communication over untrusted network, And then we provides EAP authentication framework EAP-SPAKE by using it.