• Journal of Internet of Things and Convergence
• /
• v.10 no.1
• /
• pp.39-45
• /
• 2024

Container volume is a very important factor in accurate evaluation of port performance, and accurate prediction of effective port development and operation strategies is essential. However, it is difficult to improve the accuracy of container volume prediction due to rapid changes in the marine industry. To solve this problem, it is necessary to analyze the impact on port performance using the Internet of Things (IoT) and apply it to improve the competitiveness and efficiency of Busan Port. Therefore, this study aims to develop a prediction model for predicting the future container volume of Busan Port, and through this, focuses on improving port productivity and making improved decision-making by port management agencies. In order to predict port container volume, this study introduced the Extreme Gradient Boosting (XGBoost) technique of a machine learning model. XGBoost stands out of its higher accuracy, faster learning and prediction than other algorithms, preventing overfitting, along with providing Feature Importance. Especially, XGBoost can be used directly for regression predictive modelling, which helps improve the accuracy of the volume prediction model presented in previous studies. Through this, this study can accurately and reliably predict container volume by the proposed method with a 4.3% MAPE (Mean absolute percentage error) value, highlighting its high forecasting accuracy. It is believed that the accuracy of Busan container volume can be increased through the methodology presented in this study.

• Korean Journal of Remote Sensing
• /
• v.33 no.5_2
• /
• pp.721-732
• /
• 2017

With the increasing socio-economic importance of rice as a global staple food, several models have been developed for rice yield estimation by combining remote sensing data with carbon cycle modelling. In this study, we aimed to estimate rice yield in Korea using such an integrative model using satellite remote sensing data in combination with a biophysical crop growth model. Specifically, daily meteorological inputs derived from MODIS (Moderate Resolution imaging Spectroradiometer) and radar satellite products were used to run a light use efficiency based crop growth model, which is based on the MODIS gross primary production (GPP) algorithm. The modelled biomass was converted to rice yield using a harvest index model. We estimated rice yield from 2003 to 2014 at the county level and evaluated the modelled yield using the official rice yield and rice straw biomass statistics of Statistics Korea (KOSTAT). The estimated rice biomass, yield, and harvest index and their spatial distributions were investigated. Annual mean rice yield at the national level showed a good agreement with the yield statistics with the yield statistics, a mean error (ME) of +0.56% and a mean absolute error (MAE) of 5.73%. The estimated county level yield resulted in small ME (+0.10~+2.00%) and MAE (2.10~11.62%),respectively. Compared to the county-level yield statistics, the rice yield was over estimated in the counties in Gangwon province and under estimated in the urban and coastal counties in the south of Chungcheong province. Compared to the rice straw statistics, the estimated rice biomass showed similar error patterns with the yield estimates. The subpixel heterogeneity of the 1 km MODIS FPAR(Fraction of absorbed Photosynthetically Active Radiation) may have attributed to these errors. In addition, the growth and harvest index models can be further developed to take account of annually varying growth conditions and growth timings.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.32 no.5
• /
• pp.469-479
• /
• 2014

N-RTK(Network based RTK) methods are able to improve the accuracy of GNSS positioning results through modelling of the distance-dependent error sources(i.e. primarily the ionospheric and tropospheric delays and orbit errors). In this study, the comparison of the TTFF(Time-To-Fix-First ambiguity), accuracy and discrepancies in horizontal/vertical components of N-RTK methods(VRS and FKP) with the static GNSS at 20 Unified Control Stations covering Incheon metropolitan city area during solar storms(Solar cycle 24 period) were performed. The results showed that the best method, compared with the statics GNSS survey, is the VRS, followed by the FKP, but vertical components of both VRS and FKP were approximately two times bigger than horizontal components. The reason for this is considered as the ionospheric scintillation because of irregularities in electron density, and the tropospheric scintillation because of fluctuations on the refractive index take the place. When the TTFF at each station for each technique used, VRS gave shorter initialization time than FKP. The possible reasons for this result might be the inherent differences in principles, errors in characteristics of different correction networks, interpolating errors of FKP parameters according to the non-linear variation of the dispersive and non-dispersive errors at rover when considering both domestic mobile communication infra and the standardized high-compact data format for N-RTK. Also, those test results revealed degradation of positing accuracy, long initialization time, and sudden re-initialization, but more failures to resolve ambiguity during space weather events caused by Sunspot activity and solar flares.

• Journal of Korea Water Resources Association
• /
• v.49 no.11
• /
• pp.951-959
• /
• 2016

This study was conducted to evaluate observed runoff data collected every 10 minutes at stream gauging stations in Jeju Island using a physically-based model, SWAT. The Hancheon watershed was selected as study area, and ephemeral stream algorithm suggested by previous research was incorporated into the model, which is able to simulate ephemeral runoff pattern of Jeju streams. Simulated runoff and runoff rates were compared to observations during 2008-2013, which showed 'very good' performance rating in Nash-Sutcliffe model efficiency (ME) and determination coefficient ($R^2$). Some observations had problems such that runoff rates were very high for some rainfall events with little amount of antecedent rainfall, and were very low or missing with much rainfall comparing to previous researches. Additionally, regression equation between precipitation and simulated runoff was generated with high degree of correlation. The equation can be utilized to simply predict reasonable runoff, or to investigate and complement the abnormal or missing data of observations on the assumption that modelling results were sufficiently reliable and satisfactory. As results, minimizing the error in calibrating the model by evaluation of observed data would be helpful to accurately model the rainfall-runoff characteristics and analyze the water balance components of watersheds in Jeju Island.

• Journal of Korea Water Resources Association
• /
• v.39 no.10 s.171
• /
• pp.823-832
• /
• 2006

Precipitation is the most important component to the study of water and energy cycle in hydrology. In this study we investigate rainfall retrieval uncertainty from different sources of remotely sensed precipitation field and then probable error propagation in the simulation of hydrologic variables especially, runoff on different vegetation cover. Two remotely sensed rainfall retrievals (space-borne IR-only and ground radar rainfall) are explored and compared visually and statistically. Then, an offline Community Land Model (CLM) is forced with in situ meteorological data to simulate the amount of runoff and determine their impact on model predictions. A fundamental assumption made in this study is that CLM can adequately represent the physical land surface processes. Results show there are big differences between different sources of precipitation fields in terms of the magnitude and temporal variability. The study provides some intuitions on the uncertainty of hydrologic prediction via the interaction between the land surface and near atmosphere fluxes in the modelling approach. Eventually it will contribute to the understanding of water resources redistribution to the climate change in Korean Peninsula.

• Korean Chemical Engineering Research
• /
• v.45 no.1
• /
• pp.73-80
• /
• 2007

This article aims to optimize the nitrogen removal of a sequencing batch reactor (SBR) through the use of the activated sludge model and iterative dynamic programming (IDP). Using a minimum batch time and a maximum nitrogen removal for minimum energy consumption, a performance index is developed on the basis of minimum area criteria for SBR optimization. Choosing area as the performance index makes the optimization problem simpler and a proper weighting in the performance index makes it possible to solve minimum time and energy problem of SBR simultaneously. The optimized results show that the optimal set-point of dissolved oxygen affects both the total batch time and total energy cost. For two different influent loadings, IDP-based SBR optimizations suggest each supervisory control of batch scheduling and set-point trajectory of dissolved oxygen (DO) concentration, and can save 20% of the total energy cost, while meeting the treatment requirements of COD and nitrogen. Moreover, it shows that the re-optimization of IDP within a batch can solve the modelling error problem due to the influent loading changes, or the process faults.

• Journal of Korea Water Resources Association
• /
• v.35 no.2
• /
• pp.231-240
• /
• 2002

The wetland has very important functions in hydrologic and ecological aspects and the research of wetland functions requires the basic hydrological properties such as water quantity. However, we do not have a research work on the hydrological properties for a wetland study in Korea. Therefore, this study is to estimate the relations between the volume(V), the area(A), and the depth(h) of water in the wetland which might be the basis for the wetland research in Korea. To estimate the relations, we derive the basic equations, obtain the surveyed data and do modelling, and estimate the relations of A-h and V-h using the Surfer program. The estimated and observed volumes for 5-wetland are compared and the errors are in the range of 2 % to 11 % for 4-wetland and 34 % for the rest. The wetlands in small errors showed the similar ones with the profile of the wetted perimeter which is assumed for the derivation of the equation but the wetland of large error has much different profile with the assumed one. We re-estimate the volumes for 3-wetland(W3, W4, W5) which showed the large errors due to the bended profiles of the wetland slopes. say, after the slopes was divided into two parts of upper and lower ones, the volumes were estimated. From our re-estimation, we obtained very good results ranged from 1 % to 8 % in their errors. We conjecture that the procedure suggested in this study might be useful as a reference for the future research on the relations of V-A-h in Korea.

• Korean Journal of Construction Engineering and Management
• /
• v.14 no.3
• /
• pp.53-64
• /
• 2013

In building construction project, there are numerous information or data parts across many different software applications and professional specialists. BIM (Building Information Modeling), as a medium for managing information generated during construction project, it is intended to enhance the effectiveness of construction management and reap a lot of advantages such as, automatic quantity takeoff, error-free estimation, 4D(3D+Time), 5D(4D+Cost) simulation. Nevertheless, the overall and practical effectiveness of BIM utilization is difficult to justify at this stage. While helpful, there are some limitation when BIM applied to construction management due to the differences of data processing process between BIM and work in the field, limitations of information generated from BIM object and interoperability problem among BIM application. Therefore, this paper propose a framework integrating BIM with cost-schedule information using IFC. And we construct the system prototype based on the framework and performed case study to examine the framework. The proposed framework provides the information basis for BIM based cost-schedule integration. ultimately, the framework increase the utilization of BIM and work efficiency of construction industry by supporting an understanding of information.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.621-626
• /
• 2006

Today's commercial high resolution satellite imagery such as IKONOS and QuickBird, offers the potential to extract useful spatial information for geographical database construction and GIS applications. Extraction of 3D building information from high resolution satellite imagery is one of the most active research topics. There have been many previous works to extract 3D information based on stereo analysis, including sensor modelling. Practically, it is not easy to obtain stereo high resolution satellite images. On single image performance, most studies applied the roof-bottom points or shadow length extracted manually to sensor models with DEM. It is not suitable to apply these algorithms for dense buildings. We aim to extract 3D building information from a single satellite image in a simple and practical way. To measure as many buildings as possible, in this paper, we suggested a new way to extract building height by triangular vector structure that consists of a building bottom point, its corresponding roof point and a shadow end point. The proposed method could increase the number of measurable building, and decrease the digitizing error and the computation efficiency.

• Journal of the Geological Society of Korea
• /
• v.54 no.5
• /
• pp.545-556
• /
• 2018

This study was conducted to estimate the deep percolation using numerical modeling and field observation data based on rainfall in Haean basin. Soil moisture sensors were installed to monitoring at 30, 60 and 90 cm depths in four sites (YHS1-4) and automatic weather station was installed to around YHS3. Soil moisture and meteorological data was observed from March 25, 2017 to March 25, 2018 and May 06, 2016 to May 06, 2018, respectively. Numerical analysis was performed from June to August, 2017 using the HYDRUS-1D. Average soil moisture contents were high to generally in YHS3 for 0.300 to $0.334m^3/m^3$ and lowest in YHS1 for 0.129 to $0.265m^3/m^3$ during the soil moisture monitoring period. The results of soil moisture flow modeling showed that field observations and modeling values were similar but the peak values were larger in the modeling result. Correlation analysis between observation and modeling data showed that r, $r^2$ and RMSE were 0.88, 0.77, and 0.0096, respectively. This show high correlation and low error rate. The total deep percolation was 744.2 mm during the period of modelling at 500 cm depth. This showed that 61.3% of the precipitation amount (1,214 mm) was recharged in 2017. Deep percolation amount was high in the study area. This study is expected to provide basic data for the estimation of groundwater recharge through unsaturated zone.