• Communications for Statistical Applications and Methods
• /
• v.30 no.1
• /
• pp.49-63
• /
• 2023

A lot of studies on the summary measures of predictive strength of categorical response models consider the likelihood ratio index (LRI), also known as the McFadden-R², a better option than many other measures. We propose a simple modification of the LRI that adjusts for the effect of the number of response categories on the measure and that also rescales its values, mimicking an underlying latent measure. The modified measure is applicable to both binary and ordinal response models fitted by maximum likelihood. Results from simulation studies and a real data example on the olfactory perception of boar taint show that the proposed measure outperforms most of the widely used goodness-of-fit measures for binary and ordinal models. The proposed R² interestingly proves quite invariant to an increasing number of response categories of an ordinal model.

• Applied Biological Chemistry
• /
• v.50 no.3
• /
• pp.192-197
• /
• 2007

3D-QSARs on the fungicidal activity of N-phenylbenzenesulfonamide and N-phenyl-2-thienylsulfonamide analogues (1-37) against Phytophthora blight (Phytophthora capsici) were studied quantitatively using CoMFA and CoMSIA methods. The statistical results of the optimized CoMFA (2) model ($r^2_{cv.}(q^2)$ = 0.692 & $r^2_{ncv.}$= 0.965) show better predictability and fitness than CoMSIA (2) model ($r^2_{cv.}(q^2)$ = 0.796 & $r^2_{ncv.}$= 0.958). The fungicidal activities according to the information of the optimized CoMFA (2) model were dependent upon the steric and electrostatic fields of the molecules. Therefore, from the contribution contour maps of CoMFA (2) model, it is expected that 63% contribution was caused by the steric bulk of meta-substituent ($R_1$) on the S-phenyl ring. Also, the other contribution level of 32.9% was represented by the positive charged $R_4-group$ ($R_1$) on the N-phenyl ring and para-substituent ($R_1$) on the S-phenyl ring. A series of higher active compounds, $R_1$= 3-decyl substituent ($pred.pI_50$= 5.88) etc. were predicted based on the findings.

• Korean Journal of Metals and Materials
• /
• v.47 no.10
• /
• pp.613-620
• /
• 2009

The Kachanov-Rabotnov (K-R) creep model was proposed to accurately model the long-term creep curves above $10^5$ hours of Alloy 617. To this end, a series of creep data was obtained from creep tests conducted under different stress levels at $950^{\circ}C$. Using these data, the creep constants used in the K-R model and the modified K-R model were determined by a nonlinear least square fitting (NLSF) method, respectively. The K-R model yielded poor correspondence with the experimental curves, but the modified K-R model provided good agreement with the curves. Log-log plots of ${\varepsilon}^{\ast}$-stress and ${\varepsilon}^{\ast}$-time to rupture showed good linear relationships. Constants in the modified K-R model were obtained as ${\lambda}$=2.78, and $k=1.24$, and they showed behavior close to stress independency. Using these constants, long-term creep curves above $10^5$ hours obtained from short-term creep data can be modeled by implementing the modified K-R model.

• The Journal of Information Systems
• /
• v.19 no.2
• /
• pp.73-95
• /
• 2010

This study shows the scientific and systematic Evaluation Model using factor analysis and AHP methods for the success of defense Information System R&D projects. The evaluation model was divided into 7 evaluation factors such as Developing support, Developing infrastructure, Developing management and test & evaluation, Support factors for strength, Understanding & developing strategy, Developing technology & organization, and Developing performance. And those were composed of totally 24 low level Evaluation index. The Developed Evaluation Model in the paper could be contributed more to objectively and transparently company selection of defense Information System R&D and other defense R&D Projects in the future.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.31 no.5
• /
• pp.100-109
• /
• 2003

A performacne simulation model of the PT6A-62 turboprop engine using the $SIMULINK^R$ was proposed to predict transient and steady state behaviors. The $SIMULINK^R$ has several advantages such as user-friendliness due to the GUI(Graphic User Interfaces) and ease in the modification of the computer program. The $SIMULINK^R$ model consists of subsystems to represent engine gas path components such as flight initial subsystem, compressor subsystem, burner subsystem, compressor turbine subsystem, power turbine, exhaust nozzle subsystem and integrator subsystem. In addition to subsystems, there are search subsystems to find an appropriate operating point by scaling from the 2-D components look-up table, Gasprop Subsystem to calculate the gas property precisely. In case of steady state validation, performance results analyzed by the proposed $SIMULINK^R$ model were agreed well with the analysis results by the commercial GASTURB program. Moreover in validation of the transient model, it was found that performance simulation results by the proposed model were reasonable agreement with analysis results by the well-proved computer program using FORTRAN.

• IE interfaces
• /
• v.25 no.2
• /
• pp.187-195
• /
• 2012

The driver model based on the ACT-R cognitive architecture was developed in order to predict the performance and cognitive workload of a driver operating HVI devices. In the 10 HVI tasks, the predicted performance time and cognitive workload by the ACT-R driver model was well matched and highly correlated with the mean of performance times and subjective workload ratings from 15 participants, respectively. It is strongly proposed that the ACT-R driver model in this study can be applied to evaluate the usability of a new HVI design with less cost in the early stage of system development.

• Korean Journal of Exercise Nutrition
• /
• v.25 no.1
• /
• pp.35-41
• /
• 2021

[Purpose] This pilot study aimed to develop a regression model to estimate the excess post-exercise oxygen consumption (EPOC) of Korean adults using various easy-to-measure dependent variables. [Methods] The EPOC and dependent variables for its estimation (e.g., sex, age, height, weight, body mass index, fat-free mass [FFM], fat mass, % body fat, and heart rate_sum [HR_sum]) were measured in 75 healthy adults (31 males, 44 females). Statistical analysis was performed to develop an EPOC estimation regression model using the stepwise regression method. [Results] We confirmed that FFM and HR_sum were important variables in the EPOC regression models of various exercise types. The explanatory power and standard errors of estimates (SEE) for EPOC of each exercise type were as follows: the continuous exercise (CEx) regression model was 86.3% (R²) and 85.9% (adjusted R²), and the mean SEE was 11.73 kcal, interval exercise (IEx) regression model was 83.1% (R²) and 82.6% (adjusted R²), while the mean SEE was 13.68 kcal, and the accumulation of short-duration exercise (AEx) regression models was 91.3% (R²) and 91.0% (adjusted R²), while the mean SEE was 27.71 kcal. There was no significant difference between the measured EPOC using a metabolic gas analyzer and the predicted EPOC for each exercise type. [Conclusion] This pilot study developed a regression model to estimate EPOC in healthy Korean adults. The regression model was as follows: CEx = -37.128 + 1.003 × (FFM) + 0.016 × (HR_sum), IEx = -49.265 + 1.442 × (FFM) + 0.013 × (HR_sum), and AEx = -100.942 + 2.209 × (FFM) + 0.020 × (HR_sum).

• Journal of Korean Society of Water and Wastewater
• /
• v.22 no.1
• /
• pp.3-14
• /
• 2008

ASM No. 2(Activated sludge model No. 2) is very useful model to analyze the wastewater treatment which removes nitrogen and phosphorus. But, it is difficult to apply ASM No. 2 to control of wastewater treatment since it has 17 material divisions and 46 parameters. So the purpose of this study was the simplification of ASM No. 2 and the provement of simplification model. Firstly ASM No. 2 was simplified with 5 material division and three phases(Anaerobic, aerobic, anoxic phases). The simplified model was proved by R-square using track study data. As a result of provement, the values of R-square in ${NH_4}^+$ were 0.9815 in ASM No. 2 and 0.9250 in simplified model and in ${NO_3}^-$ were 0.8679 in ASM No. 2 and 0.7914 in simplified model and in ${PO_4}^{3-}$ are 0.9745 in ASM No. 2 and 0.9187 in the simplified model when the ability to express the material variation was compared by R-square. So, the simplified model has enough ability to express the variation of ${NH_4}^+$, ${NO_3}^-$ and ${PO_4}^{3-}$.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.57 no.6
• /
• pp.173-183
• /
• 2015

The aim of this study was to develop a soil moisture simulation model equipped with meteorological data enhanced by WRF (Weather Research and Forecast) model, and this soil moisture model was applied for quantifying soil moisture content and irrigation requirement. The WRF model can provide grid based meteorological data at various resolutions. For applicability assessment, comparative analyses were conducted using WRF data and weather data obtained from weather station located close to test bed. Water balance of each upland grid was assessed for soils represented with four layers. The soil moisture contents simulated using the soil moisture model were compared with observed data to evaluate the capacity of the model qualitatively and quantitatively with performance statistics such as correlation coefficient (R), coefficient of determination (R2) and root mean squared error (RMSE). As a result, R is 0.76, $R^2$ is 0.58 and RMSE 5.45 mm in soil layer 1 and R 0.61, $R^2$ 0.37 and RMSE 6.73 mm in soil layer 2 and R 0.52, $R^2$ 0.27 and RMSE 8.64 mm in soil layer 3 and R 0.68, $R^2$ 0.45 and RMSE 5.29 mm in soil layer 4. The estimated soil moisture contents and irrigation requirements of each soil layer showed spatiotemporally varied distributions depending on weather and soil texture data incorporated. The estimated soil moisture contents using weather station data showed uniform distribution about all grids. However the estimated soil moisture contents from WRF data showed spatially varied distribution. Also, the estimated irrigation requirements applied WRF data showed spatial variabilities reflecting regional differences of weather conditions.

• The Korean Journal of Pesticide Science
• /
• v.10 no.1
• /
• pp.7-14
• /
• 2006

Three-dimensional quantitative structure-activity relationships (3D-QSARs) on the herbicidal activities against in-vitro pre-emergence rice plant (Oryza sativa L.) and barnyard grass (Echinochloa crus-galli) by new 5-benzofuryl-2-[1-(alkoxyimino)alkyl]-3-hydroxycyclohex-2-en-1-one derivatives were studied quantitatively using comparative molecular similarity indices analysis (CoMSIA) methodology. The optimized CoMSIA model(A5: $r^2_{cv.}=0.569$ & $r^2_{ncv.}=0.941$) for rice plant exhibited a good correlation with steric (31.6%) and hydrophobic (39.7%) factors of the substrate molecules, and the model (B4: $r^2_{cv.}=0.569$ & $r^2_{ncv.}=0.941$) for barnyardgrass exhibited a good correlation with electrostatic (46.7%) and H-bond acceptor field (30.8%), respectively. The predicted $R_1=SF_5,\;R_2=R_3=R_4=H(P1)$ substituent (Rice plant: $pI_{50}=4.84$ & Barnyardgrass: $pI_{50}=7.21$, ${\Delta}pI_{50}=2.37$) by the model (B4) not only exhibited to the highest herbicidal activity against barnyardgrass, but also exhibited to the highest selecticity between two plants.