• Journal of radiological science and technology
• /
• v.43 no.6
• /
• pp.495-502
• /
• 2020

In this study, the prevalence of osteoporosis was predicted based on 10 independent variables such as age, weight, and alcohol consumption and 4 tree-based machine-learning models, and the performance of each model was compared. Also the model with the highest performance was used to check the performance by clearing the independent variable, and Area Under Curve(ACU) was utilized to evaluate the performance of the model. The ACU for each model was Decision tree 0.663, Random forest 0.704, GBM 0.702, and XGBoost 0.710 and the importance of the variable was shown in the order of age, weight, and family history. As a result of using XGBoost, the highest performance model and clearing independent variables, the ACU shows the best performance of 0.750 with 7 independent variables. This data suggests that this method be applied to predict osteoporosis, but also other various diseases. In addition, it is expected to be used as basic data for big data research in the health care field.

• Journal of Biosystems Engineering
• /
• v.26 no.5
• /
• pp.449-460
• /
• 2001

This study was carried out to develop a simulation model with EES(Engineering equation solver) for analyzing the performance of a grain cooler. In order to validate the developed simulation model, several main factors which have affected on the performance of the gain cooler were investigated through experiments. A simulation model was developed in the standard vapor compression cycle, and then this model was modified considering irreversibe factors so that the developed alternate model could predict the actual cycle of a grain cooler. The compressor efficiency in vapor compression cycle considering irreversibility much affected on the coefficient of performance(COP). The COP in the standard vapor compression cycle model was greatly as high as about 6.50, but the COP in an alternative model considering irreversibility was as low as about 3.27. As a result of comparison between the actual cycle and the vapor compression cycle considering irreversibility, the difference of pressure at compressor outlet(inlet) was a little by about 48kPa (8.8kPa), the temperatures of refrigerant at main parts of the grain cooler were similar. and the temperature of chilled air was about 8$\^{C}$ in both. The model considering irreversibility could predict performance of the grain cooler. The theoretical period required to chill grain of 1,383kg from the initial temperature 24$\^{C}$ to below 11$\^{C}$ was about 55 hours 30 minutes, and the actual period required in a grain bin was about 58 hours. The difference between the predicted and an actual period was about 2 hours 30 minutes. The cooling performance predicted by the developed model could well estimate the cooling period required to chill the grain.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.5
• /
• pp.425-438
• /
• 2015

This study proposes a three-stage model of R&BD performance which captures commercialization outcomes as well as conventional R&D performance. The model is composed of three factors : inputs (R&D budgets and researchers), outputs (patents and papers), and outcomes (technical fees, products sales, and cost savings). Three stages are defined for each transformation process between the three factors : efficiency stage from input to output (stage 1), effectiveness stage from output to outcome (stage 2), and productivity stage from input to outcome (stage 3). The performance of each stage is measured by data envelopment analysis (DEA). DEA is a non-parametric efficiency measurement technique that has widely been used in R&D performance measurement. We measure the performance of 171 projects of 6 public R&BD programs managed by Seoul Business Agency using the proposed three-stage model. In order to provide a balanced and holistic view of R&BD performance, the R&BD performance map is also constructed based on performance of efficiency and productivity stages.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.24 no.12
• /
• pp.1625-1634
• /
• 2000

Verification of measurements is required for precise evaluation of turbine cycle performance in nuclear power plant. We assumed that initial acceptance data and design data of the plant could provide correlation information between performance data. The data can be used as sample sets for the correct estimation model of measurement value. The modeling was done practically by using regression model based on plant design data, plant acceptance data and verified plant performance data of domestic nuclear power plant. We can construct more robust performance analysis system for an operation nuclear power plant with this validation scheme.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.4
• /
• pp.71-79
• /
• 2016

This study proposes a performance model of a shared bus multi-processor system and analyzes the effect of input/output types on system performance and overload of shared resources. This system performance model reflects the memory reference time in relation to the effect of input/output types on shared resources and the input/output processing time in relation to the input/output processor, disk buffer, and device standby places. In addition, it demonstrates the contribution of input/output types to system performance for comprehensive analysis of system performance. As the concept of workload in the probability theory and the presented model are utilized, the result of operating and analyzing the model in various conditions of processor capability, cache miss ratio, page fault ratio, disk buffer hit ratio (input/output processor and controller), memory access time, and input/output block size. A simulation is conducted to verify the analysis result.

• Communications for Statistical Applications and Methods
• /
• v.28 no.2
• /
• pp.189-204
• /
• 2021

In a regression analysis, a single best model is usually selected among several candidate models. However, it is often useful to combine several candidate models to achieve better performance, especially, in the prediction viewpoint. Model combining methods such as stacking and Bayesian model averaging (BMA) have been suggested from the perspective of averaging candidate models. When the candidate models include a true model, it is expected that BMA generally gives better performance than stacking. On the other hand, when candidate models do not include the true model, it is known that stacking outperforms BMA. Since stacking and BMA approaches have different properties, it is difficult to determine which method is more appropriate under other situations. In particular, it is not easy to find research papers that compare stacking and BMA when regression model assumptions are violated. Therefore, in the paper, we compare the performance among model averaging methods as well as a single best model in the linear regression analysis when standard linear regression assumptions are violated. Simulations were conducted to compare model averaging methods with the linear regression when data include outliers and data do not include them. We also compared them when data include errors from a non-normal distribution. The model averaging methods were applied to the water pollution data, which have a strong multicollinearity among variables. Simulation studies showed that the stacking method tends to give better performance than BMA or standard linear regression analysis (including the stepwise selection method) in the sense of risks (see (3.1)) or prediction error (see (3.2)) when typical linear regression assumptions are violated.

• Proceedings of the Korea Database Society Conference
• /
• 1994.09a
• /
• pp.49-69
• /
• 1994

A client/server system has become the computing architecture for the business organization which seeks competitive edges. Technically, a client/server system places application processing close to the user and thus increases performance. This paper's two primary goals are (i) to present a performance model for client/server database systems and (ii) to demonstrate analytically the effectiveness of client/server computing in comparison with other computing architectures via an illustrative example. The model is most likely to be used as a practical performance guide for client/server computing.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.2
• /
• pp.401-409
• /
• 2007

This paper addresses a performance evaluation model for ERP system's implementation using Analytic Network Process (ANP) technique. In this study, the performance variables are identified as the perspectives of cost, business process, systems operation, and change management, respectively. The empirical study also investigated factors that affect the performance variables to find out the causal relationship between them using the ANP approach. The data for the empirical analysis were collected from manufacturing companies that have implemented ERP systems. The research findings indicate the proposed model is powerful in proposing that the indirect relationship between influencing factors and managerial effectiveness, mediated by employee satisfaction, is an important one.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2020.06a
• /
• pp.94-95
• /
• 2020

This paper introduces the mix design and performance evaluation of Ultra-High Performance Concrete (UHPC). The concrete mixture is designed to achieve a densely compacted cementitious matrix via the modified Andreasen & Andersen particle packing model. The compressive strengths of UHPC designed by this method reached 154MPa. The relationship between packing theory and compressive strength of UHPC is discussed in this paper.

• Journal of KIISE:Software and Applications
• /
• v.33 no.11
• /
• pp.936-941
• /
• 2006

To apply object recognition techniques to real environment, illumination compensation method should be developed. As effective illumination compensation model, we focused our attention on Retinex model and illumination-Reflectance model, implemented them, and experimented on their performance. We implemented Retinex model with Single Scale Retinex, Multi-Scale Retinex, and Retinex Neural Network and Multi-Scale Retinex Neural Network, neural network model of Retinex model. Also, we implemented illumination-Reflectance model with reflectance image calculation by calculating an illumination image by low frequency filtering in frequency domain of Discrete Cosine Transform and Wavelet Transform, and Gaussian blurring. We compare their illumination compensation performance to facial images under nine illumination directions. We also compare their performance after post processing using Principal Component Analysis(PCA). As a result, illumination Reflectance model showed better performance and their overall performance was improved when illumination compensated images were post processed by PCA.