• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.349-357
• /
• 2007

Named entities (NEs) are important in many Natural Language Processing (NLP) applications, and discovering NE-related relations in texts may be beneficial for these applications. This paper proposes a method to extract the ISA relation between a "named entity" and its category, and an IS-RELATED-TO relation between the category and its related object. Based on the pattern extraction algorithm "Person Category Extraction" (PCE), we extend it for solving our problem. Our experiments on Wall Street Journal (WSJ) corpus show promising results. We also demonstrate a possible application of these relations by utilizing them for semantic search.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2009.10a
• /
• pp.1350-1353
• /
• 2009

Conventional depth extraction in integral imaging is based on the disparity information between the elemental images. Since the disparity is measured in pixel unit, however, the extracted depth is discrete, resulting in the quantization error. Moreover, the quantization error grows as the object depth increases, which limits the accuracy of the depth extraction for distant objects. In this paper, we propose a new method for depth extraction in integral imaging using sub-pixel registration information between subimages to obtain linear and accurate depth.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.24 no.67
• /
• pp.49-60
• /
• 2001

Data warehouse(DW) manages all information in a Enterprise and also offers the specific information to users. However, it might be difficult to develope an effective DW system due to varieties in computing facilities, data base, and operating systems. The heterogeneous system environments make it harder to extract data and to provide proper information to usesr in real time. Also commonly occurred is data inconsistency of non-integrated legacy system, which requires an effective and efficient data extraction flow control as well as data cleansing. We design the integrated automatic ETT(Extraction Transformation Transportation) system to control data extraction flow and suggest implementation methodology. Detail analysis and design are given to specify the proposed ETT approach with a real implementation.

• ETRI Journal
• /
• v.41 no.5
• /
• pp.684-695
• /
• 2019

In a cloud environment, performance degradation, or even downtime, of virtual machines (VMs) usually appears gradually along with anomalous states of VMs. To better characterize the state of a VM, all possible performance metrics are collected. For such high-dimensional datasets, this article proposes a feature extraction algorithm based on unsupervised fuzzy linear discriminant analysis with kernel (UFKLDA). By introducing the kernel method, UFKLDA can not only effectively deal with non-Gaussian datasets but also implement nonlinear feature extraction. Two sets of experiments were undertaken. In discriminability experiments, this article introduces quantitative criteria to measure discriminability among all classes of samples. The results show that UFKLDA improves discriminability compared with other popular feature extraction algorithms. In detection accuracy experiments, this article computes accuracy measures of an anomaly detection algorithm (i.e., C-SVM) on the original performance metrics and extracted features. The results show that anomaly detection with features extracted by UFKLDA improves the accuracy of detection in terms of sensitivity and specificity.

• Proceedings of the Korean Society for Language and Information Conference
• /
• 2007.11a
• /
• pp.415-421
• /
• 2007

This paper proposes a convolution tree kernel-based approach for relation extraction where the parse tree is expanded with entity features such as entity type, subtype, and mention level etc. Our study indicates that not only can our method effectively capture both syntactic structure and entity information of relation instances, but also can avoid the difficulty with tuning the parameters in composite kernels. We also demonstrate that predicate verb information can be used to further improve the performance, though its enhancement is limited. Evaluation on the ACE2004 benchmark corpus shows that our system slightly outperforms both the previous best-reported feature-based and kernel-based systems.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.859-861
• /
• 2003

In order to present a space in details, it is indispensable to acquire 3D shape and texture simultaneously from the same platform. 3D shape is acquired by Laser Scanner as point cloud data, and texture is acquired by CCD sensor. Positioning data is acquired by IMU (Inertial Measurement Unit). All the sensors and equipments are assembled on a hand-trolley. In this research, a method of integrating the 3D shape and texture for automated construction of Digital Surface Model is developed. This Digital Surface Model is applied for efficient feature extraction. More detailed extraction is possible , because 3D Digital Surface Model has both 3D shape and texture information.

• Proceedings of the KSRS Conference
• /
• 2005.10a
• /
• pp.641-644
• /
• 2005

This paper introduces an Interactive Feature Extraction (!FE) approach for the registration of satellite imagery by matching extracted point and line features. !FE method contains both point extraction by cross-correlation matching of singular points and line extraction by Hough transform. The purpose of this study is to minimize user's intervention in feature extraction and easily apply the extracted features for image registration. Experiments with these imagery dataset proved the feasibility and the efficiency of the suggested method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.419-423
• /
• 2005

This paper is a research on feature extraction and comparison method of dynamic (on-line) signature verification. We suggest desirable feature information and modified DTW(Dynamic Time Warping) and describe the performance results of our enhanced dynamic signature verification system.

• Journal of Computing Science and Engineering
• /
• v.11 no.2
• /
• pp.39-48
• /
• 2017

Main content extraction of web pages is widely used in search engines, web content aggregation and mobile Internet browsing. However, a mass of irrelevant information such as advertisement, irrelevant navigation and trash information is included in web pages. Such irrelevant information reduces the efficiency of web content processing in content-based applications. The purpose of this paper is to propose an automatic main content extraction method of web pages. In this method, we use two indicators to describe characteristics of web pages: text density and hyperlink density. According to continuous distribution of similar content on a page, we use an estimation algorithm to judge if a node is a content node or a noisy node based on characteristics of the node and neighboring nodes. This algorithm enables us to filter advertisement nodes and irrelevant navigation. Experimental results on 10 news websites revealed that our algorithm could achieve a 96.34% average acceptable rate.

• KSCI Review
• /
• v.15 no.1
• /
• pp.185-190
• /
• 2007

An image retrieval system is a piece of software that searches identical or similar images based on various image-specific features. This paper proposes a trademark image retrieval system that uses image colors and forms. In the proposed system, input images are segmented into several other regions, and color distribution histograms for different regions are extracted for use as color information. The proposed system uses form information through the preprocessing process such as boundary surface extraction, centroid extraction, angular sampling and, and through calculating the sums of the distances between the centroid and the boundary surfaces, standard deviations, and the ratios between long and short axes. Like this, the color and form information extracted is used to perform retrieval through measuring similarity.