• Journal of the Korean Society for Marine Environment & Energy
• /
• v.14 no.2
• /
• pp.107-113
• /
• 2011

To evaluate the performance of the hydrodynamic model, we introduced 10 skill assessments that are assorted by two groups: quantitative skill assessments (Absolute Average Error or AAE, Root Mean Squared Error or RMSE, Relative Absolute Average Error or RAAE, Percentage Model Error or PME) and qualitative skill assessments (Correlation Coefficient or CC, Reliability Index or RI, Index of Agreement or IA, Modeling Efficiency or MEF, Cost Function or CF, Coefficient of Residual Mass or CRM). These skill assessments were applied and calculated to evaluate the hydrodynamic modeling at one of Florida estuaries for water level, current, and salinity as comparing measured and simulated values. We found that AAE, RMSE, RAAE, CC, IA, MEF, CF, and CRM are suitable for the error assessment of water level and current, and AAE, RMSE, RAAE, PME, CC, RI, IA, CF, and CRM are good at the salinity error assessment. Quantitative and qualitative skill assessments showed the similar trend in terms of the classification for good and bad performance of model. Furthermore, this paper suggested the criteria of the "good" model performance for water level, current, and salinity. The criteria are RAAE < 10%, CC > 0.95, IA > 0.98, MEF > 0.93, CF < 0.21 for water level, RAAE < 20%, CC > 0.7, IA > 0.8, MEF > 0.5, CF < 0.5 for current, and RAAE < 10%, PME < 10%, CC > 0.9, RI < 1.15, CF < 0.1 for salinity.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.12
• /
• pp.565-572
• /
• 2017

Traditional method for time series analysis, autoregressive integrated moving average (ARIMA) allows to mine significant patterns from the past observations using autocorrelation and to forecast future sequences. However, Korean baseball games do not have regular intervals to analyze relationship among the past attendance observations. To address this issue, we propose artificial neural network (ANN) based attendance prediction model using various measures including performance, team characteristics and social influences. We optimized ANNs using grid search to construct optimal model for regression problem. The evaluation shows that the optimal and ensemble model outperform the baseline model, linear regression model.

• 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.

• Journal of Korean Society of Environmental Engineers
• /
• v.35 no.8
• /
• pp.540-546
• /
• 2013

The main purpose of the present study was to establish a quicker and cheaper model for predicting the LHV of MSW based on its wet physical composition being brought into C Incinerator. The one regression model was developed to correlate the energy content with variables from physical composition based on a wet matter. The performance of this model for MSW of the C Incinerator was superior to that of equations developed on a dry matter basis by other researchers for estimating energy content. The applicability of this model at the other 4 incinerators showed also an acceptable precision level.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.920-923
• /
• 2017

본 연구는 기존의 수요 예측 등의 시계열 분석에서 주로 사용되는 ARIMA 모형의 어려움을 극복하고자 인공신경망(Artificial Neural Network) 모형을 이용하여 한국 프로 야구 관중 수를 예측하였다. 인공신경망의 가장 기본적인 종류인 전방향 신경망(Feedforward Neural Network)의 초모수(Hyperparameter) 선정에 그리드 탐색(Grid Search)을 적용하여 최적의 모형을 찾고자 하였다. 훈련 자료로는 2015년 3월부터 8월까지의 일별 KBO 관중 수 자료를 대상으로 하였고, 예측력 검증을 위해 2015년 9월 관중 수를 예측하여 실제 관측값과 비교하였다. 그 결과, 그리드 탐색법에서 최적 모형이라고 판단한 모형의 예측력은, 평균 절대 백분율 오차(MAPE) 기준으로 평균 27.14% 였다. 또한, 앙상블 기법에서 착안하여 오차율이 낮은 모형 5개의 예측값 평균의 MAPE는 평균 28.58% 였다. 이는 다중회귀와 비교해보았을 때, 평균적으로 각각 14%, 13.6% 높은 예측력을 보이고 있다.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.153-160
• /
• 2020

Energy Consumption Predictions for Industries has a prominent role to play in the energy management and control system as dynamic and seasonal changes are occurring in energy demand and supply. This paper introduces and explores the steel industry's predictive models of energy consumption. The data used includes lagging and leading reactive power lagging and leading current variable, emission of carbon dioxide (tCO2) and load type. Four statistical models are trained and tested in the test set: (a) Linear Regression (LR), (b) Radial Kernel Support Vector Machine (SVM RBF), (c) Gradient Boosting Machine (GBM), and (d) Random Forest (RF). Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are used for calculating regression model predictive performance. When using all the predictors, the best model RF can provide RMSE value 7.33 in the test set.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.20 no.5
• /
• pp.526-534
• /
• 2014

In this study, single-input transfer function model is applied to forecast monthly mean sea surface temperature(SST) in 2010 at Yeosu in Korean coastal waters. As input series, monthly mean air temperature series for ten years(2000-2009) at Yeosu in Korea is used, and Monthly mean SST at Yeosu station in Korean coastal waters is used as output series(the same period of input). To build transfer function model, first, input time series is prewhitened, and then cross-correlation functions between prewhitened input and output series are determined. The cross-correlation functions have just two significant values at time lag at 0 and 1. The lag between input and output series, the order of denominator and the order of numerator of transfer function, (b, r, s) are identified as (0, 1, 0). The selected transfer function model shows that there does not exist the lag between monthly mean air temperature and monthly mean SST, and that transfer function has a first-order autoregressive component for monthly mean SST, and that noise model was identified as $ARIMA(1,0,1)(2,0,0)_{12}$. The forecasted values by the selected transfer function model are generally $0.3-1.3^{\circ}C$ higher than actual SST in 2010 and have 6.4 % mean absolute percentage error(MAPE). The error is 2 % lower than MAPE by ARIMA model. This implies that transfer function model could be more available than ARIMA model in terms of forecasting performance of SST.

• Journal of the Korean Institute of Gas
• /
• v.22 no.6
• /
• pp.90-103
• /
• 2018

This paper presents the development of two ANN models which can predict an optimum production rate by controlling choke size in oil well, and gas injection rate in gas-lift well. The input data was solution gas-oil ratio, water cut, reservoir pressure, and choke size or gas injection rate. The output data was wellhead pressure and production rate. Firstly, a range of each parameters was decided by conducting sensitive analysis of input data for onshore oil well. In addition, 1,715 sets training data for choke size decision model and 1,225 sets for gas injection rate decision model were generated by nodal analysis. From the results of comparing between the nodal analysis and the ANN on the same reservoir system showed that the correlation factors were very high(>0.99). Mean absolute error of wellhead pressure and oil production rate was 0.55%, 1.05% with the choke size model, respectively. And the gas injection rate model showed the errors of 1.23%, 2.67%. It was found that the developed models had been highly accurate.

• Progress in Medical Physics
• /
• v.26 no.4
• /
• pp.193-200
• /
• 2015

The aim of this study is to present commissioning results of the ViewRay system. We verified safety functions of the ViewRay system. For imaging system, we acquired signal to noise ratio (SNR) and image uniformity. In addition, we checked spatial integrity of the image. Couch movement accuracy and coincidence of isocenters (radiation therapy system, imaging system and virtual isocneter) was verified. Accuracy of MLC positioing was checked. We performed reference dosimetry according to American Association of Physicists in Medicine (AAPM) Task Group 51 (TG-51) in water phantom for head 1 and 3. The deviations between measurements and calculation of percent depth dose (PDD) and output factor were evaluated. Finally, we performed gamma evaluations with a total of 8 IMRT plans as an end-to-end (E2E) test of the system. Every safety system of ViewRay operated properly. The values of SNR and Uniformity met the tolerance level. Every point within 10 cm and 17.5 cm radii about the isocenter showed deviations less than 1 mm and 2 mm, respectively. The average couch movement errors in transverse (x), longitudinal (y) and vertical (z) directions were 0.2 mm, 0.1 mm and 0.2 mm, respectively. The deviations between radiation isocenter and virtual isocenter in x, y and z directions were 0 mm, 0 mm and 0.3 mm, respectively. Those between virtual isocenter and imaging isocenter were 0.6 mm, 0.5 mm and 0.2 mm, respectively. The average MLC positioning errors were less than 0.6 mm. The deviations of output, PDDs between mesured vs. BJR supplement 25, PDDs between measured and calculated and output factors of each head were less than 0.5%, 1%, 1% and 2%, respectively. For E2E test, average gamma passing rate with 3%/3 mm criterion was $99.9%{\pm}0.1%$.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.5
• /
• pp.1535-1545
• /
• 2014

This study aims at improving the Reliability of DSRC Traffic information considering Traffic and Road Characteristics. First of all, this study analyzed the characteristics of DSRC data on urban expressway and problems of outlier data occurrence. After then, this study produced reliable traffic information by using an optimal method of the Outlier-Filtering. After Outlier-Filtering, this study performed accuracy evaluation and appropriateness check for the number of samples per confidence level. As a result, it showed that the MAPE was between 2.2% and 9.7% and RSME was between 2.2 and 7.5 which are very similar figures to the actual average traffic speed. Also, The samples of both Am peak and Pm peak periods were analyzed to be appropriate at the confidence level of 95%, and 90% within the allowable error range of 5kph.