• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.4
• /
• pp.203-214
• /
• 2017

There are two references of genetic information in Korean soybean cultivar. This study suggested that the new seven genetic information to supplement the uncertainty on prediction of potential yield of two references in soybean, and assessed the availability of two references and seven genetic information for future research. We carried out evaluate the prediction on flowering time and potential yield of the two references of genetic parameters and the new seven genetic parameters (New1~New7); the new seven genetic parameters were calibrated in Jinju, Suwon, Chuncheon during 2003-2006. As a result, in the individual and regional combination genetic parameters, the statistical indicators of the genetic parameters of the each site or the genetic parameters of the participating stations showed improved results, but did not significant. In Daegu, Miryang, and Jeonju, the predictability on flowering time of genetic parameters of New7 was not improved than that of two references. However, the genetic parameters of New7 showed improvement of predictability on potential yield. No predictability on flowering time of genetic parameters of two references as having the coefficient of determination ($R^2$) on flowering time respectively, at 0.00 and 0.01, but the predictability of genetic parameter of New7 was improved as $R^2$ on flowering time of New7 was 0.31 in Miryang. On the other hand, $R^2$ on potential yield of genetic parameters of two references were respectively 0.66 and 0.41, but no predictability on potential yield of genetic parameter of New7 as $R^2$ of New7 showed 0.00 in Jeonju. However, it is expected that the regional combination genetic parameters with the good evaluation can be utilized to predict the flowering timing and potential yields of other regions. Although it is necessary to analyze further whether or not the input data is uncertain.

• Management & Information Systems Review
• /
• v.30 no.2
• /
• pp.237-255
• /
• 2011

This empirical study is focused on practical application of Range-Based Volatility which is estimated by opening, high, low, closing price of overall asset. Especially proper forecasting period is what I want to know. There is four useful Range-Based Volatility(RV) such as Parkinson(1980; PK), Garman and Klass(1980; GK) Rogers and Satchell(1991; RS), Yang and Zhang(2008; YZ). So, four RV of KOPSI 200 index during 2000.5.22-2009.9.18 was used for empirical test. The emprirical result as follows. First, the best RV which shows the best forecasting performance is PK volatility among PK, GK, RS, YZ volatility. According to estimating period forcasting performance of RV shows delicate difference. PK has better performance in the period with financial crisis of sub-prime mortgage loan. if not, RS is better. Second, almost result shows better performance on forecasting volatility without sub-prime mortgage loan period. so we can say that forecasting performance is lower when historical volatiltiy is comparatively high. Finally, I find that longer estimating period in AR(1) and MA(1) model can reduce forecasting error. More interesting point is that the result shows rapid decrease form 60 days to 90 days and there is no more after 90 days. So, if we forecast the volatility using Range-Based volaility it is better to estimate with 90 trading period or over 90 days.

• Journal of Advanced Navigation Technology
• /
• v.16 no.5
• /
• pp.752-759
• /
• 2012

In this paper, near-real-time positioning accuracies of precise point positioning technique were analyzed using IGS predicted orbits. As a result, we could get the mean errors of 1~1.6 cm, standard deviation of 1~1.3cm from one year of GPS data. This results were similar level to positioning accuracy using the IGS rapid orbits. Positioning errors of >10cm showed 44% of observed days of orbital anomalies. When the orbital anomalies of the predicted orbits were shown, maximum error was 1.7 km, and maximum of mean errors was 308 m. From this study, we conclude that check and consideration were necessary before using the IGS predicted orbits.

• The Korean Journal of Applied Statistics
• /
• v.35 no.1
• /
• pp.93-104
• /
• 2022

In forecasting realized volatility of the major US stock price indexes (S&P 500, Russell 2000, DJIA, Nasdaq 100), internet search volume reflecting investor's interests and implied volatility are used to improve forecast via a deep learning method of the LSTM. The LSTM method combined with search volume index produces better forecasts than existing standard methods of the vector autoregressive (VAR) and the vector error correction (VEC) models. It also beats the recently proposed vector error correction heterogeneous autoregressive (VECHAR) model which takes advantage of the cointegration relation between realized volatility and implied volatility.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.92-111
• /
• 2021

As fine dust negatively affects disease, industry and economy, the people are sensitive to fine dust. Therefore, if the occurrence of fine dust can be predicted, countermeasures can be prepared in advance, which can be helpful for life and economy. Fine dust is affected by the weather and the degree of concentration of fine dust emission sources. The industrial sector has the largest amount of fine dust emissions, and in industrial complexes, factories emit a lot of fine dust as fine dust emission sources. This study targets regions with old industrial complexes in local cities. The purpose of this study is to explore the factors that cause fine dust and develop a predictive model that can predict the occurrence of fine dust. weather data and fine dust data were used, and variables that influence the generation of fine dust were extracted through multiple regression analysis. Based on the results of multiple regression analysis, a model with high predictive power was extracted by learning with a machine learning regression learner model. The performance of the model was confirmed using test data. As a result, the models with high predictive power were linear regression model, Gaussian process regression model, and support vector machine. The proportion of training data and predictive power were not proportional. In addition, the average value of the difference between the predicted value and the measured value was not large, but when the measured value was high, the predictive power was decreased. The results of this study can be developed as a more systematic and precise fine dust prediction service by combining meteorological data and urban big data through local government data hubs. Lastly, it will be an opportunity to promote the development of smart industrial complexes.

• Korean Journal of Construction Engineering and Management
• /
• v.14 no.2
• /
• pp.131-140
• /
• 2013

Econometric forecast models based on past time-series data have been applied to a wide variety of applications due to their advantages in short-term point estimating. These models are particularly used in predicting the impact of governmental research and development (R&D) programs because program managers should assert their feasibility due to R&D program's huge amount of budget. The construction governmental R&D programs, however, separately make an investment by dividing total budget into five sub-business area. It make R&D program managers difficult to understand how R&D programs affect the whole system including economy because they are restricted with regard to many dependent and dynamic variables. In this regard, system dynamics (SD) model provides an analytic solution for complex, nonlinear, and dynamic systems such as the impacts of R&D programs by focusing on interactions among variables and understanding their structures. This research, therefore, developed SD model to capture the different impacts of five construction R&D sub-business by considering different characteristics of sub-business area. To overcome the SD's disadvantages in point estimating, this research also proposed the method for constructing quantitative forecasting model using qualitative data. Understanding the different characteristics of each construction R&D sub-business can support R&D program managers to demonstrate their feasibility of capital investment.

• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.701-717
• /
• 2017

The interest of Korean society and government on future demographic structures is increasing due to rapid aging. Korea's mortality rate is decreasing, but the declined gap is variable. In this study, we compare the Lee-Carter, Lee-Miller, Booth-Maindonald-Smith model and functional data model (FDM) as well as Coherent FDM using non-parametric smoothing technique. We are then examine a reasonable model for projecting on mortality declined rate trend in terms of accuracy of mortality rate by ages and life expectancy. The possibility of using non-parametric techniques for the prediction of mortality in Korea was also examined. Based on the analysis results, FDM and Coherent FDM, which uses the non-parametric technique and reflects the trend of recent data, are excellent. As a result, FDM and Coherent FDM are good fit, and predictability is also excellent assuming no significant future changes.

• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.49-57
• /
• 2020

This study predicts the ratio of added value, which represents the competitiveness of export industries in South Korea, using various machine learning techniques. To enhance the accuracy and stability of prediction, forecast combination technique was applied to predicted values of machine learning techniques. In particular, this study improved the efficiency of the prediction process by selecting key variables out of many variables using recursive feature elimination method and applying them to machine learning techniques. As a result, it was found that the predicted value by the forecast combination method was closer to the actual value than the predicted values of the machine learning techniques. In addition, the forecast combination method showed stable prediction results unlike volatile predicted values by machine learning techniques.

• 열병합발전
• /
• s.69
• /
• pp.15-20
• /
• 2009

소수력 계획 시 개발지점에 대하여 수많은 자료와 정보 등을 필요로 하게 되는데 특히 해당지역내의 유량분포에 대한 유황자료는 개발의 판단여부를 결정케 하는 중요한 요소이다. 소수력발전소의 설비용량에 직접 관계되는 설계유량의 결정과 재해방지를 위한 유출의 예측을 가능케 하고 발전소운영 시 가동률 및 경제성에도 직접적인 영향을 미치는 중용한 요소이나 여기서 논하는 소수력개발은 하천이나 댐과 같은 유형이 아니라 일정한 유량을 확보하여 배출하기 때문에 문제는 없다. 그러나 계절별 부하에 따른 냉각수량의 변화 및 소수력 발전유량의 변동, 조위(해수면) 변화 등에 따라 달라진다. 그러므로 수위조절을 위한 수문은 이들의 변화에 따라 자동운전이 가능해야 하지만 운전시 발전정격수위를 맞출 수 있도록 수문을 조절한 다음 Turbine Governor에 의해 유량 및 수위를 제어할 수 있도록 설계하여 냉각수 순환수 계통에 영향이 미치지 않게 언제나 적정수위를 유지시킬 수 있는 운전모드로 구축하는 것이 안정이라 볼 수 있다. 소수력발전설비 및 수문의 오작동 및 고장이 발생할 때 수위가 상승하여 냉각계통에 손실수두 증가, 취수펌프의 양정고 증가와 Surge 발생 등으로 발전소의 정상 운전에 미치는 영향이 없어야 하므로 세밀한 검토가 필요하기 때문에 폐쇄시간과 수압상승 값 등 요인 분석후 설계하여야 한다. Figure A와 같이 국내 화력발전단지에서 냉각수로 사용되고 방류되는 해수는 발전소에 따라 ca.70~150 CMS로 ca.2,000~5000 kW 이상의 수력에너지(H=4m 형성 기준)를 보유하고 있으나, 현재 활용되지 못하고 그대로 해양으로 방류되고 있어 이 수력에너지의 개발 방안을 오래전부터 검토하여 왔다. 발전소 온배수의 원활한 배수를 위한 설계 낙차와 함께 남서해안의 조위변화에 따른 낙차를 이용하는 것으로 소수력 발전 방식과 조력발전 방식의 특징을 동시에 활용할 수 있다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.23-26
• /
• 2022

딥 러닝 모델은 블랙 박스 (Black Box) 모델로 예측에 대한 근거를 제시하지 못해 신뢰성이 떨어지는 단점이 존재한다. 이를 해결하기 위해 딥 러닝 모델에 설명력을 부여하는 설명 가능한 인공지능 (XAI) 분야 연구가 활발하게 이루어지고 있다. 본 논문에서는 모델 예측을 프로토타입을 통해 설명하는 딥 러닝 모델을 제시한다. 즉, "주어진 이미지는 티셔츠인데, 그 이유는 티셔츠를 대표하는 모양의 프로토타입과 닮았기 때문이다."의 형태로 딥 러닝 모델을 설명한다. 해당 모델은 Encoder, Prototype Layer, Classifier로 구성되어 있다. Encoder는 Feature를 추출하는 데 활용하고 Classifier를 통해 분류 작업을 수행한다. 모델이 제시하는 분류 결과를 설명하기 위해 Prototype Layer에서 가장 유사한 프로토타입을 찾아 설명을 제시한다. 실험 결과 프로토타입 생성 기반 설명 모델은 기존 이미지 분류 모델과 유사한 예측 정확도를 보였고, 예측에 대한 설명력까지 확보하였다.