• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2002.12a
• /
• pp.162-165
• /
• 2002

Q-learning은 강화학습의 한 방법으로서, 여러 분야에 널리 응용되고 있는 기법이다. 최근에는 Linear Quadratic Regulation(이하 LQR) 문제에 성공적으로 적용된 바 있는데, 특히, 시스템모델의 파라미터에 대한 구체적인 정보가 없는 상태에서 적절한 입력과 출력만을 가지고 학습을 통해 문제를 해결할 수 있어서 상황에 따라서 매우 실용적인 대안이 될 수 있다. Neural Q-learning은 이러한 Q-learning의 Q-value를 MLP(multilayer perceptron) 신경망의 출력으로 대치시킴으로써, 비선형 시스템의 최적제어 문제를 다룰 수 있게 한 방법이다. 그러나, Neural Q방식은 신경망의 구조를 먼저 결정한 후 역전파 알고리즘을 이용하여 학습하는 절차를 취하기 때문에, 시행착오를 통하여 신경망 구조를 결정해야 한다는 점, 역전파 알고리즘의 적용으로 인해 신경망의 연결강도 값들이 지역적 최적해로 수렴한다는 점등의 문제점을 상속받는 한계가 있다. 따라서, 본 논문에서는 Neural-0 학습의 도구로, 역전파 알고리즘으로 학습되는 MLP 신경망을 사용하는 대신 최근 들어 여러 분야에서 그 성능을 인정받고 있는 서포트 벡터 학습법을 사용하는 방법을 택하여, $\varepsilon$-SVR(Epsilon Support Vector Regression)을 이용한 Q-value 근사 기법을 제안하고 관련 수식을 유도하였다. 그리고, 모의 실험을 통하여, 제안된 서포트 벡터학습 기반 Neural-Q 방법의 적용 가능성을 알아보았다.

• Environmental Engineering Research
• /
• v.24 no.1
• /
• pp.24-30
• /
• 2019

The present study explores the applicability of response surface methodology (RSM) in conjunction with central composite design (CCD) matrix to statistically optimize ettringite crystallization process for the removal of sulphate from landfill leachate. A three factor-five coded level CCD with 20 runs, was performed to estimate the best fitted model. The RSM results indicated that the fitted quadratic regression model could be appropriate to predict sulfate removal efficiency. The pH was identified as the most dominant parameter affecting sulphate removal. 61.6% of maximum sulphate removal efficiency was obtained at pH of 11.06 for a 1.87 of $Ca/SO_4$ and 0.51 of $Al/SO_4$ molar ratios. The operating cost for ettringite crystallization at optimized conditions was calculated to be 0.52 $/$m^3$. The significance of independent variables and their interactions were tested by analysis of variance. Scanning electron microscope (SEM) and SEM coupled with energy dispersive X-Ray spectroscopy results confirmed the formation of ettringite crystal and were used to describe its morphology features.

• Journal of the Korean Society of Visualization
• /
• v.17 no.2
• /
• pp.48-57
• /
• 2019

A straightforward strategy for particle image velocimetry (PIV) interrogation and post-processing has been proposed, aiming at reducing errors and clarifying vortex structures. The interrogation window size should be kept small to reduce bias error and improve spatial resolution. A spatial filter is then applied to the velocity field to reduce random error and clarify flow structure. The performance of three popular spatial filters were assessed: box filter, median filter, and local quadratic polynomial regression filter. In order to quantify random uncertainty, the image matching (IM) method is applied to an experimental dataset of homogeneous and isotropic turbulence (HIT) obtained by 2D-PIV. We statistically analyze the uncertainty propagation through the spatial filters, and verify the reduction in random uncertainty. Moreover, we illustrate that the spatial filters help clarify vortex structures using vortex identification criteria. As a result, PIV random uncertainty was reduced and the vortex structures became clearer by spatial filtering.

• Journal of Animal Science and Technology
• /
• v.63 no.3
• /
• pp.603-613
• /
• 2021

This research improved the growth potential of Bifidobacterium animalis subsp lactis strain JNU306, a commercial medium that is appropriate for large-scale production, in yeast extract, soy peptone, glucose, L-cysteine, and ferrous sulfate. Response surface methodology (RSM) was used to optimize the components of this medium, using a central composite design and subsequent analyses. A second-order polynomial regression model, which was fitted to the data at first, significantly lacked fitness. Thus, through further analyses, the model with linear and quadratic terms plus two-way, three-way, and four-way interactions was selected as the final model. Through this model, the optimized medium composition was found as 2.8791% yeast extract, 2.8030% peptone soy, 0.6196% glucose, 0.2823% L-cysteine, and 0.0055% ferrous sulfate, w/v. This optimized medium ensured that the maximum biomass was no lower than the biomass from the commonly used blood-liver (BL) medium. The application of RSM improved the biomass production of this strain in a more cost-effective way by creating an optimum medium. This result shows that B. animalis subsp lactis JNU306 may be used as a commercial starter culture in manufacturing probiotics, including dairy products.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.54 no.3
• /
• pp.271-279
• /
• 2021

Ultrasound-assisted extraction (UAE) conditions, including extraction time, extraction temperature, and ethanol concentration, were optimized to increase the total flavonoid content (TFC), tyrosinase inhibitory activity (TIA), and collagenase inhibitory activity (CIA) of Spirulina platensis through central composite design (CCD). For the optimization of the three dependent variables, a quadratic regression model was derived from 17 experimental sets for the simultaneous maximization of TFC, TIA, and CIA. The predicted optimal UAE conditions were 44.0 min of extraction time, 82.8℃ of extraction temperature, and 96.0% of ethanol concentration. Under these conditions, 0.93 mg QE/g DM of TFC, 81.9% of CIA, and 92.1% of TIA were predicted. The CCD-based UAE optimization enabled an increase in TFC, CIA, and TIA, thereby confirming that the S. platensis extract can be used in the development of a cosmetic material with skin whitening and anti-wrinkle effects.

• Journal of Korea Planning Association
• /
• v.54 no.3
• /
• pp.15-26
• /
• 2019

The development of science and transportation technology leads to the increase of inter - city networks that play an important role in urban growth. Overall, numerous studies based on network theory pay attention to positive effects of urban network on urban growth. However, some studies have pointed out the negative effects of inter-city interactions such as straw effects. This implies that the network between cities may not be positively correlated with urban growth, and that the direction of the influence may vary from a certain threshold, such as the marginal utility curve. In this context, the purpose of this study is to measure the impacts of network with central city on urban growth in the capital region and examine the relationship between urban network and growth. Two multiple regression models are employed with changes in population and employment as dependent variables. The urban network index and other control variables are used as independent variables. Especially, the urban network indexes are used in quadratic forms to examine non linear relations with urban growth such U-shape or an inverted U-shape. The results show that the relationships between networks with the central city and urban growth are not a simple linear, and the influence can be changed from the critical point.

• Journal of Distribution Science
• /
• v.20 no.5
• /
• pp.119-127
• /
• 2022

Purpose: The purpose of this study is to analyze the Cost-Effectiveness Analysis (CEA) of wholesale and retail brokerage businesses in Korea. And give managerial implications and contribute to academics. Research design, data and methodology: This research empirically analyzes the relationship between expenses and business performance. As for business performance, this research considered two financial performances; sales and profit. As for antecedent variables, this research measured three cost investment expenses; human resource management (HRM), marketing (MKT) and corporate social responsibility (CSR). This research used frequency analysis, correlation analysis, stepwise regression analysis and curve estimation analysis. Results: The result shows that HRM and CSR positive significant influence on sales yet marketing negatively significant influence on sales. And for profit, HRM and CSR give a positive significant influence. However, marketing's influence was not significant. According to curve estimation analysis, the relation between individual cost and performance, best functional relation was all quadratic functions. Some results show ∩ shape and others show shape. Conclusions: Based on this study result, implications for practical management to Wholesale and Retail Brokerage companies in Korea. And the contribution to academics is expected. Also, based on the limitation of this study, future research is suggested.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.61-69
• /
• 2022

The function of coolant in machining is to reduce the frictional force in the contact area in between the tool and the material, and to increase the precision by cooling the work-piece and the tool, to make the machining surface uniform, and to extend the tool life. However, cutting oil is harmful to the human body because it uses chlorine-based extreme pressure additives to cause environmental pollutants. In this study, the effect of cutting temperature and surface roughness of titanium alloy for medical purpose (Ti-6Al-7Nb) in eco-friendly ADL slot shape machining was investigated using the response surface analysis method. As the design of the experiment, three levels of cutting speed, feed rate, and depth of cut were designed and the experiment was conducted using the central composite planning method. The regression expressions of cutting temperature and surface roughness were respectively obtained as quadratic functions to obtain the minimum value and optimal cutting conditions. The values from this formula and the experimental values were compared. As a result, this study makes and establishes the basis to prevent environmental pollution caused by the use of coolant and to replace it with ADL (Aerosol Dry Lubricant) machining that uses a very small amount of vegetable oil with high pressure.

• Structural Engineering and Mechanics
• /
• v.88 no.6
• /
• pp.521-533
• /
• 2023

In the present study, the finite volume method is applied for the thermal performance prediction of the natural ventilation system using vertical solar chimney whereas, design parameters are optimized through the response surface methodology (RSM). The computational simulations are performed for various parameters of the solar chimney such as absorber temperature (40≤T_abs≤70℃), inlet temperature (20≤T₀≤30℃), inlet height of (0.1≤h≤0.2 m) and chimney width (0.1≤d≤0.2 m). Analysis of variance (ANOVA) was carried out to identify the design parameters that influence the average Nusselt number (Nu) and mass flow rate (ṁ). Then, quadratic polynomial regression models were developed to predict of all the response parameters. Consequently, numerical and graphical optimizations were performed to achieve multi-objective optimization for the desired criteria. According to the desirability function approach, it can be seen that the optimum objective functions are Nu=25.67 and ṁ=24.68 kg/h·m, corresponding to design parameters h=0.18 m, d=0.2 m, T_abs=46.81℃ and T₀=20℃. The optimal ventilation flow rate is enhanced by about 96.65% compared to the minimum ventilation rate, while solar energy consumption is reduced by 49.54% compared to the maximum ventilation rate.

• Korean Journal of Plant Resources
• /
• v.23 no.2
• /
• pp.172-178
• /
• 2010

This study was carried out to investigate abiotic and biotic environmental factors affecting homoharringtonine (HHT) contents of Cephalotaxus koreana, whereby, to provide basic information of high value-added industry production of HHT as a promising anti-cancer agent. For correlation between abiotic environmental factors (soil moisture, soil pH, habitat density and temperature) and HHT contents, the contents were highly correlated with soil moisture (0.77) and soil pH (-0.68). For multiple regression analysis of relationship between abiotic environmental factors (soil moisture and soil pH) and HHT contents, soil moisture appeared to be strongly affecting the contents relatively due to being significant at only its regression coefficient ($26.48^{***}$). For the effect of biotic environmental factors (damage index) affecting HHT contents, the contents was quadratic with equation of $H=278.23+1242D-398.87D^2$, also, damage index had strong effect on the contents. Finally, for the result of the most influencing an environmental factor on HHT contents, both damage index and soil moisture were suitable in second polynomial regression, also, damage index ($R^2=0.73^{***}$) was turned out to be more influencing factor than soil moisture ($R^2=0.67^{**}$) on HHT contents relatively. Therefore, we predict that HHT contents in the trees of Cephalotaxus koreana is produced as a chemical defense mechanism triggered by a stress-related damage of fungi or insects.