• The Korean Journal of Applied Statistics
• /
• v.28 no.5
• /
• pp.885-893
• /
• 2015

It is important to improve the forecasting accuracy of one-year-ahead seasonal factors in order to produce seasonally adjusted series of the following year. In this paper, seasonal factors of 8 monthly Korean economic time series are examined and forecast based on the functional principal component regression. One-year-ahead forecasts of seasonal factors from the functional principal component regression are compared with other forecasting methods based on mean absolute error (MAE) and mean absolute percentage error (MAPE). Forecasting seasonal factors via the functional principal component regression performs better than other comparable methods.

• Journal of Korea Multimedia Society
• /
• v.24 no.10
• /
• pp.1414-1424
• /
• 2021

In this paper, the importance of input factors of a DNN (Deep Neural Network) PM_2.5 forecasting model using LRP(Layer-wise Relevance Propagation) is analyzed, and forecasting performance is improved. Input factor importance analysis is performed by dividing the learning data into time and PM_2.5 concentration. As a result, in the low concentration patterns, the importance of weather factors such as temperature, atmospheric pressure, and solar radiation is high, and in the high concentration patterns, the importance of air quality factors such as PM_2.5, CO, and NO₂ is high. As a result of analysis by time, the importance of the measurement factors is high in the case of the forecast for the day, and the importance of the forecast factors increases in the forecast for tomorrow and the day after tomorrow. In addition, date, temperature, humidity, and atmospheric pressure all show high importance regardless of time and concentration. Based on the importance of these factors, the LRP_DNN prediction model is developed. As a result, the ACC(accuracy) and POD(probability of detection) are improved by up to 5%, and the FAR(false alarm rate) is improved by up to 9% compared to the previous DNN model.

• The Korean Journal of Applied Statistics
• /
• v.35 no.2
• /
• pp.189-201
• /
• 2022

In this study, we propose factor augmentation to improve forecasting power of cryptocurrency return. We consider financial and economic variables as well as psychological aspect for possible factors. To be more specific, financial and economic factors are obtained by applying principal factor analysis. Psychological factor is summarized by news sentiment analysis. We also visualize such factors through impulse response analysis. In the modeling perspective, we consider ARIMAX as the classical model, and random forest and deep learning to accommodate nonlinear features. As a result, we show that factor augmentation reduces prediction error and the GRU performed the best amongst all models considered.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.2
• /
• pp.13-22
• /
• 2017

The present study proposes a new methodology for predicting the demand for truck rest areas beside national highways. Previous demand forecasting methods were reviewed first in order to complement them with additional items. The results of the study are as follows. In the demand forecasting process, the primary task is to divide parking demands of trucks into short-term parking and long-term parking. Since short-term and long-term parking vary in utilization, congestion, and turnover rate, different influence factors should be considered according to parking time. Furthermore, the demand characteristics of rest and convenience facilities need to be reflected as well, because they in turn affect the demand for truck rest areas. In sum, the demand forecasting process for destination-type truck rest areas on national highways requires more attention than that for truck rest areas on expressways, and possible influences of various factors should be examined in this process.

• Journal of Digital Convergence
• /
• v.15 no.3
• /
• pp.157-163
• /
• 2017

Forecasting container cargo volumes is very important factor for port related organizations in inversting in the recent port management. Especially forcasting of domestic and foreign container volume is necessary because adjacent nations are competing each other to handle more container cargoes. Exact forecasting is essential elements for national port policy, however there is still some difficulty in developing the predictive model. In this respect, the purpose of this study is to develop and suggest the forecasting model of container cargo volumes of China using System Dynamics (SD). The monthly data collected from Clarkson's Shipping Intelligence Network from year 2004 to 2015 during 12 years are used in the model. The accuracy of the model was tested by comparisons between actual container cargo volumes and forecasted corgo volumes suggested by the research model. The MAPE values are calcualted as 6.21% for imported cargo volumes and 7.68% for exported cargo volumes respectively. Less than 10% of MAPE value means that the suggested model is very accurate.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.155-155
• /
• 2018

Uncertainty in flood forecasting using a coupled meteorological and hydrological model is arisen from various sources, especially the uncertainty comes from the inaccuracy of Quantitative Precipitation Forecasts (QPFs). In order to improve the capability of flood forecast, the uncertainty estimation and mitigation are required to perform. This study is conducted to investigate and reduce such uncertainty. First, ensemble QPFs are generated by using Monte - Carlo simulation, then each ensemble member is forced as input for a hydrological model to obtain ensemble streamflow prediction. Likelihood measures are evaluated to identify feasible member. These members are retained to define upper and lower limits of the uncertainty interval and assess the uncertainty. To mitigate the uncertainty for very short lead time, a blending method, which merges the ensemble QPFs with radar-based rainfall prediction considering both qualitative and quantitative skills, is proposed. Finally, blending bias ratios, which are estimated from previous time step, are used to update the members over total lead time. The proposed method is verified for the two flood events in 2013 and 2016 in the Yeonguol and Soyang watersheds that are located in the Han River basin, South Korea. The uncertainty in flood forecasting using a coupled Local Data Assimilation and Prediction System (LDAPS) and Sejong University Rainfall - Runoff (SURR) model is investigated and then mitigated by blending the generated ensemble LDAPS members with radar-based rainfall prediction that uses McGill algorithm for precipitation nowcasting by Lagrangian extrapolation (MAPLE). The results show that the uncertainty of flood forecasting using the coupled model increases when the lead time is longer. The mitigation method indicates its effectiveness for mitigating the uncertainty with the increases of the percentage of feasible member (POFM) and the ratio of the number of observations that fall into the uncertainty interval (p-factor).

• International Journal of Highway Engineering
• /
• v.18 no.3
• /
• pp.47-57
• /
• 2016

PURPOSES : This study aims to examine the differences between the existing traffic demand forecasting method and the traffic demand forecasting method considering future regional development plans and new road construction and expansion plans using a four-step traffic demand forecast for a more objective and sophisticated national highway maintenance. This study ultimately aims to present future pavement deterioration and budget forecasting planning based on the examination. METHODS : This study used the latest data offered by the Korea Transport Data Base (KTDB) as the basic data for demand forecast. The analysis scope was set using the Daejeon Metropolitan City's O/D and network data. This study used a traffic demand program called TransCad, and performed a traffic assignment by vehicle type through the application of a user equilibrium-based multi-class assignment technique. This study forecasted future traffic demand by verifying whether or not a realistic traffic pattern was expressed similarly by undertaking a calibration process. This study performed a life cycle cost analysis based on traffic using the forecasted future demand or existing past pattern, or by assuming the constant traffic demand. The maintenance criteria were decided according to equivalent single axle loads (ESAL). The maintenance period in the concerned section was calculated in this study. This study also computed the maintenance costs using a construction method by applying the maintenance criteria considering the ESAL. The road user costs were calculated by using the user cost calculation logic applied to the Korean Pavement Management System, which is the existing study outcome. RESULTS : This study ascertained that the increase and decrease of traffic occurred in the concerned section according to the future development plans. Furthermore, there were differences from demand forecasting that did not consider the development plans. Realistic and accurate demand forecasting supported an optimized decision making that efficiently assigns maintenance costs, and can be used as very important basic information for maintenance decision making. CONCLUSIONS : Therefore, decision making for a more efficient and sophisticated road management than the method assuming future traffic can be expected to be the same as the existing pattern or steady traffic demand. The reflection of a reliable forecasting of the future traffic demand to life cycle cost analysis (LCCA) can be a very vital factor because many studies are generally performed without considering the future traffic demand or with an analysis through setting a scenario upon LCCA within a pavement management system.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2005.10a
• /
• pp.327-332
• /
• 2005

This paper aims to analysis for evaluation factor and success prediction of port innovative cluster. This paper is divided three factors such ac policy, source and operation. In addition, three factors are divided into the twelve detail factors. the weight of each factor is calculated by Kohonen Network. At the result, this paper places the priority on the source factor.

• Journal of Korea Water Resources Association
• /
• v.43 no.1
• /
• pp.51-65
• /
• 2010

We suggest a simple and practical flood forecasting and warning system, which can predict change in the water level of a river in a small to medium-size watershed where flash flooding occurs in a short time. We first choose the flood defense target points, through evaluation of the flood risk of dike overflow and lowland inundation. Using data on rainfall, and on the water levels at the observed and prediction points, we investigate the interrelations and derive a regression formula from which we can predict the flood level at the target points. We calculate flood water levels through a calibrated flood simulation model for various rainfall scenarios, to overcome the shortage of real water stage data, and these results as basic population data are used to derive a regression formula. The values calculated from the regression formula are modified by the weather condition factor, and the system can finally predict the flood stages at the target points for every leading time. We also investigate the applicability of the prediction procedure for real flood events of the Jungnang Stream basin, and find the forecasting values to have close agreement with the surveyed data. We therefore expect that this suggested warning scheme could contribute usefully to the setting up of a flood forecasting and warning system for a small to medium-size river basin.

• Journal of Korean Society for Atmospheric Environment
• /
• v.33 no.6
• /
• pp.554-569
• /
• 2017

Sensitivity analysis on $PM_{10}$ forecasting simulations was carried out by using two different initial and boundary conditions of meteorological fields: NCEP/FNL (National Centers for Environmental Prediction/Final Analysis) reanlaysis data and NCEP/GFS (National Centers for Environmental Prediction/Global Forecast System) forecasting data, and the comparisons were made between two different simulations. The two results both yielded lower $PM_{10}$ concentrations than observations, with relatively lower biased results by NCEP/FNL than NCEP/GFS. We explored the detailed individual meteorological variables to associate with $PM_{10}$ prediction performance. With the results of NCEP/FNL outperforming GFS, our conclusion is that no particular significant bias was found in temperature fields between NCEP/FNL and NCEP/GFS data, while the overestimated wind speed by NCEP/GFS data influenced on the lower $PM_{10}$ concentrations simulation than NCEP/FNL, by decreasing the duration time of high-$PM_{10}$ loaded air mass over both coastal and metropolitan areas. These comparative characteristics of FNL against GFS data such as maximum 3~4 m/s weaker wind speed, $PM_{10}$ concentration control with the highest possible factor of 1.3~1.6, and one or two hour difference of peak time for each case in this study, were also reflected into the results of statistical analysis. It is implying that improving the surface wind speed fluctuation is an important controlling factor for the better prediction of $PM_{10}$ over Korean Peninsula.