• Journal of Korea Water Resources Association
• /
• v.54 no.12
• /
• pp.1275-1284
• /
• 2021

This paper presents a machine learning technique applied to prediction of time-dependent local scour around bridge piers in both non-cohesive and cohesive beds. The support vector machines (SVM), which is known to be free from overfitting, is used. The time-dependent scour depths are expressed by 7 and 9 variables for the non-cohesive and cohesive beds, respectively. The SVM models are trained and validated with time series data from different sources of experiments. Resulting Mean Absolute Percentage Error (MAPE) indicates that the models are trained and validated properly. Comparisons are made with the results from Choi and Choi's formula and Scour Rate in Cohesive Soils (SRICOS) method by Briaud et al., as well as measured data. This study reveals that the SVM is capable of predicting time-dependent local scour in both non-cohesive and cohesive beds under the condition that sufficient data of good quality are provided.

• Computers and Concrete
• /
• v.24 no.2
• /
• pp.151-158
• /
• 2019

The sustainable development principle of replacing natural resources with renewable material is an important research topic. In this study, waste LCD (liquid crystal display) glass powder was used to replace cement (0%, 10%, 20% and 30%) through a volumetric method using three water-binder ratios (0.47, 0.59, and 0.71) to make cement mortar. The compressive strength was tested at the ages of 7, 28, 56 and 91 days. The test results show that the compressive strength increases with age but decreases as the water-binder ratio increases. The compressive strength slightly decreases with an increase in the replacement of LCD glass powder at a curing age of 7 days. However, at a curing age of 91 days, the compressive strength is slightly greater than that for the control group (glass powder is 0%). When the water-binder ratios are 0.47, 0.59 and 0.71, the compressive strength of the various replacements increases by 1.38-1.61 times, 1.56-1.80 times and 1.45-2.20 times, respectively, during the aging process from day 7 to day 91. Furthermore, a prediction model of the compressive strength of a cement mortar with waste LCD glass powder was deduced in this study. According to the comparison between the prediction analysis values and test results, the MAPE (mean absolute percentage error) values of the compressive strength are between 2.79% and 5.29%, and less than 10%. Thus, the analytical model established in this study has a good forecasting accuracy. Therefore, the proposed model can be used as a reliable tool for assessing the design strength of cement mortar from early age test results.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.813-824
• /
• 2021

To improve educational performance by analyzing the learning trends of adult learners of Open High Schools, various algorithm models using artificial intelligence were designed and performance was evaluated by applying them to real data. We analyzed Log data of 115 adult learners in the cyber education system of Open High Schools. Most adult learners of Open High Schools learned more than recommended learning time, but at the end of the semester, the actual learning time was significantly reduced compared to the recommended learning time. In the second half of learning, the participation rate of VODs, formation assessments, and learning activities also decreased. Therefore, in order to improve educational performance, learning time should be supported to continue in the second half. In the latter half, we developed an artificial intelligence algorithm models using Tensorflow to predict learning time by data they started taking the course. As a result, when using CNN(Convolutional Neural Network) model to predict single or multiple outputs, the mean-absolute-error is lowest compared to other models.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.12
• /
• pp.419-430
• /
• 2020

This paper investigated methods to improve the forecasting accuracy of the electricity consumption prediction model. Currently, the demand for electricity has continuously been rising more than ever. Since the industrial sector uses more electricity than any other sectors, the importance of a more precise forecasting model for manufacturing sites has been highlighted to lower the excess energy production. We propose a double encoder-decoder model, which uses two separate encoders and one decoder, in order to adapt both long-term and short-term data for better forecasts. We evaluated our proposed model on our electricity power consumption dataset, which was collected in a manufacturing site of Sehong from January 1st, 2019 to June 30th, 2019 with 1 minute time interval. From the experiment, the double encoder-decoder model marked about 10% reduction in mean absolute error percentage compared to a conventional encoder-decoder model. This result indicates that the proposed model forecasts electricity consumption more accurately on manufacturing sites compared to an encoder-decoder model.

• Journal of Navigation and Port Research
• /
• v.44 no.6
• /
• pp.517-523
• /
• 2020

Pyeongtaek·Dangjin port handles the largest volume of finished vehicles in Korea, including more than 95% of imported cars. However, since the volume of imported cars has been stagnant since 2015, officials planning to invest in port development or automobile-related industries must make new forecasts. Economic variables such as the GDP often have been used in predicting automobile volume, but prior research showed that the impact of these economic variables on automobile volume I has been gradually decreasing in developed countries. These variables remain important predictors, however, in developing countries that experience rapid economic growth. In this study, predicting the volume of imported passenger cars at Pyeongtaek·Dangjin port, the decreasing Korean population was a major factor we considered. Our forecast showed that the volume of imported passenger cars at Pyeongtaek·Dangjin port will gradually decrease -by 2021. The Mean Absolute Percentage Error (MAPE) verification was performed to measure the accuracy of the predicted results, and the scenario analysis was performed on the share of imported passenger cars.

• Journal of the Institute of Convergence Signal Processing
• /
• v.22 no.2
• /
• pp.79-84
• /
• 2021

The most important device of the AGV is the guide sensor, and the typical function of this sensor is high accuracy and extraction of the road. If the accuracy of the guide sensor is low or the sensor device is extracted the wrong track, this causes the problems such as the AGV collision, track-out, the load falling due to AGV swing. In order to improve these problems, this study is proposed a signal processing method of the guide sensor based on multi-maskings and the center of gravity method, and evaluated its performance. As a result, the proposed method showed that the mean error of absolute value is 2.32[mm] and it showed performance improvement of 27[%] than the center of gravity method of existence. Therefore, when the proposed signal processing method is applied, It is thought that the posture control and driving stability of the AGV will be improved.

• Journal of the Economic Geographical Society of Korea
• /
• v.25 no.1
• /
• pp.171-181
• /
• 2022

The real estate price index plays key roles as quantitative data in real estate market analysis. International organizations including OECD publish the real estate price indexes by country, and the Korea Real Estate Board announces metropolitan-level and municipal-level indexes. However, when the index is set on the smaller spatial unit level than metropolitan and municipal-level, problems occur: missing values. As the spatial scope is narrowed down, there are cases where there are few or no transactions depending on the unit period, which lead index calculation difficult or even impossible. This study suggests a supervised learning-based machine learning model to compensate for missing values that may occur due to no transaction in a specific range and period. The models proposed in our research verify the accuracy of predicting the existing values and missing values.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.3
• /
• pp.63-73
• /
• 2022

A more accurate understanding of the irrigation water supply is necessary for efficient agricultural water management. Although we measure water levels in an irrigation canal using ultrasonic water level gauges, some errors occur due to malfunctions or the surrounding environment. This study aims to apply CNN (Convolutional Neural Network) Deep-learning-based image classification and segmentation models to the irrigation canal's CCTV (Closed-Circuit Television) images. The CCTV images were acquired from the irrigation canal of the agricultural reservoir in Cheorwon-gun, Gangwon-do. We used the ResNet-50 model for the image classification model and the U-Net model for the image segmentation model. Using the Natural Breaks algorithm, we divided water level data into 2, 4, and 8 groups for image classification models. The classification models of 2, 4, and 8 groups showed the accuracy of 1.000, 0.987, and 0.634, respectively. The image segmentation model showed a Dice score of 0.998 and predicted water levels showed R² of 0.97 and MAE (Mean Absolute Error) of 0.02 m. The image classification models can be applied to the automatic gate-controller at four divisions of water levels. Also, the image segmentation model results can be applied to the alternative measurement for ultrasonic water gauges. We expect that the results of this study can provide a more scientific and efficient approach for agricultural water management.

• Korean Journal of Materials Research
• /
• v.32 no.8
• /
• pp.345-353
• /
• 2022

In this study, using deep learning, super-resolution images of transmission electron microscope (TEM) images were generated for nanomaterial analysis. 1169 paired images with 256 × 256 pixels (high resolution: HR) from TEM measurements and 32 × 32 pixels (low resolution: LR) produced using the python module openCV were trained with deep learning models. The TEM images were related to DyVO₄ nanomaterials synthesized by hydrothermal methods. Mean-absolute-error (MAE), peak-signal-to-noise-ratio (PSNR), and structural similarity (SSIM) were used as metrics to evaluate the performance of the models. First, a super-resolution image (SR) was obtained using the traditional interpolation method used in computer vision. In the SR image at low magnification, the shape of the nanomaterial improved. However, the SR images at medium and high magnification failed to show the characteristics of the lattice of the nanomaterials. Second, to obtain a SR image, the deep learning model includes a residual network which reduces the loss of spatial information in the convolutional process of obtaining a feature map. In the process of optimizing the deep learning model, it was confirmed that the performance of the model improved as the number of data increased. In addition, by optimizing the deep learning model using the loss function, including MAE and SSIM at the same time, improved results of the nanomaterial lattice in SR images were achieved at medium and high magnifications. The final proposed deep learning model used four residual blocks to obtain the characteristic map of the low-resolution image, and the super-resolution image was completed using Upsampling2D and the residual block three times.