• Journal of the Korean Data and Information Science Society
• /
• v.7 no.1
• /
• pp.113-118
• /
• 1996

Principal component analysis(PCA) is an essential technique for data compression and feature extraction, and has been widely used in statistical data analysis, communication theory, pattern recognition, and image processing. Oja(1992) found that a linear neuron with constrained Hebbian learning rule can extract the principal component by using stochastic gradient ascent method. In practice real data often contain some outliers. These outliers will significantly deteriorate the performances of the PCA algorithms. In order to make PCA robust, Xu & Yuille(1995) applied statistical physics to the problem of robust principal component analysis(RPCA). Devlin et.al(1981) obtained principal components by using techniques such as M-estimation. The propose of this paper is to investigate from the statistical point of view how Xu & Yuille's(1995) RPCA works under the same simulation condition as in Devlin et.al(1981).

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.7
• /
• pp.157-165
• /
• 1989

To recover three dimensional information in Shape from Texture, the distorting effects of projection must be distinguished from properties of the texture on which the distortion acts. In this paper, we show an approximated maximum likelihood estimation method in which we find surface orientation of the visible surface (hemisphere) in gaussian sphere using local analysis of the texture. In addition, assuming that an orthogonal projection and a circle is an image formation system and a texel (texture element) respectively, we drive the surface orientation from the distribution of variation by means of orthogonal projection of a tangent direction which exists regularly in the arc length of a circle. We present the orientation parameters of textured surface with slant and tilt in gradient space, and also the surface normal of the resulted surface orientationas as needle map. This algorithm is applied to geographic contour (artificially generated chejudo) and synthetic texture.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.58-58
• /
• 2019

최근 기계학습기법에 대한 활발한 연구로 인하여 많은 기계학습기법들이 개발되었다. 이러한 최신기계학습기법은 기존에 사용되어온 기계학습기법과 경험식들보다 자연현상을 예측하고 재현하는데 높은 성능을 보이는 것으로 알려져 있다. 레이더 자료를 이용한 강우추정 기법으로는 ZR관계식이 널리 사용되고 있다. 이상적인 조건에서는 ZR 관계식을 이용한 레이더 강우추정이 양호한 성능을 보이나, 실제 레이더 자료를 이용한 강우추정은 이상적인 환경이 아닌 경우가 매우 많다. 이런 ZR관계식의 한계점을 보완하기 위한 방법으로 기계학습기법을 이용한 레이더 강우추정 기법들이 개발되었으나, 현재 한국의 레이더 자료를 대상으로 해서는 많은 연구가 진행되어 오지 않고 있다. 레이더 자료를 이용한 강우추정의 정확도 향상을 위해서는 최신 기계학습기법들의 레이더 강우추정 기법에 대한 적용가능성을 평가해 볼 필요성이 있다. 본 연구에서는 random forest, stochastic gradient boosted model, extreme learning machine의 강우 레이더 강우추정 기법으로의 적용성을 평가하였다. 강우추정 기법 개발 및 성능 비교를 위해서 2018년 광덕산 이중편파 레이더 자료를 이용하였다. 다양한 이중편파 매개변수 조합을 레이더 강우추정 기법의 입력변수로 적용하였다. 기존 연구의 사용되어 온 ZR관계식의 매개변수를 또한 강우사상과 이중편파 매개변수 조합을 이용하여 추정하였다. 기계학습을 적용한 레이더 강우추정 기법이 ZR관계식보다 상관계수와 제곱근오차를 기준으로 높은 강우추정 정확도를 보였다. 특히 개발된 강우추정 기법은 호우사상에서 높은 정확도를 보이는 것을 확인 할 수 있었다. 적용된 기계학습 기법 중에서는extreme learning machine이 레이더 강우추정기법 개발에 가장 적합한 것으로 나타났다.

• Geomechanics and Engineering
• /
• v.32 no.6
• /
• pp.583-600
• /
• 2023

The resilient modulus (M_R) of various pavement materials plays a significant role in the pavement design by a mechanistic-empirical method. The M_R determination is done by experimental tests that need time and money, along with special experimental tools. The present paper suggested a novel hybridized extreme gradient boosting (XGB) structure for forecasting the M_R of modified base materials subject to wet-dry cycles. The models were created by various combinations of input variables called deep learning. Input variables consist of the number of W-D cycles (WDC), the ratio of free lime to SAF (CSAFR), the ratio of maximum dry density to the optimum moisture content (DMR), confining pressure (σ₃), and deviatoric stress (σ_d). Two XGB structures were produced for the estimation aims, where determinative variables were optimized by particle swarm optimization (PSO) and black widow optimization algorithm (BWOA). According to the results' description and outputs of Taylor diagram, M1 model with the combination of WDC, CSAFR, DMR, σ₃, and σ_d is recognized as the most suitable model, with R² and RMSE values of BWOA-XGB for model M1 equal to 0.9991 and 55.19 MPa, respectively. Interestingly, the lowest value of RMSE for literature was at 116.94 MPa, while this study could gain the extremely lower RMSE owned by BWOA-XGB model at 55.198 MPa. At last, the explanations indicate the BWO algorithm's capability in determining the optimal value of XGB determinative parameters in M_R prediction procedure.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.89-98
• /
• 2005

Fingerprint segmentation and ridge orientation estimation algorithms with images from a mobile camera are proposed. The fingerprint images from a mobile camera are quite different from those from conventional sensor, called touch based sensor such as optical, capacitive, and thermal. For example, the images from a mobile camera are colored and the backgrounds or non-finger regions are very erratic depending on how the image capture time and place. Also the contrast between ridge and valley of a mobile camera image are lower than that of touch based sensor image. To segment fingerprint region, we first detect the initial region using color information and texture information. The LUT (Look Up Table) is used to model the color distribution of fingerprint images using manually segmented images and frequency information is extracted to discriminate between in focused fingerprint regions and out of focused background regions. With the detected initial region, the region growing algerian is executed to segment final fingerprint region. In fingerprint orientation estimation, the problem of gradient based method is very sensitive to outlier that occurred by scar and camera noise. To solve this problem, we propose a robust regression method that removes the outlier iteratively and effectively. In the experiments, we evaluated the result of the proposed fingerprint segmentation algerian using 600 manually segmented images and compared the orientation algorithms in terms of recognition accuracy.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.17 no.2 s.105
• /
• pp.158-164
• /
• 2006

In this paper, we proposed a new algorithm of the inverse scattering for the reconstruction of unknown dielectric scatterers using the finite-difference time-domain method and the design sensitivity analysis. We introduced the design sensitivity analysis based on the gradient information for the fast convergence of the reconstruction. By introducing the adjoint variable method for the efficient calculation, we derived the adjoint variable equation. As an optimal algorithm, we used the steepest descent method and reconstructed the dielectric targets using the iterative estimation. To verify our algorithm, we will show the numerical examples for the two-dimensional $TM^2$ cases.

• Journal of Environmental Science International
• /
• v.26 no.12
• /
• pp.1321-1331
• /
• 2017

This study reviewed the applicability of the existing flood discharge calculation method on Jeju Island Han Stream and compared this method with observation results by improving the mediating variables for the Han Stream. The results were as follows. First, when the rain-discharge status of the Han Stream was analyzed using the flood discharge calculation method of the existing design (2012), the result was smaller than the observed flood discharge and the flood hydrograph differed. The result of the flood discharge calculation corrected for the curve number based on the terrain gradient showed an improvement of 1.47 - 6.47% from the existing flood discharge, and flood discharge was improved by 4.39 - 16.67% after applying the new reached time. In addition, the sub-basin was set separately to calculate the flood discharge, which yielded an improvement of 9.92 - 32.96% from the existing method. In particular, the steepness and rainfall-discharge characteristics of Han Stream were considered in the reaching time, and the sub-basin was separated to calculate the flood discharge, which resulted in an error rate of -8.77 to 8.71%, showing a large improvement of 7.31 - 28.79% from the existing method. The flood hydrograph also showed a similar tendency.

• Journal of Korean Society of Forest Science
• /
• v.76 no.3
• /
• pp.193-199
• /
• 1987

Simple estimating method of rock drilling and blasting work size is necessary to apply as a guidance of general road plan and a cost analysis of mountain forest road construction. For this work study, 11 cycles were divided in 5km route at Hyeonnammeon Yangyang-gun and the mountain slope at every 20m interval was measured. During working days all kind of works concerned on drilling and blasting was investigated in every cycle. Depending on the simple work study results it's work size can bef estimated with high correlation between drilling length in meter and frequency percentage of mountain slope more than 70%. With total drilling length known the machinery hours, drillers and explosive quantify can be estimated by the regression with high correlation. Estimation of drilling and blasting work by mountain slope gradient in road route is proposed like table 5 with estimating value of machinery hour, drillers and explosive in granite gneiss region.

• Journal of Korean Society for Atmospheric Environment
• /
• v.23 no.6
• /
• pp.734-743
• /
• 2007

Polyurethane foam-disk passive air samplers (PAS) were deployed in a southern area of Korea for three months. The target compounds were 12 coplanar polychlorinated biphenyls (PCBs). The congener profiles measured in this study were the same as those in ambient air and emission gas from the incinerator. A gradient of the total PCBs in different regions (industrial>residential>rural) was observed, suggesting the industrial complex may be an important source of coplanar PCBs. In general, only gas-phase compounds are mainly sequestrated by PAS. In order to estimate the concentration of particle-phase PCBs, a gas/particle partition model was used. A combined result (gas+particle-phase PCBs) was compared with previous results, indicating that the level of coplanar PCBs in our study area is comparable to those in other urban sites in the world. The validation of this method for estimating the total concentration is required through additional backup studies.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.2
• /
• pp.298-305
• /
• 2010

In this paper, a new algorithm of optimal Volt/Var Control is proposed using Volt/Var control for the Distribution Automation System (DAS) with Distributed Generation (DG) based on the modeling of the distributed load and the distributed current. In the proposed, algorithm based on the modeling of the distributed load and the distributed current are estimated from constants of four terminals using the measurement of the current and power factor from a Feeder Remote Terminal Unit (FRTU) and DG data from RTU for DG. For the optimal Volt/Var Control, the gradient method is applied to find optimal solution for tap, capacity and power control of OLTC (On-Load Tap Changers), SVR (Step Voltage Regulator), PC (Power Condenser) and DG (Distributed Generation). In the case studies, the estimation and control of the voltages have been testified in a radial distribution system with DG using matlab program.