• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.10
• /
• pp.7061-7070
• /
• 2015

Multi-Response Surface Optimization aims at finding the optimal setting of input variables considering multiple responses simultaneously. The Weighted Mean Squared Error (WMSE) minimization approach, which imposes a different weight on the two components of mean squared error, squared bias and variance, first obtains WMSE for each response and then minimizes all the WMSEs at once. Most of the methods proposed for the WMSE minimization approach to date are classified into the prior preference articulation approach, which requires that a decision maker (DM) provides his/her preference information a priori. However, it is quite difficult for the DM to provide such information in advance, because he/she cannot experience the relationships or conflicts among the responses. To overcome this limitation, this paper proposes a posterior preference articulation method to the WMSE minimization approach. The proposed method first generates all (or most) of the nondominated solutions without the DM's preference information. Then, the DM selects the best one from the set of nondominated solutions a posteriori. Its advantage is that it provides an opportunity for the DM to understand the tradeoffs in the entire set of nondominated solutions and effectively obtains the most preferred solution suitable for his/her preference structure.

• The Korean Journal of Applied Statistics
• /
• v.21 no.6
• /
• pp.901-910
• /
• 2008

Incidence of Plasmodium vivax malaria in South Korea have been reemerged from mid-1990 and infected around 1600 patients annually recent years. The authors calculated the distribution of malaria infection and prevalence in South Korea using incidence (2001-2006) and incubation period distributions by a back-calculation formula and the least squares estimation method. The estimated infection has a normal distribution with a mean 207 and a standard deviation 30.7 days. In addition, the authors found the estimated daily average prevalence is 628.8 patients.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.20 no.3
• /
• pp.262-276
• /
• 2018

Models to predict Leaf Wetness Duration (LWD) were evaluated using the observed meteorological and dew data at the 11 citrus orchards in Jeju, South Korea from 2016 to 2017. The sensitivity and the prediction accuracy were evaluated with four models (i.e., Number of Hours of Relative Humidity (NHRH), Classification And Regression Tree/Stepwise Linear Discriminant (CART/SLD), Penman-Monteith (PM), Deep-learning Neural Network (DNN)). The sensitivity of models was evaluated with rainfall and seasonal changes. When the data in rainy days were excluded from the whole data set, the LWD models had smaller average error (Root Mean Square Error (RMSE) about 1.5hours). The seasonal error of the DNN model had the similar magnitude (RMSE about 3 hours) among all seasons excluding winter. The other models had the greatest error in summer (RMSE about 9.6 hours) and the lowest error in winter (RMSE about 3.3 hours). These models were also evaluated by the statistical error analysis method and the regression analysis method of mean squared deviation. The DNN model had the best performance by statistical error whereas the CART/SLD model had the worst prediction accuracy. The Mean Square Deviation (MSD) is a method of analyzing the linearity of a model with three components: squared bias (SB), nonunity slope (NU), and lack of correlation (LC). Better model performance was determined by lower SB and LC and higher NU. The results of MSD analysis indicated that the DNN model would provide the best performance and followed by the PM, the NHRH and the CART/SLD in order. This result suggested that the machine learning model would be useful to improve the accuracy of agricultural information using meteorological data.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.923-932
• /
• 2013

This paper proposes a method to predict the number of foodborne disease outbreaks by microbes. The weekly data of food poisoning occurrences by microbes in Korea contain many zero-valued observations and have dependency between outbreaks. In order to model both phenomena, the number of food poisonings is predicted by an autoregressive model and the probabilities of food poisoning occurrences by microbes (given the total of food poisonings) are estimated by the baseline category logit model. The predicted number of foodborne disease outbreaks by a microbe is obtained by multiplying the predicted number of foodborne disease outbreaks and the estimated probability of the food poisoning by the corresponding microbe. The mean squared error and the mean absolute value error are evaluated to compare the performances of the proposed method and the zero-inflated model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.905-905
• /
• 2012

현재 도시유역의 홍수피해를 경감시키기 위한 방안으로 우수유출 저감시설에 대한 연구가 활발히 진행 중에 있다. 그러나 침투형 우수유출 저감시설의 경우 침투량 산정에 필요한 여러 인자 중 토성에 의해 저감 능력에 많은 차이를 보이고 있으며, 강우시 침투로 인한 토양내 함수비의 변화와 선행강우 조건 등에 의해 정량적인 분석이 어려워 활용도가 미흡한 실정이다. 따라서 본 연구에서는 2009년 국립방재연구원에서 시행한 침투실험 자료의 조건과 동일하게 투수계수 및 형상이 다른 두 종류의 투수성 보도블록 A, B와 토양내 선행강우의 유무에 대하여 표 1과 같이 검증 케이스로 구분하고, 4 가지의 강우강도로 모의 조건을 설정한 후 불포화 투수층의 침투해석을 실시하고 실험결과를 이용하여 모의결과에 대한 검증을 시행하였으며, 모의 결과의 검증을 뒷받침하기 위하여 통계적인 적합도를 나타내는 평균제곱오차(RMSE), 평균편차비율(PBIAS), 모형 효율성 계수(NSE), 지속성 모형효율성 계수(PME)을 산정해 보았다. 검증 결과 그림 1과 같이 투수성 보도블록 B의 형태가 투수성 보도블록 A의 형태보다 적합도가 높게 나타났고, 50mm/hr의 강우강도에서 변동성이 크게 나타났으나, 50mm/hr를 제외한 나머지 강우조건에서 양호한 적합도를 보였으며, 선행강우가 있는 조건이 선행강우가 없는 조건에 비해 높은 적합도를 나타내었다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.7
• /
• pp.884-889
• /
• 2021

The number of people infected with Covid-19 in Korea seemed to be gradually decreasing thanks to various efforts such as social distancing and vaccines. However, just as the number of infected people increased after a particular incident on February 20, 2020, the number of infected people has been increasing rapidly since December 2020 by approximately 500 per day. Therefore, the future Covid-19 is predicted through the Prophet algorithm using Kaggle's dataset, and the explanatory power for this prediction is added through the coefficient of determination, mean absolute error, mean percent error, mean square difference, and mean square deviation through Scikit-learn. Moreover, in the absence of a specific incident rapidly increasing the cases of Covid-19, the proposed method predicts the number of infected people in Korea and emphasizes the importance of implementing epidemic prevention and quarantine rules for future diseases.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.49-49
• /
• 2020

하천 보 상류영역에서 발생하는 박리 흐름을 분석하기 위해 실험수로에 하천보 모형을 설치하고, 보 주변에서 발생하는 흐름 구조를 입자 영상 유속계(PIV)로 이용하여 정밀하게 측정하였다. 본 연구에 사용된 보는 하천 설계기준을 따른, 전방 수직벽과 하류 경사램프가 있는 유한한 마루 길이 보이다. 실험 조건은 보 상·하류부 수심으로 인한 4가지 흐름(Hydraulic jump, Plunging jet, Surface wave, Surface jet)을 기반으로 설정하여 수리조건에 따른 유속 특성을 규명하였다. 실험에서 측정한 수직-수평방향 평균 유속·유선도를 분석한 결과, 보 전방의 하부에서 재순환 흐름이 관측되었고, 역방향 흐름도 이 지역에서 발견되었다. 유속 편차의 제곱 평균(Root Mean Square) 흐름장에서 보 전방과 재순환 흐름 영역에 불안전한 흐름이 강하게 발견되었다. 역방향 흐름은 박리 흐름에서 발견되는 주요 특성으로, 역방향 흐름의 전체 면적을 매 관측마다 측정하여 이를 분석한 결과, 재순환 흐름의 면적은 오른쪽으로 기울어진 분포를 가지고, 항상 0보다 큰 값을 가지는 것으로 나타났다. 재순환 면적에 따른 흐름 특성은 역방향 흐름 면적에 대한 조건부 평균을 이용하여 파악했는데, 조건부 평균의 구간은 재순환 흐름의 중심에서 지배적인 주기값을 이용했다. 역방향 흐름이 작은 영역에선, 보 상류의 흐름이 재순환 흐름으로 말려들어가는 열린 박리흐름이 나타나며, 역방향 흐름이 큰 경우에는 재순환 영역의 흐름은 보 상류의 흐름과 분리되는 닫힌 박리흐름이 발생하였다. 역방향 흐름이 가장 큰 경우, 보 전방의 박리흐름은 보의 상단을 넘는 것으로 관찰되었다. 이러한 결과를 통해 보 마루에서 발생하는 박리흐름이 보 전방에 박리흐름에 영향을 미치는 것으로 파악되었다. 조건부 평균된 역방향 흐름의 면적과 박리 지점(separation point)의 관계를 분석한 결과, 역방향 흐름의 오른쪽으로 기울어진 분포와 대규모 흐름 방출 현상이 관측되었다. 박리 지점의 위치와 수리 매개변수의 관계를 분석한 결과, 상류의 수심 증가에 따라 증가하는 경향이 나타났다.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.20 no.3
• /
• pp.321-331
• /
• 2008

A model has been constructed in this study for the investigation of physical characteristics of the Gyeonggi Bay and Han River estuary. MIKE 21 HD (HyDrodynamics) has been used for the uncertainty analysis of the tide of the Gyeonngi Bay and Han River estuary. A total of 15 model experiments have been performed for the hydrodynamic parts and the analysis of results have been made in terms of RMSD (Root-mean square deviation) which has been frequently employed in the suitability analysis of hydrological data since the introduction by NERC(1975), U.K. A smaller value of RMSD indicates the more suitability of a parameter to the model. Analysis of the hydrodynamic results has shown that RMSD of the mean tidal range has the largest value of 0.1148 at Yeomha channel while has the smallest value of 0.0400 at Yeonphyong-do, indicating that the uncertainty in the mean tidal range on near-shore side is larger than that of offshore side. Experiment with reduced water depth by 10% has produced a most significant increase in RMSD. It is therefore implied that the model response changes more sensitively to water depth rather than grid sizes, open boundary forcing and river discharge.

• Journal of the Society of Naval Architects of Korea
• /
• v.32 no.4
• /
• pp.27-37
• /
• 1995

A performance index is very important and indispensable to the evaluation of automatic steering system of ships in open sea from the viewpoint of energy saving. In this paper, we derive the performance index of automatic steering system from the concept of energy loss of propulsive power. The index is found to consist of three terms, energy loss due to elongation of sailing distance, energy loss due to steering, and energy loss due to yawing motion. We also provide two kinds of calculation method on the performance index ; frequency response analysis and digital simulation. The numerical calculations are carried out for an ore carrier and a fishing boat by both methods. The frequency response analysis is found to be useful if the system is linear and the disturbance on ship is not large. If the system is nonlinear or the disturbance is excessive, the method of digital simulation has to be applied for the accurate evaluation of the performance index. Further investigations into the effects of nonlinear elements such as weather adjuster, power unit etc. on the performance index, will be dealt with in another paper.

• Journal of Biomedical Engineering Research
• /
• v.25 no.1
• /
• pp.33-41
• /
• 2004

Accuracy of registration between images acquired from various medical image modalities is one of the critical issues in radiation treatment planing. In this study, a method of accuracy evaluation of image registration using a homemade brain phantom was investigated. Chamfer matching of CT-MR and CT-SPECT imaging was applied for the multimodal image registration. The accuracy of image correlation was evaluated by comparing the center points of the inserted targets of the phantom. The three dimensional root-mean-square translation deviations of the CT-MR and CT-SPECT registration were 2.1${\pm}$0.8 mm and 2.8${\pm}$1.4 mm, respectively. The rotational errors were ＜ 2$^{\circ}$ for the three orthogonal axes. These errors were within a reasonable margin compared with the previous phantom studies. A visual inspection of the superimposed CT-MR and CT- SPECT images also showed good matching results.