• Journal of Korea Water Resources Association
• /
• v.41 no.4
• /
• pp.413-422
• /
• 2008

It is essential to locally adjust the Hargreaves parameter for estimating reference evapotranspiration with short data as a substitute of Penman-Monteith equation. In this study, evaluation of daily-based reference evapotranspiration is computed with Hargreaves equation. in Gyeonggi bay area including Ganghwa, Incheon, Suwon, Seosan, and Cheonan station for the time period of 1997-2004. Hargreaves coefficient is adjusted to give the best fit with Penman-Monteith evapotranspiration, being regarded as a reference. Then, the preferred parameters are validated for the same stations for the time period of 2005-2006. The optimization-based correction in calibration for 1997-2004 shows improved performance of the Hargreaves equation, giving 0.68-0.77 to 0.92-0.98 in Nash-Sutcliffe coefficient of efficiency (NSC) and 14.63-23.30 to 5.23-11.75 in RMSE. The validation for 2005-2006 shows improved performance of the Hargreaves equation, giving 0.43-0.85 to 0.93-0.97 in NSC and 14.43-26.81 to 6.48-9.09 in RMSE.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.259-266
• /
• 2020

Many developments have been steadily carried out by researchers with applying knowledge-based expert system or machine learning algorithms to the financial field. In particular, it is now common to perform knowledge based system trading in using stock prices. Recently, deep learning technologies have been applied to real fields of stock trading marketplace as GPU performance and large scaled data have been supported enough. Especially, LSTM has been tried to apply to stock price prediction because of its compatibility for time series data. In this paper, we implement stock price prediction using LSTM. In modeling of LSTM, we propose a fitness combination of model parameters and activation functions for best performance. Specifically, we propose suitable selection methods of initializers of weights and bias, regularizers to avoid over-fitting, activation functions and optimization methods. We also compare model performances according to the different selections of the above important modeling considering factors on the real-world stock price data of global major companies. Finally, our experimental work brings a fitness method of applying LSTM model to stock price prediction.

• Journal of the Korean Geotechnical Society
• /
• v.18 no.2
• /
• pp.51-64
• /
• 2002

Observational results of ground movement during the construction were very different from those predicted during the analysis of design step because of the uncertainty of the numerical analysis modelling, the soil parameter, and the condition of a construction field, etc., however accurately numerical analysis method was applied for prediction of ground movement per the excavation step. Therefore, the management system through the construction field measurement should be achieved for grasping the situation during the excavation. Until now, the measurement system restricted by 'Absolute Value Management system'analyzing only the stability of present step has been executed. So, it was difficult to expect the prediction of ground movement fur the next excavation step. In this situation, this study developed 'The Management system TOMAS-EXCAV'consisted of 'Absolute value management system'analyzing the stability of present step and 'Prediction management system'expecting the ground movement of next excavation step and analyzing the stability of next excavation step by 'Back Analysis'. TOMAS-EXCAV could be applied to all the uncertainty of earth retaining structures analysis by connecting 'Forward analysis program'and 'Back analysis program'and optimizing the main design variables using SQP-MMFD optimization method through measurement results. The applicability of TOMAS-EXCAV was confirmed by back analysis selecting two earth retains construction fields.

• The Journal of Engineering Research
• /
• v.3 no.1
• /
• pp.65-73
• /
• 1998

One approach to improved image restoration methods has been the incorporation of additional source information via Gibbs priors that assume a source that is piecewise smooth. A natural Gibbs prior for expressing such constraints is an energy function defined on binary valued line processes as well as source intensities. However, the estimation of both continuous variables and binary variables is known to be a difficult problem. In this work, we consider the application of the deterministic annealing method. Unlike other methods, the deterministic annealing method offers a principled and efficient means of handling the problems associated with mixed continuous and binary variable objectives. The application of the deterministic annealing method results in a sequence of objective functions (defined only on the continuous variables) whose sequence of solutions approaches that of the original mixed variable objective function. The sequence is indexed by a control parameter (the temperature). The energy functions at high temperatures are smooth approximations of the energy functions at lower temperatures. Consequently, it is easier to minimize the energy functions at high temperatures and then track the minimum through the variation of the temperature. This is the essence of a continuation method. We show experimental results, which demonstrate the efficacy of the continuation method applied to a Bayesian restoration model.

• Smart Structures and Systems
• /
• v.26 no.5
• /
• pp.575-589
• /
• 2020

For vibration control of stay cables in cable-stayed bridges, viscous dampers are frequently used, and they are regularly installed between the cable and the bridge deck. In practice, neoprene rubber bushings (or of other types) are also widely installed inside the cable guide pipe, mainly for reducing the bending stresses of the cable near its anchorages. Therefore, it is important to understand the effect of the bushings on the performance of the external damper. Besides, for long cables, external dampers installed at a single position near a cable end can no longer provide enough damping due to the sag effect and the limited installation distance. It is thus of interest to improve cable damping by additionally installing dampers inside the guide pipe. This paper hence studies the combined effects of an external damper and an internal damper (which can also model the bushings) on a stay cable. The internal damper is assumed to be a High Damping Rubber (HDR) damper, and the external damper is considered to be a viscous damper with intrinsic stiffness, and the cable sag is also considered. Both the cases when the two dampers are installed close to one cable end and respectively close to the two cable ends are studied. Asymptotic design formulas are derived for both cases considering that the dampers are close to the cable ends. It is shown that when the two dampers are placed close to different cable ends, their combined damping effects are approximately the sum of their separate contributions, regardless of small cable sag and damper intrinsic stiffness. When the two dampers are installed close to the same end, maximum damping that can be achieved by the external damper is generally degraded, regardless of properties of the HDR damper. Field tests on an existing cable-stayed bridge have further validated the influence of the internal damper on the performance of the external damper. The results suggest that the HDR is optimally placed in the guide pipe of the cable-pylon anchorage when installing viscous dampers at one position is insufficient. When an HDR damper or the bushing has to be installed near the external damper, their combined damping effects need to be evaluated using the presented methods.

• Journal of Korea Multimedia Society
• /
• v.5 no.5
• /
• pp.512-522
• /
• 2002

In this paper, we propose a hybrid method which is mixed with frame selection and weighting model rank method, based on GMM(gaussian mixture model), for real-time text-independent speaker recognition system. In the system, maximum likelihood estimation was used for GMM parameter optimization, and maximum likelihood was used for recognition basically Proposed hybrid method has two steps. First, likelihood score was calculated with speaker models and test data at frame level, and the difference is calculated between the biggest likelihood value and second. And then, the frame is selected if the difference is bigger than threshold. The second, instead of calculated likelihood, weighting value is used for calculating total score at each selected frame. Cepstrum coefficient and regressive coefficient were used as feature parameters, and the database for test and training consists of several data which are collected at different time, and data for experience are selected randomly In experiments, we applied each method to baseline system, and tested. In speaker recognition experiments, proposed hybrid method has an average of 4% higher recognition accuracy than frame selection method and 1% higher than W method, implying the effectiveness of it.

• Journal of Wetlands Research
• /
• v.14 no.4
• /
• pp.519-535
• /
• 2012

In order to establish a rainfall-runoff model, calibration of hydrological parameters for the model is very important. Especially, Curve Number(CN), estimated by NRCS method, is a main factor to apply unit hydrograph theory to calculation of peak discharge. For using NRCS method, it is needed selecting AMC because CN is strongly connected with that. In this study, we focus our concern on finding a applicable standard for selecting AMC for CN. For this, three dams which are Boryeong, Habchon, Namgang are selected as target basins to use observed data including rainfall and dam inflow. As a result of this research, it is found that CN must be included as a calibrated parameter to calculate effective rainfall for the rainfall-runoff model. Also, it is preferred to use PWRMSE of HEC-HMS program as a objective function for optimizing hydrological parameters. From the analyzing result of variation of AMC for peak discharge, it is recommended to apply AMC-III to estimation of CN for calculating effective rainfall of design hydrograph.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.657-664
• /
• 2003

Reliable tracking of moving humans is essential to motion estimation, video surveillance and human-computer interface. This paper presents a new approach to human motion tracking that combines appearance-based and model-based techniques. Monocular color video is processed at both pixel level and object level. At the pixel level, a Gaussian mixture model is used to train and classily individual pixel colors. At the object level, a 3D human body model projected on a 2D image plane is used to fit the image data. Our method does not use inverse kinematics due to the singularity problem. While many others use stochastic sampling for model-based motion tracking, our method is purely dependent on nonlinear programming. We convert the human motion tracking problem into a nonlinear programming problem. A cost function for parameter optimization is used to estimate the degree of the overlapping between the foreground input image silhouette and a projected 3D model body silhouette. The overlapping is computed using computational geometry by converting a set of pixels from the image domain to a polygon in the real projection plane domain. Our method is used to recognize various human motions. Motion tracking results from video sequences are very encouraging.

• Clean Technology
• /
• v.24 no.3
• /
• pp.239-248
• /
• 2018

In this study, pervaporation experiments of water, ethanol and IPA (Isopropyl alcohol) single components and water/ethanol, water/IPA mixtures were carried out using zeolite 4A membranes developed by Fine Tech Co. Ltd. Those membranes were fabricated by hydrothermal synthesis (growth in hydrothermal condition) after uniformly dispersing the zeolite seeds on the tubular alumina supports. They have a pore size of about $4{\AA}$ by ion exchange of $Na^+$ to the LTA structure with Si/Al ratio of 1.0, and shows strong hydrophilic property. Physical characteristics of prepared membranes were evaluated by using SEM (surface morphology), porosimetry (macro- or meso- pore analysis), BET (micropore analysis), and load tester (compressive strength). Pervaporation experiments with various temperature and concentration conditions confirmed that the zeolite 4A membrane can selectively separate water from ethanol and IPA. Water/ethanol separation factor was over 3,000 and water/IPA separation factor was over 1,500 (50 : 50 wt%, initial feed concentration). Pervaporation behaviors of single components and binary mixtures were predicted using ACM (activity coefficient model), GMS (generalized Maxwell Stefan) model and DGM (Dusty Gas Model). The adsorption and diffusion coefficients of the zeolite top layer were obtained by parameter estimation using GA (Genetic Algorithm, stochastic optimization method). All the calculations were carried out using MATLAB 2018a version.

• The Korean Journal of Food And Nutrition
• /
• v.29 no.3
• /
• pp.371-381
• /
• 2016

The present study investigated the effects of processing parameters such as time (10, 20, 30, 40 min), pressure (25, 50, 75, 100 MPa), and the salinity of brine (0~10%(w/v)) on jacopever (Sebastes schlegeli Hilgendorf) in order to establish optimization of the three factors using a high hydrostatic pressure (HHP) machine. To do so, it analyzed the quality characteristics of volatile basic nitrogen (VBN), trimethylamine (TMA), total bacterial counts, dynamic viscoelasticities, and differential scanning calorimetry (DSC) properties. First, when the time increased to 40 mins, by 10 min intervals, the total bacterial counts in HHP groups under $25^{\circ}C$, 100 MPa, and 4%(w/v) brine were significantly decreased except for the first 10 min in comparison to the control group. In regards to DSC properties, the onset temperature ($T_O$) of the first endothermal curve was significantly reduced. Second, when the pressure level increased up to 100 MPa by 25 MPa increments, the total bacterial counts in the HHP samples significantly decreased for 20 min at 50 MPa or higher. As the pressure increased, G', G" and the slope of tan ${\delta}$ decreased (except for 50 MPa). Third, in regards to the salinities of brine, when the HHP processing was treated at 100 MPa, $25^{\circ}C$ for 20 min, the total bacterial counts of all the HHP groups significantly decreased in comparison to those of the control group. A significant difference was found in the enthalpy of the second endothermic curve in the 6~10%(w/v) (except 7%(w/v)) HHP groups. Therefore, the salinity of the immersion water under the HHP condition was appropriate when it was lower than 6%(w/v). The present study demonstrated that the optimum parameter condition according to/under the condition of the microbial inhibition and economic effects using an HHP would be the reaction time for 20 min, reaction pressure at 100 MPa, and the salinity of 4%(w/v) brine.