• Journal of the Korean Data and Information Science Society
• /
• v.21 no.4
• /
• pp.765-775
• /
• 2010

For the accelerated failure time (AFT) model a lot of effort has been devoted to develop effective estimation methods. AFT model assumes a linear relationship between the logarithm of event time and covariates. In this paper we propose a semiparametric support vector machine to consider situations where the functional form of the effect of one or more covariates is unknown. The proposed estimating equation can be computed by a quadratic programming and a linear equation. We study the effect of several covariates on a censored response variable with an unknown probability distribution. We also provide a generalized approximate cross-validation method for choosing the hyper-parameters which affect the performance of the proposed approach. The proposed method is evaluated through simulations using the artificial example.

• Coupled systems mechanics
• /
• v.12 no.5
• /
• pp.419-428
• /
• 2023

We have developed a model for estimating the parameters of viscous materials from indirect tensile tests for asphalt. This is a simple Burger nonlinear rheological two-cell model or standard model. At the same time, we begin to develop a more versatile and complex multi-cell model. The simple model is validated using experimental load-displacement results from laboratory tests: The recorded displacements are used as input values and the measured force data are simulated with the model. The optimal model parameters are estimated using the Levenberg-Marquardt method and a very good agreement between the experimental results and the model calculations is shown. However, not all parts of the model are active in the loading phase of the experiment, so we extended the validation of the model to the simulation of the relaxation behaviour. In this stage, the other model parameters are activated and the simulation results are consistent with the literature. At this stage, we have estimated the parameters only for the two-cell uniaxial model, but further work will include results for the multi-cell model.

• Computers and Concrete
• /
• v.24 no.4
• /
• pp.295-302
• /
• 2019

Evolutionary algorithms based on conventional statistical methods such as regression and classification have been widely used in data mining applications. This work involves application of gene expression programming (GEP) for predicting compressive strength of fly ash geopolymer concrete, which is gaining increasing interest as an environmentally friendly alternative of Portland cement concrete. Based on 56 test results from the existing literature, a model was obtained relating the compressive strength of fly ash geopolymer concrete with the significantly influencing mix design parameters. The predictions of the model in training and validation were evaluated. The coefficient of determination ($R^2$), mean (${\mu}$) and standard deviation (${\sigma}$) were 0.89, 1.0 and 0.12 respectively, for the training set, and 0.89, 0.99 and 0.13 respectively, for the validation set. The error of prediction by the model was also evaluated and found to be very low. This indicates that the predictions of GEP model are in close agreement with the experimental results suggesting this as a promising method for compressive strength prediction of fly ash geopolymer concrete.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.2
• /
• pp.363-369
• /
• 2010

In this paper we propose a mixed-effects least squares support vector regression (LS-SVR) for longitudinal data. We add a random-effect term in the optimization function of LS-SVR to take random effects into LS-SVR for analyzing longitudinal data. We also present the model selection method that employs generalized cross validation function for choosing the hyper-parameters which affect the performance of the mixed-effects LS-SVR. A simulated example is provided to indicate the usefulness of mixed-effect method for analyzing longitudinal data.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.2 no.2
• /
• pp.81-89
• /
• 2001

Space systems are operating in a changing and uncertain space environment and are desired to have autonomous capability for long periods of time without frequent telecommunications from the ground station At the same time. requirements for new set of projects/systems calling for ""autonomous"" operations for long unattended periods of time are emerging. Since, by the nature of space systems, it is desired that they perform their mission flawlessly and also it is of extreme importance to have fault-tolerant sensor/actuator sub-systems for the purpose of validating science measurement data for the mission success. Technology innovations attendant on autonomous data validation and health monitoring are articulated for a growing class of autonomous operations of space systems. The greatest need is on focus research effort to the development of a new class of fault-tolerant space systems such as attitude actuators and sensors as well as validation of measurement data from scientific instruments. The characterization for the next step in evolving the existing control processes to an autonomous posture is to embed intelligence into actively control. modify parameters and select sensor/actuator subsystems based on statistical parameters of the measurement errors in real-time. This research focuses on the identification/demonstration of critical technology innovations that will be applied to Autonomous Spacecraft Health Monitoring/Data Validation Control Systems (ASHMDVCS). Systems (ASHMDVCS).

• Journal of Korean Society on Water Environment
• /
• v.31 no.5
• /
• pp.507-522
• /
• 2015

In this study, some of the model verification results of STREAM (Spatio-Temporal River-basin Ecohydrology Analysis Model), a newly-developed hybrid watershed model, are presented for the runoff processes of nonpoint source pollution. For verification study of STREAM, the model was applied to a test watershed and a sensitivity analysis was also carried out for selected parameters. STREAM was applied to the Mankyung River Watershed to review the applicability of the model in the course of model calibration and validation against the stream flow discharge, suspended sediment discharge and some water quality items (TOC, TN, TP) measured at the watershed outlet. The model setup, simulation and data I/O modules worked as designed and both of the calibration and validation results showed good agreement between the simulated and the measured data sets: NSE over 0.7 and $R^2$ greater than 0.8. The simulation results also include the spatial distribution of runoff processes and watershed mass balance at the watershed scale. Additionally, the irrigation process of the model was examined in detail at reservoirs and paddy fields.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.59 no.3
• /
• pp.63-70
• /
• 2017

The purpose of this study was to calibrate the hydrologic parameters of SWAT model and analyze the daily runoff for the study watershed using SWAT-CUP. The Hardware watershed is located in Virginia, USA. The watershed area is $356.15km^2$, and the land use accounts for 73.4 % of forest and 23.2 % of pasture. Input data for the SWAT model were obtained from the digital elevation map, landuse map, soil map and others. Water flow data from 1990 to 1994 was used for calibration and from 1997 to 2005 was for validation. The SUFI-2 module of the SWAT-CUP program was used to calibrate the hydrologic parameters. The parameters were calibrated for the highly sensitive parameters presented in previous studies. The P-factor, R-factor, $R^2$, Nash-Sutcliffe efficiency (NS), and average flow were used for the goodness-of-fit measures. The applicability of the model was evaluated by sequentially increasing the number of applied parameters from 4 to 11. In this study, 10-parameter set was accepted for calibration in consideration of goodness-of-fit measures. For the calibration period, P-factor was 0.85, R-factor was 1.76, $R^2$ was 0.51 and NS was 0.49. The model was validated using the adjusted ranges of selected parameters. For the validation period, P-factor was 0.78, R-factor was 1.60, $R^2$ was 0.60 and NS was 0.57.

• Korean Journal of Radiology
• /
• v.24 no.1
• /
• pp.51-61
• /
• 2023

Objective: To develop and test a machine learning model for classifying human papillomavirus (HPV) status of patients with oropharyngeal squamous cell carcinoma (OPSCC) using ¹⁸F-fluorodeoxyglucose (¹⁸F-FDG) PET-derived parameters in derived parameters and an appropriate combination of machine learning methods in patients with OPSCC. Materials and Methods: This retrospective study enrolled 126 patients (118 male; mean age, 60 years) with newly diagnosed, pathologically confirmed OPSCC, that underwent ¹⁸F-FDG PET-computed tomography (CT) between January 2012 and February 2020. Patients were randomly assigned to training and internal validation sets in a 7:3 ratio. An external test set of 19 patients (16 male; mean age, 65.3 years) was recruited sequentially from two other tertiary hospitals. Model 1 used only PET parameters, Model 2 used only clinical features, and Model 3 used both PET and clinical parameters. Multiple feature transforms, feature selection, oversampling, and training models are all investigated. The external test set was used to test the three models that performed best in the internal validation set. The values for area under the receiver operating characteristic curve (AUC) were compared between models. Results: In the external test set, ExtraTrees-based Model 3, which uses two PET-derived parameters and three clinical features, with a combination of MinMaxScaler, mutual information selection, and adaptive synthetic sampling approach, showed the best performance (AUC = 0.78; 95% confidence interval, 0.46-1). Model 3 outperformed Model 1 using PET parameters alone (AUC = 0.48, p = 0.047) and Model 2 using clinical parameters alone (AUC = 0.52, p = 0.142) in predicting HPV status. Conclusion: Using oversampling and mutual information selection, an ExtraTree-based HPV status classifier was developed by combining metabolic parameters derived from ¹⁸F-FDG PET/CT and clinical parameters in OPSCC, which exhibited higher performance than the models using either PET or clinical parameters alone.

• Water Engineering Research
• /
• v.4 no.3
• /
• pp.141-154
• /
• 2003

Nonpoint source pollutants from agriculture are identified as one of the main causes of water quality degradation in the United States. The Hydrological Simulation Program-Fortran (HSPF) was used to simulate runoff, nitrogen, and sediment loads from an urbanizing watershed; the Polecat Creek watershed located in Virginia. Model parameters related to hydrology and water quality were calibrated and validated using observed hydrologic and water quality data collected at the watershed outlet and at several sub-watershed outlets. A comparison of measured and simulated monthly runoff at the outlet of the watershed resulted in a correlation coefficient of 0.94 for the calibration period and 0.74 for the validation period. The annual observed and simulated sediment loads for the calibration period were 220.9 kg/ha and 201.5 kg/ha, respectively. The differences for annual nitrate nitrogen ($NO_3$) loads between the observed and simulated values at the outlet of the watershed were 5.1% and 42.1% for the calibration and validation periods, respectively. The corresponding values for total Kjeldahl nitrogen (TKN) were 60.9% and 40.7%, respectively. Based on the simulation results, the calibrated HSPF input parameters were considered to adequately represent the Polecat Creek watershed.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.317-325
• /
• 2011

Vehicle model validation for the static vehicle testing has been done by comparison of the simulation results and test results and the parameters of the vehicle model to be used in the simulation have been adjusted to reflect the measured behaviour. The vehicle model fort the simulation should be validated by suitable tests and/or practical experience. The static vehicle test used to validate the vehicle model are the weight measurement, the wheel offloading test, the bogie rotational resistance test and the sway test. Finally, the computer simulation model has been validated and using the validated vehicle model the acceptance of the vehicle safety of the resistance to flange climbing derailment at low speed can be examined.