• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.3
• /
• pp.98-109
• /
• 2006

Fire control system(FCS) errors can be classified as hardware errors, filter prediction errors, effective ballistic function errors, and aiming errors. Among these errors, the filter prediction errors are the most significant error sources. To reduce them, a target future position calculation method using the acceleration estimate is suggested and it is compared with the constant velocity target prediction method. Simulation results show that the suggested method has better performance than the constant velocity prediction method. Target tracking algorithm is established with multiple target tracking filters based on IMM structure.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.28 no.10
• /
• pp.1247-1254
• /
• 2004

In momentum exchange theory the loss models for the circulatory flow is critically important. But because of lack of loss model on the circulatory flow, analysis model on regenerative turbomachines is not available in the open literature. In the present study circulatory loss is evaluated by combining bend's losses. Through the comparison with the previous experimental data on linear pressure gradient, a combination factor is suggested in terms of the aspect ratio of a channel. Applying this factor to two kinds of regenerative blowers the predicted results are found to be in good agreement with the experimental data of the overall performance and the head distribution along the rotational direction. Especially, the comparison with the head distribution demonstrates the accuracy of hydraulic model and loss model suggested in the present study. And the comparison with the overall performance confirms the validness of physical models as well as loss models suggested in the present study.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.9
• /
• pp.979-988
• /
• 2014

Recently, the interest in the thermal comfort is ever increasing as the time people stay in the automobile is gradually increasing. So far, however, the cooling performance of the HVAC(heating and ventilation air conditioning) system is evaluated by thermal environment criteria such as indoor air velocity and temperature, not by a thermal comfort index. Furthermore, the precise criteria has not been established yet when the thermal comfort for the automobile is evaluated using numerical analysis. In this study, the numerical analysis of automobile indoor thermal comfort according to various parameters such as HVAC operating mode, airflow, passenger boarding conditions is performed during the HVAC system's initial operating time(20 minutes). The solar ray tracing model and S2S radiation model are used and validated to simulate an external heat source. Based on this study, an evaluation model which can predict the thermal comfort index for the combination of the above parameters is presented.

• Composites Research
• /
• v.27 no.2
• /
• pp.66-71
• /
• 2014

This study carried out finite element vibration analysis of pole structures made of GFRP, which is based on the micro-mechanical approach for different fiber-volume fractions. The finite element (FE) models for composite structures using multi-scale approaches described in this paper is attractive not only because it shows excellent accuracy in analysis but also it shows the effect of the material combination. The FE model is used for studying free vibrations of laminated composite poles for various fiber-volume fractions. In particular, new results reported in this paper are focused on the significant effects of the fiber-volume fraction for various parameters, such as fiber angles, layup sequences, and length-thickness ratios. It may be concluded from this study that the combination effect of fiber and matrix, largely governing the dynamic characteristics of composite structures, should not be neglected and thus the optimal combination could be used to design such civil structures for better dynamic performance.

• Journal of the Korea Concrete Institute
• /
• v.14 no.6
• /
• pp.1022-1031
• /
• 2002

This paper presents efficient models for bridge structures using CART-ANFIS (classification and regression tree-adaptive neuro fuzzy inference system). A fuzzy decision tree partitions the input space of a data set into mutually exclusive regions, each region is assigned a label, a value, or an action to characterize its data points. Fuzzy decision trees used for classification problems are often called fuzzy classification trees, and each terminal node contains a label that indicates the predicted class of a given feature vector. In the same vein, decision trees used for regression problems are often called fuzzy regression trees, and the terminal node labels may be constants or equations that specify the predicted output value of a given input vector. Note that CART can select relevant inputs and do tree partitioning of the input space, while ANFIS refines the regression and makes it continuous and smooth everywhere. Thus it can be seen that CART and ANFIS are complementary and their combination constitutes a solid approach to fuzzy modeling.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.277-286
• /
• 2002

Genetic programming (GP) has been combined with quantum mechanical perturbation theory to make a new algorithm to construct mathematical models and perform predictions for chaotic time series from real world. Procedural similarities between time series modeling and perturbation theory to solve quantum mechanical wave equations are discussed, and the exemplary GP approach for implementing them is proposed. The approach is based on multiple populations and uses orthogonal functions for GP function set. GP is applied to original time series to get the first mathematical model. Numerical values of the model are subtracted from the original time series data to form a residual time series which is again subject to GP modeling procedure. The process is repeated until predetermined terminating conditions are met. The algorithm has been successfully applied to construct highly effective mathematical models for many real world chaotic time series. Comparisons with other methodologies and topics for further study are also introduced.

• Journal of the Korean Society for Railway
• /
• v.10 no.5
• /
• pp.527-532
• /
• 2007

In this paper, we suggest those two design plans for power supply method of Hot Standby Sparing System; one is the plan using MTBF based on Constant Failure Rate, and the plan using Reliability Function is the other. Traditionally, RBD (Reliability Block Diagram) is used for reliability prediction which is required to meet any requirements before system operation. However, the system that has redundancy, such as Hot Standby Sparing System, Is not suitable for system reliability modeling using combination model, such as RBD. In this paper, therefore, we demonstrate that for redundancy controller, redundancy modeling design toward fault occurrence design is more effective to build up a system with higher reliability and achieve the effectiveness of loss cost due to maintenance and failure occurred in operation, rather than combinational modeling design.

• Korean Journal of Food Science and Technology
• /
• v.37 no.6
• /
• pp.1012-1017
• /
• 2005

Predictive growth model of putrefactive bacteria of surimi-based imitation crab in the modified surimi-based imitation crab (MIC) broth was investigated. The growth curves of putrefactive bacteria were obtained by measuring cell number in MIC broth under different conditions (Initial cell number, $1.0{\times}10^2,\;1.0{\times}10^3$ and $1.0{\times}10^4$ colony forming unit (CFU)/mL; temperature, $15^{\circ}C,\;20^{\circ}C\;and\;25^{\circ}C$) and applied them to Gompertz model. The microbial growth indicators, maximum specific growth rate constant (k), lag time (LT) and generation time (GT), were calculated from Gompertz model. Maximum specific growth rate (k) of putrefactive bacteria was become fast with rising temperature and fastest at $25^{\circ}C$. LT and GT were become short with rising temperature and shortest at $25^{\circ}C$. There were not significant differences in k, LT and GT by initial cell number (p>0.05). Polynomial model, $k=-0.2160+0.0241T-0.0199A_0$, and square root model, $\sqrt{k}=0.02669$ (T-3.5689), were developed to express the combination effects of temperature and initial cell number, The relative coefficient of experimental k and predicted k of polynomial model was 0.87 from response surface model. The relative coefficient of experimental k and predicted k of square root model was 0.88. From above results, we found that the growth of putrefactive bacteria was mainly affected by temperature and the square root model was more credible than the polynomial model for the prediction of the growth of putrefactive bacteria.

• Journal of the Korea Concrete Institute
• /
• v.14 no.1
• /
• pp.118-125
• /
• 2002

Hydration is the main reason for the growth of the material properties. An exact parameter to control the chemical and physical process is not the time, but the degree of hydration. Therefore, it is reasonable that development of all material properties and the formation of microstructure should be formulated in terms of degree of hydration. Mathematical formulation of degree of hydration is based on combination of reaction rate functions. The effect of moisture conditions as well as temperature on the rate of reaction is considered in the degree of hydration model. This effect is subdivided into two contributions: water shortage and water distribution. The former is associated with the effect of W/C ratio on the progress of hydration. The water needed for progress of hydration do not exist and there is not enough space for the reaction products to form. The tatter is associated with the effect of free capillary water distribution in the pore system. Physically absorption layer does not contribute to progress of hydration and only free water is available for further hydration. In this study, the effects of chemical composition of cement, W/C ratio, temperature, and moisture conditions on the degree of hydration are considered. Parameters that can be used to indicate or approximate the real degree of hydration are liberated heat of hydration, amount of chemically bound water, and chemical shrinkage, etc. Thus, the degree of heat liberation and adiabatic temperature rise could be determined by prediction of degree of hydration.