• Journal of Korean Society of Transportation
• /
• v.28 no.2
• /
• pp.123-133
• /
• 2010

The national standards for the installation of pedestrian crosswalks prohibits installation of crosswalks within 200 meters of nearby overpasses, underpasses, or crosswalks. In case the exceptional installation is required, the feasibility study is to be thoroughly conducted by the local police agency. However, it is an undeniable fact that the specific installation standards for optimal types and locations of crosswalks are not yet to be established. This paper examines the development of traffic accident prediction model applicable to different types and locations of bus stops(type A and type B) at mid-block intersections. Furthermore, it develops the poisson regression model which sets the "number of traffic accidents" and "traffic accident severity" as dependent variables, while using "traffic volumes", "pedestrian traffic volumes" and "the distance between crosswalks and bus stops" as independent variables. According to the traffic accident prediction model applicable to the type A bus stop location, the traffic accident severity increases relative to the number of traffic volumes, the number of pedestrian traffic volumes, and the distance between crosswalks and bus stops. In case of the type B bus stop model, the further the bus stop is from crosswalks, the number of traffic accidents decreases while it increases when traffic volumes and pedestrian traffic volumes increase. Therefore, it is reasonable to state that the bus stop design which minimizes the traffic accidents is the type C design, which is the one in combination of type A and type B, and the optimal distance is found to be 65 meters. In case of the type A design and the type B design, the optimal distances are found to be within range 60~70meters.

• Journal of Korea Water Resources Association
• /
• v.54 no.2
• /
• pp.93-104
• /
• 2021

Due to climate change the sustainable water resources management of agricultural reservoirs, the largest number of reservoirs in Korea, has become important. However, the DIROM, rainfall-runoff model for calculating agricultural reservoir inflow, has used regression equation developed in the 1980s. This study has optimized the parameters of the DIROM using the genetic algorithm (GA) based on historical inflow data for some agricultural reservoirs that recently begun to observe inflow data. The result showed that the error between the historical inflow and simulated inflow using the optimal parameters was decreased by about 80% compared with the annual inflow with the existing parameters. The correlation coefficient and root mean square error with the historical inflow increased to 0.64 and decreased to 28.2 × 103 ㎥, respectively. As a result, if the DIROM uses the optimal parameters based on the historical inflow of agricultural reservoirs, it will be possible to calculate the long-term reservoir inflow with high accuracy. This study will contribute to future research using the historical inflow of agricultural reservoirs and improvement of the rainfall-runoff model parameters. Furthermore, the reliable long-term inflow data will support for sustainable reservoir management and agricultural water supply.

• Journal of Soil and Groundwater Environment
• /
• v.13 no.5
• /
• pp.57-73
• /
• 2008

Nitrate concentrations were measured up to 49 mg/L (as $NO_3$-N) and 22% of the samples exceeded drinking water standard in shallow and bedrock groundwater of the northern Nonsan area. Nitrate concentrations showed a significant difference among land use groups. To predict nitrate concentration in groundwater, multiple regression analysis was carried out using hydrogeologic parameters of soil media, topography and land use which were categorized as several groups, well depth and altitude, and field parameters of temperature, pH, DO and EC. Hydrogeologic parameters were quantified as area proportions of each category within circular buffers centering at wells. Regression was performed to all the combination of variables and the most relevant model was selected based on adjusted coefficient of determination (Adj. $R^2$). Regression using hydrogelogic parameters with varying buffer radii show highest Adj. $R^2$ at 50m and 300m for shallow and bedrock groundwater, respectively. Shallow groundwater has higher Adj. $R^2$ than bedrock groundwater indicating higher susceptibility to hydrogeologic properties of surface environment near the well. Land use and soil media was major explanatory variables for shallow and bedrock groundwater, respectively and residential area was a major variable in both shallow and bedrock groundwater. Regression involving hydrogeologic parameters and field parameters showed that EC, paddy and pH were major variables in shallow groundwater whereas DO, EC and natural area were in bedrock groundwater. Field parameters have much higher explanatory power over the hydrogeologic parameters suggesting field parameters which are routinely measured can provide important information on each well in assessment of nitrate contamination. The most relevant buffer radii can be applied to estimation of travel time of contaminants in surface environment to wells.

• Journal of Navigation and Port Research
• /
• v.39 no.1
• /
• pp.69-75
• /
• 2015

The concrete purpose of this study is to suggest actually a debt ratio to optimize the capital structure providing a kind of approach to estimate the proper debt ratio with an analytical model and empirical data in Korean shipping industry. The mathematical and analytical model is started from the first equation about ROE, return of net operating income on equity, with an independent variable, debt ratio. It is constructed with several parameters, ROS(return of operating income on sales), TAT(total assets turnover), and NFCL(net finance cost to liabilities). There could not be a certain relationship between debt ratio and ROS or TAT, while some correlation or causality between debt ratio and NFCL. In other words, most of firms with high debt ratio is likely to burden higher finance cost than others with low one. In this case, there is a linearity relationship between debt ratio and NFCL, so then the second equation considering this relation could be included within the analytical approach of this paper. To be short, if the criteria of adequate debt ratio has to be defined as some level of debt ratio to optimize ROE, the ROE could be illustrated as a quadratic equation to debt ratio from two equations. Next, this research estimated those parameters' numbers through the single regression method with data over 12 years of Korean shipping industry, and identified empirically the fact that optimal debt ratio would be approximately 400%. To conclude, if that industry's sales and operating incomes are stable, the debt ratio could be accepted until twice of 200% had forced in order to guarantee its financial safety in past time.

• Korean Journal of Food Science and Technology
• /
• v.46 no.4
• /
• pp.410-417
• /
• 2014

Berries and green tea are underutilized in the food industry despite their great potential as a functional food ingredients. The purpose of this study was to determine the extraction conditions under which total phenolic contents and antioxidant activities of berry and green tea extracts are maximized. Extracts produced using 0-80% ethanol and temperatures ranging from $5-65^{\circ}C$ were evaluated for total phenolic content (TP), as well as for DPPH and ABTS radical-scavenging activities by using response surface methodology. Both ethanol and temperature had significant effects (p<0.05). Ogaja extract produced at $67^{\circ}C$ by using 33% ethanol yielded maximum TP, ABTS, and DPPH values of 23.74 mg GAE/g, 19.77, and 25.04 mg VCE/g, respectively. Optimum conditions for mulberry and raspberry extraction were found to be $65^{\circ}C$ by using 69% and 40% ethanol, respectively. Mulberry and raspberry extracts had TP, DPPH, and ABTS values of 20.74 mg GAE/g, 23.55, and 35.44 mg VCE/g, and 26.08 mg GAE/g, 39.93, and 55.60 mg VCE/g, respectively. Green tea extraction at $57^{\circ}C$ by using 43% ethanol was found to be optimal, yielding TP, ABTS, and DPPH values of 101.15 mg GAE/g, 171.38, and 177.56 mg VCE/g, respectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.6
• /
• pp.557-564
• /
• 2019

The characteristics of the torque and torque ripple of Interior Permanent Magnet Synchronous Motor(IPMSM) are influenced by the size and position of the rotor magnet and the size of the stator slot. This paper deals with the optimal design method for improving torque and torque ripplerate for IPMSM using Response Surface Methodology(RSM). Two objective functions of torque output and torque ripple were derived from the sensitivity analysis by Plackett-Burmann(PB) for the characteristic variables affecting torque and torque ripple. Secondary characteristic variables were selected from the derived objective function and RSM secondary regression model function was estimated by the experiment schedule and analysis results according to the Central Composite Design (CCD). The reliability of the secondary regression model was verified using ANOVA table. The analysis according to the experimental schedule was verified by JMAG(Ver. 18.0) which is Finite Element Method(FEM) software. The torque output of IPMSM applied with final characteristic variables was increased torque output by 11.5 % and the torque ripplerate was reduced by 9.1 %.

• Journal of Korea Water Resources Association
• /
• v.54 no.9
• /
• pp.731-745
• /
• 2021

In this study, the monthly temperature of the Han River basin was predicted by statistical multiple regression models that use global climate indices and weather data of the target region as predictors. The optimal predictors were selected through teleconnection analysis between the monthly temperature and the preceding patterns of each climate index, and forecast models capable of predicting up to 12 months in advance were constructed by combining the selected predictors and cross-validating the past period. Fore each target month, 1000 optimized models were derived and forecast ranges were presented. As a result of analyzing the predictability of monthly temperature from January 1992 to December 2020, PBIAS was -1.4 to -0.7%, RSR was 0.15 to 0.16, NSE was 0.98, and r was 0.99, indicating a high goodness-of-fit. The probability of each monthly observation being included in the forecast range was about 64.4% on average, and by month, the predictability was relatively high in September, December, February, and January, and low in April, August, and March. The predicted range and median were in good agreement with the observations, except for some periods when temperature was dramatically lower or higher than in normal years. The quantitative temperature forecast information derived from this study will be useful not only for forecasting changes in temperature in the future period (1 to 12 months in advance), but also in predicting changes in the hydro-ecological environment, including evapotranspiration highly correlated with temperature.

• Journal of the Economic Geographical Society of Korea
• /
• v.21 no.2
• /
• pp.107-118
• /
• 2018

Due to the rapid economic development, traffic congestion has become a dire concern in Beijing, China. Levying a congestion toll is seen as the most effective solution to the problem. Building a congestion pricing model is a crucial step in implementing a workable toll scheme. Unlike previous attempts, this study not only covers the theoretical discussion but also considers three practical issues: the speed-density relationship, the value of travel time savings, and the determination of optimal traffic volume. We estimate the speed-density relationship by regression models and the value of travel time saved through survey results. We further suggest a way through which the government could identify the optimal traffic flow by a series of trial-and-errors, without the knowledge of exact road demand structure. Finally, a practical tolling scheme is proposed for Beijing's second ring road along with some policy recommendations.

• The KIPS Transactions:PartB
• /
• v.19B no.3
• /
• pp.155-164
• /
• 2012

This study aims to identify the multidimensional variables and sub-variables and study their relative weight in music recommender systems when maximizing the rating function R. To undertake the task, a optimization formula and variables for a research model were derived from the review of prior works on recommender systems, which were then used to establish the research model for an empirical test. With the research model and the actual log data of real customers obtained from an on line music provider in Korea, multiple regression analysis was conducted to induce the optimal correlation of variables in the multidimensional model. The results showed that the correlation value against the rating function R for Items was highest, followed by Social Relations, Users and Contexts. Among sub-variables, popular music from Social Relations, genre, latest music and favourite artist from Items were high in the correlation with the rating function R. Meantime, the derived multidimensional recommender systems revealed that in a comparative analysis, it outperformed two dimensions(Users, Items) and three dimensions(Users, Items and Contexts, or Users, items and Social Relations) based recommender systems in terms of adjusted $R^2$ and the correlation of all variables against the values of the rating function R.

• Journal of Intelligence and Information Systems
• /
• v.23 no.2
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.