• Journal of KIISE:Software and Applications
• /
• v.37 no.6
• /
• pp.455-463
• /
• 2010

In this paper, we present an approach to sentence boundary detection for web documents that builds on statistical-based methods and uses rule-based correction. The proposed system uses the classification model learned offline using a training set of human-labeled web documents. The web documents have many word-spacing errors and frequently no punctuation mark that indicates the end of sentence boundary. As sentence boundary candidates, the proposed method considers every Ending Eomis as well as punctuation marks. We optimize engine performance by selecting the best feature, the best training data, and the best classification algorithm. For evaluation, we made two test sets; Set1 consisting of articles and blog documents and Set2 of web community documents. We use F-measure to compare results on a large variety of tasks, Detecting only periods as sentence boundary, our basis engine showed 96.5% in Set1 and 56.7% in Set2. We improved our basis engine by adapting features and the boundary search algorithm. For the final evaluation, we compared our adaptation engine with our basis engine in Set2. As a result, the adaptation engine obtained improvements over the basis engine by 39.6%. We proved the effectiveness of the proposed method in sentence boundary detection.

• Journal of the Korean Society for Railway
• /
• v.12 no.1
• /
• pp.31-38
• /
• 2009

The selection of the support system is an important design parameter in design and construction of the tunnel using the new Australian tunnel method. It is a common practice to select the support based on the rock mass grade, in which the rock mass is classified into five rock groups. The method is applicable if the characteristics of the rock mass are uniform in the direction of tunnel excavation. However, such case is seldom encountered in practice and not applicable when the properties vary along the longitudinal direction. This study performs comprehensive three dimensional finite difference analyses to investigate the ground deformation pattern for cases in which the rock mass properties change in the direction of the tunnel axis. The numerically calculated displacements at the tunnel crown show that the displacement is highly dependent on the stiffness contrast of the rock masses. The results strongly indicate the need to select the support type $0.5{\sim}1.0D$ before the rock mass boundary. The paper proposes a new guideline for selecting the support type based the results of the analyses.

• Korean Journal of Computational Design and Engineering
• /
• v.1 no.2
• /
• pp.122-132
• /
• 1996

Features are generic shapes with which engineers associate certain attributes and knowledge useful in reasoning about the product. Feature-based modeling systems support additional levels of information beyond those available in geometric modelers. The objective of this study is to develop a PC level feature-based modeling system which explicitly represents dimensions of the part. The feature-based modeler retains all the benefits of traditional B-rep. solid models, and represents the dimensions at a high level of a abstraction so that dimension driven geometry can be achieved.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1999.04a
• /
• pp.34-41
• /
• 1999

This paper is focused on numerical analysis for perforated plate with irregular section based on Kirchhoff's fundamental equations of a circular plate. The dimensions of analysis model are as following; 1) radius:100cm, 2) hole in center:20cm, 3)thickness: l0cm and variable and have a simple support in boundary. The theoretical results are compared with data obtained by the F.2.M analysis. Both data have good agreement with each other.

• Tunnel and Underground Space
• /
• v.2 no.2
• /
• pp.237-250
• /
• 1992

The cavities formed by the excavation of coal seam cause unstable within rock body, leading to large displacement around adjacent roadway. This displacement brings the closure of roadway and deformation of support. Therefore, it is necessary to understand and predict the deformation characteristics of roadway while coal seam is under excavation. In this study, the observed displacements are compared with the calculated ones through the analysis using Linear Boundary Element Mothod under the elastostatic conditions, in order to determine the virgin stress state and deformation modulus which affect the deformation characteristices.

• Journal of Mechanical Science and Technology
• /
• v.19 no.9
• /
• pp.1753-1760
• /
• 2005

The pseudo spectral method is applied to the free vibration analysis of double-span Timoshenko beams. The analysis is based on the Chebyshev polynomials. Each section of the double-span beam has its own basis functions, and the continuity conditions at the intermediate support as well as the boundary conditions are treated separately as the constraints of the basis functions. Natural frequencies are provided for different thickness-to-length ratios and for different span ratios, which agree with those of Euler-Bernoulli beams when the thickness-to-length ratio is small but deviate considerably as the thickness-to-length ratio grows larger.

• Journal of applied mathematics & informatics
• /
• v.5 no.2
• /
• pp.465-474
• /
• 1998

Results on the analytic behavior to the limiting spectral distribution of matrices of sample convariance type. studied in Marcenko and Pastur [2] are derived. using the Stieltjes transform it is shown that the limiting distrbution has a continuous derivative away from zero the derivative being analytic whenever it is positive and the behavior of it resembles the behavior of a square root function near the boundary of its support.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.2220-2223
• /
• 2003

In this paper we used Support Vector Machines(SVMs) recently proposed as the loaming method, one of Artificial Neural Network, to divide continuous speech into phonemes, an initial, medial, and final sound, and then, performed continuous speech recognition from it. Decision boundary of phoneme is determined by algorithm with maximum frequency in a short interval. Recognition process is performed by Continuous Hidden Markov Model(CHMM), and we compared it with another phoneme divided by eye-measurement. From experiment we confirmed that the method, SVMs, we proposed is more effective in an initial sound than Gaussian Mixture Models(GMMs).

• Journal of applied mathematics & informatics
• /
• v.16 no.1_2
• /
• pp.483-488
• /
• 2004

Results on the analytic behavior of the limiting spectral distribution of large dimensional random matrices, studied in Marcenko and Pastur [2], are derived. Using the Stieltjes transform, it is shown that the limiting distribution has a continuous derivative away from zero, the derivative being analytic whenever it is positive [3]. In the present paper, it is derived that the behavior of it resembles the behavior of a square root function near the boundary of its support.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1990.10a
• /
• pp.63-68
• /
• 1990

The nature of fluctuating air pressure inside building was studied by testing a building model in a wind tunnel. The model has a single room and a sin81e window opening. Various opening conditions were tested in both laminar uniform wind and turbulent boundary-layer wind. The RMS and the spectra of the fluctuating internal pressure were measured. The test results support a recent theory which predicts the behavior of internal pressure under high wind based on aerodynamic analysis.