• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.20-20
• /
• 2000

Back-propagation neural network (BPNN) is the most prevalently used paradigm in modeling semiconductor manufacturing processes, which as a neuron activation function typically employs a bipolar or unipolar sigmoid function in either hidden and output layers. In this study, applicability of another linear function as a neuron activation function is investigated. The linear function was operated in combination with other sigmoid functions. Comparison revealed that a particular combination, the bipolar sigmoid function in hidden layer and the linear function in output layer, is found to be the best combination that yields the highest prediction accuracy. For BPNN with this combination, predictive performance once again optimized by incrementally adjusting the gradients respective to each function. A total of 121 combinations of gradients were examined and out of them one optimal set was determined. Predictive performance of the corresponding model were compared to non-optimized, revealing that optimized models are more accurate over non-optimized counterparts by an improvement of more than 30%. This demonstrates that the proposed gradient-optimized teaming for BPNN with a linear function in output layer is an effective means to construct plasma models. The plasma modeled is a hemispherical inductively coupled plasma, which was characterized by a 24 full factorial design. To validate models, another eight experiments were conducted. process variables that were varied in the design include source polver, pressure, position of chuck holder and chroline flow rate. Plasma attributes measured using Langmuir probe are electron density, electron temperature, and plasma potential.

• Structural Engineering and Mechanics
• /
• v.12 no.6
• /
• pp.685-698
• /
• 2001

In this paper, a general method for the automatic search for Strut-and-Tie (S&T) models representative of possible resistant mechanisms in reinforced concrete elements is proposed. The representativeness criterion here adopted is inspired to the principle of minimum strain energy and requires the consistency of the model with a reference stress field. In particular, a highly indeterminate pin-jointed framework of a given layout is generated within the assigned geometry of the concrete element and an optimum truss is found by the minimisation of a suitable objective function. Such a function allows us to search the optimum truss according to a reference stress field deduced through a F.E.A. and assumed as representative of the given continuum. The theoretical principles and the mathematical formulation of the method are firstly explained; the search for a S&T model suitable for the design of a deep beam shows the method capability in handling the reference stress path. Finally, since the analysis may consider the structure as linear-elastic or cracked and non-linear in both the component materials, it is shown how the proposed procedure allows us to verify the possibilities of activation of the design model, oriented to the serviceability condition and deduced in the linear elastic field, by following the evolution of the resistant mechanisms in the cracked non-linear field up to the structural failure.

• Journal of Information Technology Applications and Management
• /
• v.28 no.4
• /
• pp.13-20
• /
• 2021

In this paper, I was applied the life distribution following linear failure rate distribution, Lindley distribution and Burr-Hatke exponential distribution extensively used in the arena of software reliability and were associated the reliability possessions of the software using the nonhomogeneous Poisson process with finite failure. Furthermore, the average value functions of the life distribution are non-increasing form. Case of the linear failure rate distribution (exponential distribution) than other models, the smaller the estimated value estimation error in comparison with the true value. In terms of accuracy, since Burr-Hatke exponential distribution and exponential distribution model in the linear failure rate distribution have small mean square error values, Burr-Hatke exponential distribution and exponential distribution models were stared as the well-organized model. Also, the linear failure rate distribution (exponential distribution) and Burr-Hatke exponential distribution model, which can be viewed as an effectual model in terms of goodness-of-fit because the larger assessed value of the coefficient of determination than other models. Through this study, software workers can use the design of mean square error, mean value function as a elementary recommendation for discovering software failures.

• Journal of Families and Better Life
• /
• v.20 no.1
• /
• pp.45-56
• /
• 2002

The main purposes of this article are to introduce the theoretical backgrounds and empirical application methods of two different Models for the function of expenditure, and to compare the goodness-o(-fit of the two models: a single-equation model and a complete-system-of-demand-equation model. For the empirical analysis of the single-equation model, a linear formula and a double-leg formula were employed. In order to test the complete-system-of-demand-equation model empirically, the \"Linear Approximation/Almost Ideal Demand System (LA/AIDS)" was used. The independent variables were the total living expense and expenditure categories Price index. The data used in this study were obtained from the quarterly statistics of "The Annual Report on the Urban Family Income and Expenditure Survey (Dosigagyeyonbo)" and "The Annual Report on the Consumer Price Index (Sobijamulgajaryo)," for the years 1994 to 1997. The goodness-of-fit (R-square) was higher with the complete-system-of-demand-equation model than with the single-equation model for the budget share on food (excluding eating-out expenses) and for the share on cultural and recreational activities. However, there was no difference between the two models in terms of the proportion of the expenditure on automobile fuel.fuel.

• Journal of Environmental Science International
• /
• v.27 no.7
• /
• pp.509-518
• /
• 2018

Weather is the most influential factor for crop cultivation. Weather information for cultivated areas is necessary for growth and production forecasting of agricultural crops. However, there are limitations in the meteorological observations in cultivated areas because weather equipment is not installed. This study tested methods of predicting the daily mean temperature in onion fields using geostatistical models. Three models were considered: inverse distance weight method, generalized additive model, and Bayesian spatial linear model. Data were collected from the AWS (automatic weather system), ASOS (automated synoptic observing system), and an agricultural weather station between 2013 and 2016. To evaluate the prediction performance, data from AWS and ASOS were used as the modeling data, and data from the agricultural weather station were used as the validation data. It was found that the Bayesian spatial linear regression performed better than other models. Consequently, high-resolution maps of the daily mean temperature of Jeonnam were generated using all observed weather information.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.2
• /
• pp.73-82
• /
• 2017

In this research, we tried to check the applicability of a Chow test to the linear models which are generated in the process of transportation planning or traffic flow analyses. The Chow test is a very popular statistical method which is being used to see if the coefficients from two separate linear regression models are equal or not. In order to prove the effectiveness of the Chow test, we found the linear relationships between speed and density under the situations such as driving in daytime and in nighttime on a rainy day. Based on the two months of Joong-Bu Expressway traffic data, we proved that the Chow test is useful to testify the similarity between two linear regression models. And this statistical tool seems to be able to have a very important role in traffic flow analysis or in transportation planning process. Finally, we expect the Chow test be implemented even to the non-linear regression models or to the multi-variate models.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.11
• /
• pp.989-996
• /
• 2016

This paper intends to develop the rotor track and balance (RTB) algorithm using the nonlinear RTB models and a real-coded hybrid genetic algorithm. The RTB response data computed using the trim solutions with variation of the adjustment parameters have been used to build nonlinear RTB models based on the quadratic interpolation functions. Nonlinear programming problems to minimize the track deviations and the airframe vibration responses have been formulated to find optimum settings of balance weights, trim-tab deflections, and pitch-link lengths of each blade. The results are efficiently resolved using the real-coded genetic algorithm hybridized with the particle swarm optimization techniques for convergence acceleration. The nonlinear RTB models and the optimized RTB parameters have been compared with those computed using the linear models to validate the proposed techniques. The results showed that the nonlinear models lead to more accurate models and reduced RTB responses than the linear counterpart.

• Journal of Korean Dental Science
• /
• v.15 no.1
• /
• pp.19-30
• /
• 2022

Purpose: The purpose of the study was to assess the validity of three-dimensional (3D) facial scan taken with facial scanner and digital photo wrapping on the cone-beam computed tomography (CBCT). Materials and Methods: Twenty-five patients had their CBCT scan, two-dimensional (2D) standardized frontal photographs and 3D facial scan obtained on the same day. The facial scans were taken with a facial scanner in an upright position. The 2D standardized frontal photographs were taken at a fixed distance from patients using a camera fixed to a cephalometric apparatus. The 2D integrated facial models were created using digital photo wrapping of frontal photographs on the corresponding CBCT images. The 3D integrated facial models were created using the integration process of 3D facial scans on the CBCT images. On the integrated facial models, sixteen soft tissue landmarks were identified, and the vertical, horizontal, oblique and angular distances between soft tissue landmarks were compared among the 2D facial models and 3D facial models, and CBCT images. Result: The results showed no significant differences of linear and angular measurements among CBCT images, 2D and 3D facial models except for Se-Sn vertical linear measurement which showed significant difference for the 3D facial models. The Bland-Altman plots showed that all measurements were within the limit of agreement. For 3D facial model, all Bland-Altman plots showed that systematic bias was less than 2.0 mm and 2.0° except for Se-Sn linear vertical measurement. For 2D facial model, the Bland-Altman plots of 6 out of 11 of the angular measurements showed systematic bias of more than 2.0°. Conclusion: The facial scan taken with facial scanner showed a clinically acceptable performance. The digital 2D photo wrapping has limitations in clinical use compared to 3D facial scans.

• Wind and Structures
• /
• v.31 no.4
• /
• pp.321-334
• /
• 2020

Engineering type tropical cyclone (TC) wind field models are used to estimate TC wind hazard. Some of the models are well-calibrated using observation data, while others are not extensively compared and verified. They are all proxies to the real TC wind fields. The computational effort for their use differs. In the present study, a comparison of the predicted wind fields is presented by considering three commonly used models: the gradient wind field model, slab-resolving model, and a linear height-resolving model. These models essentially predict the horizontal wind speed at a different height. The gradient wind field model and linear height-resolving model are simple to use while the nonlinear slab-resolving model is more compute-intensive. A set of factors is estimated and recommended such that the estimated TC wind hazard by using these models becomes more consistent. The use of the models, including the developed set of factors, for estimating TC wind hazard over-water and over-land is presented by considering the historical tracks for a few sites. It is shown that the annual maximum TC wind speed can be adequately modelled by the generalized extreme value distribution.

• Bulletin of the Korean Chemical Society
• /
• v.29 no.4
• /
• pp.833-841
• /
• 2008

Principal component-genetic algorithm-multiparameter linear regression (PC-GA-MLR) and principal component-genetic algorithm-artificial neural network (PC-GA-ANN) models were applied for prediction of melting point for 323 drug-like compounds. A large number of theoretical descriptors were calculated for each compound. The first 234 principal components (PC’s) were found to explain more than 99.9% of variances in the original data matrix. From the pool of these PC’s, the genetic algorithm was employed for selection of the best set of extracted PC’s for PC-MLR and PC-ANN models. The models were generated using fifteen PC’s as variables. For evaluation of the predictive power of the models, melting points of 64 compounds in the prediction set were calculated. Root-mean square errors (RMSE) for PC-GA-MLR and PC-GA-ANN models are 48.18 and $12.77{^{\circ}C}$, respectively. Comparison of the results obtained by the models reveals superiority of the PC-GA-ANN relative to the PC-GA-MLR and the recently proposed models (RMSE = $40.7{^{\circ}C}$). The improvements are due to the fact that the melting point of the compounds demonstrates non-linear correlations with the principal components.