• Journal of Korea Water Resources Association
• /
• v.54 no.spc1
• /
• pp.1143-1154
• /
• 2021

The selection of activation function has a great influence on the groundwater level prediction performance of artificial neural network (ANN) model. In this study, five activation functions were applied to ANN model for two groundwater level observation wells in the middle mountainous area of the Pyoseon watershed in Jeju Island. The results of the prediction of the groundwater level were compared and analyzed, and the optimal activation function was derived. In addition, the results of LSTM model, which is a widely used recurrent neural network model, were compared and analyzed with the results of the ANN models with each activation function. As a result, ELU and Leaky ReLU functions were derived as the optimal activation functions for the prediction of the groundwater level for observation well with relatively large fluctuations in groundwater level and for observation well with relatively small fluctuations, respectively. On the other hand, sigmoid function had the lowest predictive performance among the five activation functions for training period, and produced inappropriate results in peak and lowest groundwater level prediction. The ANN-ELU and ANN-Leaky ReLU models showed groundwater level prediction performance comparable to that of the LSTM model, and thus had sufficient potential for application. The methods and results of this study can be usefully used in other studies.

• Journal of the Korean Geotechnical Society
• /
• v.15 no.1
• /
• pp.151-160
• /
• 1999

A series of laboratory tests for the marine clay sampled under the sea of Kwangyang bay have been conducted. The main types of tests are the general index property tests, the oedometer tests and the triaxial compression tests in both undrained(CIU) and drained(CID) conditions. The clayey samples, classified as CL, CH with natural water content of 38.3~84.6% and liquidity index of 0.71~0.98, are in the normally consolidated state with O.C.R. of 1.0l~l.60. The undrained stress path from CIU tests can be normalized with isotropic consolidation pressure$(p_0)$ and equal shear strain contour is linear passing through the origin in the (q, p) plot. The undrained shear strain is found to be the only function of the stress ratio($\eta$) and linear with intercept in the ($\varepsilon/\eta,\eta$) plot. The built-up pore pressure normalized with pc is also linear with respect to $\eta$. and its slope is defined by ´C´ as a pore pressure parameter. Equations to predict the undrained stress path and the shear strain are proposed. It is proved that the proposed equations give better agreements to the measured values than the Cam-clay theories. The failure points of the stress path are located on the same C.S.L. in (q, p) plot during both CIU and CID tests, which justifies the concept of critical state theory.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.33-41
• /
• 2018

The purpose of this study is to develop more accurate and robust emotion prediction neural network (EPNN) model by combining heart rate variability (HRV) and neural network. For the sake of improving the prediction performance more reliably, the proposed EPNN model is based on various types of activation functions like hyperbolic tangent, linear, and Gaussian functions, all of which are embedded in hidden nodes to improve its performance. In order to verify the validity of the proposed EPNN model, a number of HRV metrics were calculated from 20 valid and qualified participants whose emotions were induced by using money game. To add more rigor to the experiment, the participants' valence and arousal were checked and used as output node of the EPNN. The experiment results reveal that the F-Measure for Valence and Arousal is 80% and 95%, respectively, proving that the EPNN yields very robust and well-balanced performance. The EPNN performance was compared with competing models like neural network, logistic regression, support vector machine, and random forest. The EPNN was more accurate and reliable than those of the competing models. The results of this study can be effectively applied to many types of wearable computing devices when ubiquitous digital health environment becomes feasible and permeating into our everyday lives.

• Science of Emotion and Sensibility
• /
• v.20 no.1
• /
• pp.83-94
• /
• 2017

In this study, we figured out that music modes and item types could affect people's urged decision making through a k-value which results from a delay discounting's hyperbolic function. Generally, high k-value is related to impulsive decision making. Concretely, there was a significant interaction between items and music. For the luxury item, the k-value was higher while listening to major music than minor. However, for the non-luxury item condition the k-value difference was not significant between two pieces of music. Moreover, we expected mood could be manipulated after listening to the music and mediate a difference of tendency. We used first movement as an allegro and second as an andante of Mozart piano concerto No.5 D-major and No.20 D-minor for stimuli. As a result, mode and tempo's main effects were not significant. Nevertheless, there was a significant two-way interaction. To put it concretely, the k-value of major condition was marginally higher than minor condition on allegro. However, the k-value of major condition was significantly lower than minor condition on andante. Also, depressed degree difference was significant but it was not significant as a mediator. Set depressed degree as a predict variable and future time span as a mediator, further research found future time perception partially mediated the effect that depressed degree affects impulsivity.

• Korean Journal of Optics and Photonics
• /
• v.29 no.4
• /
• pp.166-172
• /
• 2018

In this paper, we propose a new method to predict a mirror's surface deformation due to the stress of moisture release by a coating in the environment of outer space. We measured the surface deformation of circular samples 50 mm in diameter and 1.03 mm thick, using an interferometer. The results were analyzed using Zernike fringe polynomials. The coating stress caused by moisture release was calculated to be 152.7 MPa. This value was applied to an analytic model of a 1.25 mm thickness sample mirror, confirming that the change of surface deformation could be predicted within the standard deviation of the measurement result ($78.9{\pm}5.9nm$). Using this methodology, we predicted the surface deformation of 600 mm hyperbolic mirror for the Compact Advanced Satellite, which will be launched in 2019. The result is only $2.005{\mu}m$ of focal shift, leading to 2.3% degradation of modulation transfer function (MTF) at the Nyquist frequency, which satisfies the requirement.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2C
• /
• pp.71-79
• /
• 2009

This study is to develope the resilient modulus prediction model, which is the function of mean effective principal stress and axial strain, for three types of railroad trackbed materials such as crushed stone, weathered granite soil, and crushed-rock soil mixture. The model consists of the maximum Young's modulus and nonlinear values for higher strain, analogous to dynamic shear modulus. The maximum value is modeled by model parameters, $A_E$ and the power of mean effective principal stress, $n_E$. The nonlinear portion is represented by modified hyperbolic model, with the model parameters of reference strain, ${\varepsilon}_r$ and curvature coefficient, a. To assess the performance of the prediction models proposed herein, the elastic response of a test trackbed near PyeongTaek, Korea, was evaluated using a 3-D elastic multilayer computer program (GEOTRACK). The results were compared with measured elastic vertical displacement during the passages of freight and passenger trains at two locations, whose sub-ballasts were crushed stone and weathered granite soil, respectively. The calculated vertical displacements of the sub-ballasts are within the order of 0.6mm, and agree well with measured values. The prediction models are thus concluded to work properly in the preliminary investigation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.2A
• /
• pp.363-370
• /
• 2006

It is proposed that the electromechanical relation of the conductive materials with high electrical resistance may be used to estimate the current stress of prestressing tendons. To choose the best conductive material to this end, we studied the electromechanical relations of carbon fibers and metalic heat wires experimentally. The strain of those materials was controlled instead of the stress during the experiment. It is found that the relation of carbon fibers can be modelled by a parabolic(or hyperbolic) function in the early stage of deformation. However because the relation is not consistent when it is unloaded and reload, carbon fibers are not suitable for this purpose. Metallic heat wires show a consistent linear relation during loading and unloading in the elastic deformation and are suitable for this purpose. To estimate the electromechanics relation of metallic wires, we developed a simple formula based on the rigid plasticity. We propose a new kind of prestressing tendons whose stress can be monitored. As a side result of this study, we found that the electromechanical relation of carbon fibers without epoxy matrix becomes almost linear after a certain strain.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.46 no.3
• /
• pp.241-247
• /
• 2001

Boundary line method was adopted to analyze the relationships between rice yield and meteorological conditions during rice growing period. Boundary lines of yield responses to mean temperature($T_a$) and sunshine hour( $S_{h}$) and diurnal temperature range($T_r$) were well-fitted to hyperbolic functions of f($T_a$) =$$\beta$_{0t}$(1-EXP(-$$\beta$_{1t}$ $\times$ ($T_a$) ) and f( $S_{h}$)=$$\beta$_{0t}$((1-EXP($$\beta$_{1t}$$\times$ $S_{h}$)), to quadratic function of f($T_r$) =$\beta$$_{0r}$(1-($T_r$ 1r)$^2$), respectively. to take into account to, the sterility caused by low temperature during reproductive stage, cooling degree days [$T_c$ =$\Sigma$(20-$T_a$] for 30 days before heading were calculated. Boundary lines of yield responses to $T_c$ were fitted well to exponential function of f($T_c$) )=$\beta$$_{0c}$exp(-$$\beta$_{1c}$$\times$$T_c$ ). Excluding the constants of $\beta$$_{0s}$ from the boundary line functions, formed are the relative function values in the range of 0 to 1. And these were used as yield indices of the meteorological elements which indicate the degree of influence on rice yield. Assuming that the meteorological elements act multiplicatively and independently from each other, meteorological yield index (MIY) was calculated by the geometric mean of indices for each meteorological elements. MIY in each growth period showed good linear relationship with rice yield. The MIY's during 31 to 45 days after transplanting(DAT) in vegetative stage, during 30 to 16 days before heading (DBH) in reproductive stage and during 20 days after heading (DAH) in ripening stage showed greater explainablity for yield variation in each growth stage. MIY for the whole growth period was calculated by the following three methods of geometric mean of the indices for vegetative stage (MIVG), reproductive stage (HIRG) and ripening stage (HIRS). MI $Y_{I}$ was calculated by the geometric mean of meteorological indices showing the highest determination coefficient n each growth stage of rice. That is, (equation omitted) was calculated by the geometric mean of all the MIY's for all the growth periods devided into 15 to 20 days intervals from transplanting to 40 DAH. MI $Y_{III}$ was calculated by the geometric mean of MIY's for 45 days of vegetative stage (MIV $G_{0-45}$ ), 30 days of reproductive stage (MIR $G_{30-0}$) and 40 days of ripening stage (MIR $S_{0-40}$). MI $Y_{I}$, MI $Y_{II}$ and MI $Y_{III}$ showed good linear relationships with grain yield, the coefficients of determination being 0.651, 0.670 and 0.613, respectively.and 0.613, respectively.

• Korean Journal of Environmental Agriculture
• /
• v.18 no.4
• /
• pp.372-377
• /
• 1999

Objective of this research was to draw the basic criteria of the compost maturity evaluation, by assessing the stability of chemical and physical properties of the bark and piggery manure byproduct composts during the composting. Colors of the mature composts were black and dark brown for the bark and piggery manure by-product composts, respectively. Good earthy odor was detected for both by-product composts after approximately 40 days composting, by which odors of the original raw materials were disappeared. pH and EC of the mature bark: compost were stabilized at 6.5 and 1dS/m, respectively. The respective values for the piggery compost were stabilized at 7.2 and 6dS/m. Organic matter contents were decreased with time to be stabilized at about 60% at the end of composting. During composting, total N contents of the bark and piggery composts were maintained at $1.1{\sim}1.5%$, and $1.5{\sim}2.2%$, respectively. For both fertilizers, $NH_4-N$ contents were increased at the initial stage bur. decreased after the middle stages of decomposition, resulting in the increase of $NO_3-N$ contents. Total inorganic N contents were increased with time. C/N ratios of both mature composts were stabilized at $25{\sim}27$. CEC of the bark compost was increased logarithmically with time and that of mature compost was 87cmol(+)/㎏. CEC of the piggery manure compost was hyperbolic function with rime and reached at 70cmol(+)/㎏ at the mature stage. Crude fiber analysis indicated that relative contents of lignin were increased with composting by compensating for the decreases of cellulose and hemicellulose contents.