• Journal of the Korean Data and Information Science Society
• /
• v.28 no.1
• /
• pp.227-235
• /
• 2017

When the spatial information of each location is given specifically as coordinates it is popular to use the geographically weighted regression to incorporate the spatial information by assuming that the regression parameters vary spatially across locations. In this paper, we relax the linearity assumption of geographically weighted regression and propose a geographically weighted least squares-support vector machine for estimating geographically weighted mean by using the basic concept of kernel machines. Generalized cross validation function is induced for the model selection. Numerical studies with real datasets have been conducted to compare the performance of proposed method with other methods for predicting geographically weighted mean.

• Structural Monitoring and Maintenance
• /
• v.3 no.2
• /
• pp.129-144
• /
• 2016

We present a methodology to validate with monitoring data finite element models of existing concrete dams: numerical analyses are performed to assess the structural response under the effects of seasonal loading conditions, represented by hydrostatic pressure on the upstream-downstream dam surfaces and thermal variations as recorded by a thermometers network. We show that the stiffness effect of the rock foundation and the surface degradation of concrete due to aging are crucial aspects to be accounted for a correct interpretation of the real behavior. This work summarizes some general procedures developed by this research group at Politecnico di Milano on traditional static monitoring systems and two significant case studies: a buttress gravity and an arch-gravity dam.

• Communications for Statistical Applications and Methods
• /
• v.22 no.2
• /
• pp.159-172
• /
• 2015

This paper considers the problem of reconstructing an underlying signal from noisy data. This paper presents a reconstruction method based on synchrosqueezed wavelet transform recently developed for multiscale representation. Synchrosqueezed wavelet transform based on continuous wavelet transform is efficient to estimate the instantaneous frequency of each component that consist of a signal and to reconstruct components. However, an objective selection method for the optimal number of intrinsic mode type functions is required. The proposed method is obtained by coupling the synchrosqueezed wavelet transform with cross-validation scheme. Simulation studies and musical instrument sounds are used to compare the empirical performance of the proposed method with existing methods.

• YAKHAK HOEJI
• /
• v.43 no.4
• /
• pp.429-436
• /
• 1999

A simple, accurate and reproducible Capillary electrophoresis (CE) assay has been developed for the determination of baicalin, baicalein, wogonin and chrysin in Scutellaria baicalensis. Successful separation of these compounds has been obtained in 35 mM phosphate butter (pH 7.0) using a untreated fused silica capillary ($57{\;}cm{\times}75{\;}{\mutextrm{m}}$ i.d.) at $25^{\circ}C$ with the electric field of 19kV. Baicalin, baicalein wogonin and chrysin was separated and detected at 280 nm 13 min. The detection limits of CE were acceptable compared to HPLC. Reproducibilities of migration time and peak area were 0.66~1.11% (within-run), 2.18~3.38% (between-run) and 3.50~4.55% (within-run), 3.97~4.82%(between-run) at CE. The results indicate that CE could be a promising technique for quality and quantity control analysis of Scutellaria baicalensis as a validation method.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.2
• /
• pp.461-471
• /
• 2017

In this paper we propose a feature selection method identifying important features in the semivarying coefficient model. One important issue in semivarying coefficient model is how to estimate the parametric and nonparametric components. Another issue is how to identify important features in the varying and the constant effects. We propose a feature selection method able to address this issue using generalized cross validation functions of the varying coefficient least squares support vector regression (LS-SVR) and the linear LS-SVR. Numerical studies indicate that the proposed method is quite effective in identifying important features in the varying and the constant effects in the semivarying coefficient model.

• Structural Engineering and Mechanics
• /
• v.54 no.3
• /
• pp.475-489
• /
• 2015

This study presents the validation of a numerical model developed for dynamic analysis of buildings with roller seismic isolation bearings. Experimental methods allowed validation of the motion equations of a physical model of a building with and without roller bearings under base excitation. The results are presented in terms of modal parameters, frequency response functions (FRFs) and acceleration response. The agreement between numerical and experimental results proves the accuracy of the developed numerical model. Finally, the performance of the constructed seismic protection system is assessed through a parametric study.

• Journal of the Korea Safety Management & Science
• /
• v.9 no.2
• /
• pp.85-95
• /
• 2007

Because the damages of corrosion resulting from the chloride ion are very serious, many research studies have been performed to measure the penetration depth of the chloride ion. However, there is a problem with data selection obtained from collection during experiments. After careful study, it appears that the collected data are not conformed to a normal distribution. The result of this study will play a very important role, as a first step for the development and construction of a forecasting system to help determine a reliable service lifetime of marine structures.

• Journal of the Korean Data and Information Science Society
• /
• v.23 no.2
• /
• pp.385-392
• /
• 2012

Logistic regression is a well known binary classification method in the field of statistical learning. Mixed-effect regression models are widely used for the analysis of correlated data such as those found in longitudinal studies. We consider kernel extensions with semiparametric fixed effects and parametric random effects for the logistic regression. The estimation is performed through the penalized likelihood method based on kernel trick, and our focus is on the efficient computation and the effective hyperparameter selection. For the selection of optimal hyperparameters, cross-validation techniques are employed. Numerical results are then presented to indicate the performance of the proposed procedure.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.13 no.4
• /
• pp.511-519
• /
• 2010

This paper presents the modeling and validation of a pile-driver breech fatigue testing system model to replicate actual high pressure in a large caliber gun barrel. A hysteresis damping function was incorporated in the nonlinear impact force model. Test of real pile-driver breech fatigue testing system had been performed for model validation. Comparison of the experimental result and model simulation during impact were made. Numerical studies were performed to evaluate how the actual chamber pressure pattern in the live firing of gun barrel was affected by parameters' variation. Some of the parameters simulated included input velocity, damping coefficient and stiffness. As a result, a variety of actual chamber pressure pattern could be reproduced and controlled through current simulation model.

• Journal of Information Technology Services
• /
• v.11 no.1
• /
• pp.325-340
• /
• 2012

KUbiquitous city(U-City) is a recent trend in urban planning and management across the globe. Currently, several typologies were developed and presented classifying U-City services, but validation research of these typologies are scarce. In this study, efforts were made to qualitatively validate the usability and practicality of a typology of u-city services. Using 228 U-City services identified in previous studies, classifying exercises were conducted against a typology. Three experts were involved in this expert heuristic exercise, against a most popularly used and comprehensive typology of U-City services. Findings indicates that the selected typology is high on comprehensive exhaustiveness, and empirical applicability while low on mutual exclusivity, simplicity and theoretical contribution. Implications for the typology improvement are suggested followed by limitations and directions for further research.