• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.528-550
• /
• 2024

Warehousing demand prediction is an essential part of the supply chain, providing a fundamental basis for product manufacturing, replenishment, warehouse planning, etc. Existing forecasting methods cannot produce accurate forecasts since warehouse demand is affected by external factors such as holidays and seasons. Some aspects, such as consumer psychology and producer reputation, are challenging to quantify. The data can fluctuate widely or do not show obvious trend cycles. We introduce a new model for warehouse demand prediction called MAGRU, which stands for Multi-layer Attention with GRU. In the model, firstly, we perform the embedding operation on the input sequence to quantify the external influences; after that, we implement an encoder using GRU and the attention mechanism. The hidden state of GRU captures essential time series. In the decoder, we use attention again to select the key hidden states among all-time slices as the data to be fed into the GRU network. Experimental results show that this model has higher accuracy than RNN, LSTM, GRU, Prophet, XGboost, and DARNN. Using mean absolute error (MAE) and symmetric mean absolute percentage error(SMAPE) to evaluate the experimental results, MAGRU's MAE, RMSE, and SMAPE decreased by 7.65%, 10.03%, and 8.87% over GRU-LSTM, the current best model for solving this type of problem.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.4
• /
• pp.161-167
• /
• 2019

Recently, demand forecasting techniques have been actively studied due to interest in stable power supply with surging power demand, and increase in spread of smart meters that enable real-time power measurement. In this study, we proceeded the deep learning prediction model experiments which learns actual measured power usage data of home and outputs the forecasting result. And we proceeded pre-processing with moving average method. The predicted value made by the model is evaluated with the actual measured data. Through this forecasting, it is possible to lower the power supply reserve ratio and reduce the waste of the unused power. In this paper, we conducted experiments on three types of networks: Multi Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short Term Memory (LSTM) and we evaluate the results of each scheme. Evaluation is conducted with following method: MSE(Mean Squared Error) method and MAE(Mean Absolute Error).

• Journal of Environmental Science International
• /
• v.27 no.7
• /
• pp.499-507
• /
• 2018

Agricultural meteorological information is an important resource that affects farmers' income, food security, and agricultural conditions. Thus, such data are used in various fields that are responsible for planning, enforcing, and evaluating agricultural policies. The meteorological information obtained from automatic weather observation systems operated by rural development agencies contains missing values owing to temporary mechanical or communication deficiencies. It is known that missing values lead to reduction in the reliability and validity of the model. In this study, the hierarchical Bayesian spatio-temporal model suggests replacements for missing values because the meteorological information includes spatio-temporal correlation. The prior distribution is very important in the Bayesian approach. However, we found a problem where the spatial decay parameter was not converged through the trace plot. A suitable spatial decay parameter, estimated on the bias of root-mean-square error (RMSE), which was determined to be the difference between the predicted and observed values. The latitude, longitude, and altitude were considered as covariates. The estimated spatial decay parameters were 0.041 and 0.039, for the spatio-temporal model with latitude and longitude and for latitude, longitude, and altitude, respectively. The posterior distributions were stable after the spatial decay parameter was fixed. root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), and bias were calculated for model validation. Finally, the missing values were generated using the independent Gaussian process model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.179-179
• /
• 2023

This study suggests a new approach of water level forecasting for extended lead times using original data preprocessing with variational mode decomposition (VMD). Here, two machine learning algorithms including light gradient boosting machine (LGBM) and random forest (RF) were considered to incorporate extended lead times (i.e., 5, 10, 15, 20, 25, 30, 40, and 50 days) forecasting of water levels. At first, the original data at two water level stations (i.e., SW173 and SW269 in Bangladesh) and their decomposed data from VMD were prepared on antecedent lag times to analyze in the datasets of different lead times. Mean absolute error (MAE), root mean squared error (RMSE), and mean squared error (MSE) were used to evaluate the performance of the machine learning models in water level forecasting. As results, it represents that the errors were minimized when the decomposed datasets were considered to predict water levels, rather than the use of original data standalone. It was also noted that LGBM produced lower MAE, RMSE, and MSE values than RF, indicating better performance. For instance, at the SW173 station, LGBM outperformed RF in both decomposed and original data with MAE values of 0.511 and 1.566, compared to RF's MAE values of 0.719 and 1.644, respectively, in a 30-day lead time. The models' performance decreased with increasing lead time, as per the study findings. In summary, preprocessing original data and utilizing machine learning models with decomposed techniques have shown promising results for water level forecasting in higher lead times. It is expected that the approach of this study can assist water management authorities in taking precautionary measures based on forecasted water levels, which is crucial for sustainable water resource utilization.

• Environmental Engineering Research
• /
• v.21 no.2
• /
• pp.171-179
• /
• 2016

This study analyzes guidelines to select optimum number of grids to represent behavior of a given water system appropriately. The EFDC model was chosen as a 3-D hydrodynamic and water quality model and salt was chosen as a surrogate variable of pollutant. The model is applied to an artificial canal that receives salt water from coastal area and fresh water from a river from respective gate according to previously developed gate operation rule. Grids are subdivided in vertical and horizontal (longitudinal) directions, respectively until no significant changes are found in salinity concentrations. The optimum grid size was determined by comparing errors in average salt concentrations between a test grid systems against the most complicated grid system. MSE (mean squared error) and MAE (mean absolute error) are used to compare errors. The CFL (Courant-Friedrichs-Lewy) number was used to determine the optimum number of grid systems for the study site though it can be used when explicit numerical method is applied only. This study suggests errors seem acceptable when both MSE and MAE are less than unity approximately.

• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.183-194
• /
• 2023

This study presents the prediction of the California bearing ratio (CBR) of coarse- and fine-grained soils using artificial intelligence technology. The group method of data handling (GMDH) algorithm, an artificial neural network-based model, was used in the prediction of the CBR values. In the design of the prediction models, various combinations of independent input variables for both coarse- and fine-grained soils have been used. The results obtained from the designed GMDH-type neural networks (GMDH-type NN) were compared with other regression models, such as linear, support vector, and multilayer perception regression methods. The performance of models was evaluated with a regression coefficient (R²), root-mean-square error (RMSE), and mean absolute error (MAE). The results showed that GMDH-type NN algorithm had higher performance than other regression methods in the prediction of CBR value for coarse- and fine-grained soils. The GMDH model had an R² of 0.938, RMSE of 1.87, and MAE of 1.48 for the input variables {G, S, and MDD} in coarse-grained soils. For fine-grained soils, it had an R² of 0.829, RMSE of 3.02, and MAE of 2.40, when using the input variables {LL, PI, MDD, and OMC}. The performance evaluations revealed that the GMDH-type NN models were effective in predicting CBR values of both coarse- and fine-grained soils.

• Journal of Sleep Medicine
• /
• v.15 no.2
• /
• pp.48-54
• /
• 2018

Objectives: The aim of this study was to develop a predicting model for the optimal continuous positive airway pressure (CPAP) for obstructive sleep apnea (OSA) patient with obesity by using a machine learning. Methods: We retrospectively investigated the medical records of 162 OSA patients who had obesity [body mass index (BMI) ≥ 25] and undertaken successful CPAP titration study. We divided the data to a training set (90%) and a test set (10%), randomly. We made a random forest model and a least absolute shrinkage and selection operator (lasso) regression model to predict the optimal pressure by using the training set, and then applied our models and previous reported equations to the test set. To compare the fitness of each models, we used a correlation coefficient (CC) and a mean absolute error (MAE). Results: The random forest model showed the best performance {CC 0.78 [95% confidence interval (CI) 0.43-0.93], MAE 1.20}. The lasso regression model also showed the improved result [CC 0.78 (95% CI 0.42-0.93), MAE 1.26] compared to the Hoffstein equation [CC 0.68 (95% CI 0.23-0.89), MAE 1.34] and the Choi's equation [CC 0.72 (95% CI 0.30-0.90), MAE 1.40]. Conclusions: Our random forest model and lasso model ($26.213+0.084{\times}BMI+0.004{\times}$apnea-hypopnea index+$0.004{\times}oxygen$ desaturation index-$0.215{\times}mean$ oxygen saturation) showed the improved performance compared to the previous reported equations. The further study for other subgroup or phenotype of OSA is required.

• Communications for Statistical Applications and Methods
• /
• v.30 no.3
• /
• pp.273-289
• /
• 2023

In this paper, we develop a new time series model for predicting IPO (initial public offering) data with non-negative integer value. The proposed model is based on integer-valued autoregressive (INAR) model with a Poisson thinning operator. Just as the heterogeneous autoregressive (HAR) model with daily, weekly and monthly averages in a form of cascade, the integer-valued heterogeneous autoregressive (INHAR) model is considered to reflect efficiently the long memory. The parameters of the INHAR model are estimated using the conditional least squares estimate and Yule-Walker estimate. Through simulations, bias and standard error are calculated to compare the performance of the estimates. Effects of model fitting to the Korea's IPO are evaluated using performance measures such as mean square error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) etc. The results show that INHAR model provides better performance than traditional INAR model. The empirical analysis of the Korea's IPO indicates that our proposed model is efficient in forecasting monthly IPO volumes.

• Geomechanics and Engineering
• /
• v.30 no.6
• /
• pp.551-564
• /
• 2022

Fragmenting the rock mass is considered as the most important work in open-pit mines. Ground vibration is the most hazardous issue of blasting which can cause critical damage to the surrounding structures. This paper focuses on developing an explicit model to predict the ground vibration through an multi objective evolutionary polynomial regression (MOGA-EPR). To this end, a database including 79 sets of data related to a quarry site in Malaysia were used. In addition, a gene expression programming (GEP) model and several empirical equations were employed to predict ground vibration, and their performances were then compared with the MOGA-EPR model using the mean absolute error (MAE), root mean square error (RMSE), mean (𝜇), standard deviation of the mean (𝜎), coefficient of determination (R²) and a20-index. Comparing the results, it was found that the MOGA-EPR model predicted the ground vibration more precisely than the GEP model and the empirical equations, where the MOGA-EPR scored lower MAE and RMSE, 𝜇 and 𝜎 closer to the optimum value, and higher R² and a20-index. Accordingly, the proposed MOGA-EPR model can be introduced as a useful method to predict ground vibration and has the capacity to be generalized to predict other blasting effects.

• 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.