• Journal of Korea Port Economic Association
• /
• v.32 no.4
• /
• pp.1-13
• /
• 2016

This study attempts to establish a precise forecast model for the container inventory demand of shipping companies through forecasts based on equipment type/size, ports, and weekly system dynamics. The forecast subjects were Shanghai and Yantian Ports. Only dry containers (20, 40) and high cubes (40) were used as the subject container inventory in this study due to their large demand and valid data computation. The simulation period was from 2011 to 2017 and weekly data were used, applying the actual data frequency among shipping companies. The results of the model accuracy test obtained through an application of Mean Absolute Percentage Error (MAPE) verified that the forecast model for dry 40' demand, dry 40' high cube demand, dry 20' supply, dry 40' supply, and dry 40' high cube supply in Shanghai Port provided an accurate prediction, with $0%{\leq}MAPE{\leq}10%$. The forecast model for supply and demand in Shanghai Port was otherwise verified to have relatively high prediction power, with $10%{\leq}MAPE{\leq}20%$. The forecast model for dry 40' high cube demand and dry 20' supply in Yantian Port was accurate, with $0%{\leq}MAPE{\leq}10%$. The forecast model for supply and demand in Yantian Port was generally verified to have relatively high prediction power, with $10%{\leq}MAPE{\leq}20%$. The forecast model in this study also had relatively high accuracy when compared with the actueal data managed in shipping companies.

• Journal of Korea Port Economic Association
• /
• v.26 no.4
• /
• pp.207-218
• /
• 2010

The purpose of the study is to predict the shipping business during the period of 2011 using the ARIMA-type models. This include the ARIMA and Intervention-ARIMA models. The multivariate cause-effect econometric model is not employed for not assuring a higher degree of forecasting accuracy than the univariate variable model. Such a cause-effect econometric model also fails in adjusting itself for the post-sample. This article introduces the four ARIMA models and six Intervention-ARIMA models. The monthly data cover the period January 2000 through October 2010. The out-of-sample forecasting performance is compared between the ARIMA-type models and the random walk model. Forecasting performance is measured by three summary statistics: root mean squared percent error, mean absolute percent error and mean percent error. The root mean squared percent errors of all the ARIMA-type models are somewhat higher than normally expected. Furthermore, the random walk model outperforms all the ARIMA-type models. This reveals that the BDI is just a random walk phenomenon and it's meaningless to predict the BDI using various econometric techniques. The ARIMA-type models show that the shipping market is expected to be bearish in 2011. These pessimistic ex-ante forecasts are supported by the Hodrick-Prescott filtering technique.

• Advances in concrete construction
• /
• v.10 no.6
• /
• pp.479-488
• /
• 2020

The experimental and numerical works were carried out on high performance fiber reinforced concrete (HPFRC) with w/cm ratios ranging from 0.25 to 0.40, fiber volume fraction (Vf)=0-1.5% and 10% silica fume replacement. Improvements in compressive and flexural strengths obtained for HPFRC are moderate and significant, respectively, Empirical equations developed for the compressive strength and flexural strength of HPFRC as a function of fiber volume fraction. A relation between flexural strength and compressive strength of HPFRC with R=0.78 was developed. Due to the complex mix proportions and non-linear relationship between the mix proportions and properties, models with reliable predictive capabilities are not developed and also research on HPFRC was empirical. In this paper due to the inadequacy of present method, a back propagation-neural network (BP-NN) was employed to estimate the 28-day compressive strength of HPFRC mixes. BP-NN model was built to implement the highly non-linear relationship between the mix proportions and their properties. This paper describes the data sets collected, training of ANNs and comparison of the experimental results obtained for various mixtures. On statistical analyses of collected data, a multiple linear regression (MLR) model with R2=0.78 was developed for the prediction of compressive strength of HPFRC mixes, and average absolute error (AAE) obtained is 6.5%. On validation of the data sets by NNs, the error range was within 2% of the actual values. ANN model has given the significant degree of accuracy and reliability compared to the MLR model. ANN approach can be effectively used to estimate the 28-day compressive strength of fibrous concrete mixes and is practical.

• Membrane Journal
• /
• v.33 no.1
• /
• pp.34-45
• /
• 2023

Two computational intelligence techniques namely artificial neural networks (ANN) and support vector machine (SVM) are employed to model the permeate flux based on seven input variables including time, transmembrane pressure, rotating velocity, the pore diameter of the membrane, dynamic viscosity, concentration and density of the feed fluid. The best-fit model was selected through the trial-error method and the two statistical parameters including the coefficient of determination (R²) and the average absolute relative deviation (AARD) between the experimental and predicted data. The obtained results reveal that the optimized ANN model can predict the permeate flux with R² = 0.999 and AARD% = 2.245 versus the SVM model with R² = 0.996 and AARD% = 4.09. Thus, the ANN model is found to predict the permeate flux with high accuracy in comparison to the SVM approach.

• The Journal of Korean Academy of Prosthodontics
• /
• v.54 no.3
• /
• pp.210-217
• /
• 2016

Purpose: The aim of this study was to evaluate the marginal and internal adaptation of monolithic zirconia restoration made without physical model by digital intraoral scanner. Materials and methods: A prospective clinical trial was performed on 11 restorations as a pilot study. The monolithic zirconia restorations were fabricated after digital intraoral impression taking by intraoral scanner (TRIOS, 3shape, Copenhagen, Denmark), computer-aided designing, and milling manufacturing process. Completed zirconia crowns were tried in the patients' mouth and a replica technique was used to acquire the crown-abutment replica. The absolute marginal discrepancy, marginal gap, and internal gap of axial, line angle, and occlusal part were measured after sectioning the replica in the mesiodistal and buccolingual direction. Statistical analysis was performed using Kruskal-Wallis and Mann-Whitney U test (${\alpha}=.05$). Results: From the adaptation analysis by replica, the statistically significant difference was not found between mesiodistal and buccolingual sections (P>.05), but there was significant difference among the measurement location (P<.01). The amount of absolute marginal discrepancy was larger than those of marginal gap and internal gap (P<.01). Conclusion: Within the limitations of this study, the adaptation accuracy of model-free monolithic zirconia restoration fabricated by intraoral scanner exhibited clinically acceptable result. However, the margin of zirconia crown showed tendency of overcontour and cautious clinical application and follow up is necessary.

• Journal of the Korean Geotechnical Society
• /
• v.35 no.11
• /
• pp.51-62
• /
• 2019

In this study, a simple method to estimate the soil water content variation in a wide area was proposed using hyperspectral near-infrared images. The reflectance data of a sand, granite soils, and a kaolinite were measured by reflecting the soil samples with different wavelengths in the visible and near-infrared (VNIR) regions using hyperspectral cameras. The measured reflectances and parameters were used to build a water content prediction model using the Partial Least Square Regression (PLSR) analysis. In the water content prediction model, the Area of Reflectance (Near-infrared, NIR) parameter was the most suitable parameter to determine the water content. The parameter was applicable regardless of the soil type, as the coefficient of determination (R²) exceeded 0.9 for each soil sample. Additionally, the mean absolute percentage error (MAPE) was less than 15% when compared with the actual water content of the soil. Therefore, the predictability of water content variation for soils with water content lower than 50% was confirmed. Accordingly through this study, the predictability of water content variation in several soil types using the hyperspectral near-infrared images was confirmed. For further development, a model that incorporates soil classification would be required to improve the accuracy of the model and to predict higher range of water contents.

• Korean Journal of Cognitive Science
• /
• v.23 no.3
• /
• pp.409-424
• /
• 2012

The purpose of the present study was to examine if perception of visual coordination pattern is consistent with the prediction of the HKB model (Haken, Kelso, Bunz, 1985). In addition, this study aimed to see if an additional sensory information using a grid background stabilizes perception of coordination pattern. Participants joined one of two experimental groups, Normal background and Grid background, to participate the pattern recognition training session and the pattern judgment test session. Participants observed $0^{\circ}$, $18^{\circ}$, $36^{\circ}$, $54^{\circ}$, $72^{\circ}$, $90^{\circ}$, $108^{\circ}$, $126^{\circ}$, $144^{\circ}$, $162^{\circ}$, and $180^{\circ}$ coordination patterns characterized by two oscillating dots. The dots oscillated in 0.25 Hz for the pattern recognition training and in 0.5 Hz, 1 Hz, and 2 Hz for the pattern judgment test. Judgment score, absolute judgment error, and judgment stability out of the pattern judgment test were analyzed statistically. The landscape of pattern accuracy and stability data was "inverted-U" shape with slower oscillating frequency conditions. In the faster condition, the accuracy and stability of the judgment decreased with relative phase patterns near $180^{\circ}$. These findings consistent with the prediction of the HKB model. The grid as additional sensory information did not increase accuracy and stability in coordination perception.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.8-15
• /
• 2020

A forecasting method using deep learning does not have consistent results due to the differences in the characteristics of the dataset, even though they have the same forecasting models and parameters. For example, the forecasting model X optimized with dataset A would not produce the optimized result with another dataset B. The forecasting model with the characteristics of the dataset needs to be optimized to increase the accuracy of the forecasting model. Therefore, this paper proposes novel optimization steps for outlier removal, dataset classification, and a CNN-LSTM-based hyperparameter tuning process to forecast the daily power usage of a university campus based on the hourly interval. The proposing model produces high forecasting accuracy with a 2% of MAPE with a single power input variable. The proposing model can be used in EMS to suggest improved strategies to users and consequently to improve the power efficiency.

• Genomics & Informatics
• /
• v.17 no.4
• /
• pp.47.1-47.12
• /
• 2019

The achievements of genome-wide association studies have suggested ways to predict diseases, such as type 2 diabetes (T2D), using single-nucleotide polymorphisms (SNPs). Most T2D risk prediction models have used SNPs in combination with demographic variables. However, it is difficult to evaluate the pure additive contribution of genetic variants to classically used demographic models. Since prediction models include some heritable traits, such as body mass index, the contribution of SNPs using unmatched case-control samples may be underestimated. In this article, we propose a method that uses propensity score matching to avoid underestimation by matching case and control samples, thereby determining the pure additive contribution of SNPs. To illustrate the proposed propensity score matching method, we used SNP data from the Korea Association Resources project and reported SNPs from the genome-wide association study catalog. We selected various SNP sets via stepwise logistic regression (SLR), least absolute shrinkage and selection operator (LASSO), and the elastic-net (EN) algorithm. Using these SNP sets, we made predictions using SLR, LASSO, and EN as logistic regression modeling techniques. The accuracy of the predictions was compared in terms of area under the receiver operating characteristic curve (AUC). The contribution of SNPs to T2D was evaluated by the difference in the AUC between models using only demographic variables and models that included the SNPs. The largest difference among our models showed that the AUC of the model using genetic variants with demographic variables could be 0.107 higher than that of the corresponding model using only demographic variables.

• Journal of Korea Water Resources Association
• /
• v.52 no.12
• /
• pp.963-973
• /
• 2019

This study reviews a urban flooding risk criteria estimation model to predict risk criteria in areas where flood risk criteria are not precalculated by using watershed characteristic data and limit rainfall based on damage history. The risk criteria estimation model was designed using Support Vector Machine, one of the machine learning algorithms. The learning data consisted of regional limit rainfall and watershed characteristic. The learning data were applied to the SVM algorithm after normalization. We calculated the mean absolute error and standard deviation using Leave-One-Out and K-fold cross-validation algorithms and evaluated the performance of the model. In Leave-One-Out, models with small standard deviation were selected as the optimal model, and models with less folds were selected in the K-fold. The average accuracy of the selected models by rainfall duration is over 80%, suggesting that SVM can be used to estimate flooding risk criteria.