• Smart Media Journal
• /
• v.11 no.10
• /
• pp.9-21
• /
• 2022

The recent expansion of the use of social media has served as an opportunity to express users' opinions in real time in various fields such as society, economy, politics, and culture, and brought many platforms that provide various information about companies. Among them, Glassdoor.com which started 2008 in US provides users with evaluations of the current and the former employees of their companies and also provides a outlooks for the company's growth Such a platform has the utility of providing necessary information to whom want to find a job or change jobs. In addition to this, variable studies have shown that the company information provided through these platforms is useful for investors as well. In this study, it was tested whether the corporate growth prospects of employees provided by Jobplanet, a platform with a typical function similar to Glassdoor.com in Korea, have predictive power to predict actual corporate growth. The forecast provided by Jobplanet and the company's financial indicator data received from FnGuide were collected and composed of panel data and analyzed using fixed effect model regression analysis. As a result, it was found that companies with positive prospects had higher employment growth than companies with negative prospects. When the outlook was neutral, the employment growth rate was higher than that of companies with a negative outlook.

• Journal of Wetlands Research
• /
• v.25 no.3
• /
• pp.167-175
• /
• 2023

Precipitation data is one of the essential input datasets used in various fields such as wetland management, hydrological simulation, and water resource management. In order to efficiently manage water resources using precipitation data, it is essential to secure as much data as possible by minimizing the missing rate of data. In addition, more efficient hydrological simulation is possible if precipitation data for ungauged areas are secured. However, missing precipitation data have been estimated mainly by statistical equations. The purpose of this study is to propose a new method to restore missing precipitation data using machine learning algorithms that can predict new data based on correlations between data. Moreover, compared to existing statistical methods, the applicability of machine learning techniques for restoring missing precipitation data is evaluated. Representative machine learning algorithms, Artificial Neural Network (ANN) and Random Forest (RF), were applied. For the performance of classifying the occurrence of precipitation, the RF algorithm has higher accuracy in classifying the occurrence of precipitation than the ANN algorithm. The F1-score and Accuracy values, which are evaluation indicators of the classification model, were calculated as 0.80 and 0.77, while the ANN was calculated as 0.76 and 0.71. In addition, the performance of estimating precipitation also showed higher accuracy in RF than in ANN algorithm. The RMSE of the RF and ANN algorithms was 2.8 mm/day and 2.9 mm/day, and the values were calculated as 0.68 and 0.73.

• Journal of Korean Port Research
• /
• v.11 no.2
• /
• pp.231-240
• /
• 1997

In the United States, a number of ocean outfalls discharge primary treated effluent into deep sea water and contribute for more efficient wastewater treatment. The long multiport diffuser connected by long pipe from a treatment plant discharge wastewater into deep water due to the steep slope of the sea bed. However, Plume discharged from the diffuser can have significant impacts on coastal communities and possibly immediate consequence on public health. Therefore, there have been growing interests about the dynamics of plume in the vicinity of the ocean outfalls. It is expected that the ocean outfall should be considered for more efficient and reliable wastewater treatments as soon as possible around coastal area in South Korea. A number of studies of plume ynamics have used various models to predict plume behavior. However, in many cases, the calculated values of plume behavior are in significantly poor agreement with realistic values. Therefore, in this study, it is recommended that improvements should be made in the application of the plume model to more simulate the actual discharge characteristics and ocean conditions. It should be noted that input parameters in plume models reflect realistic ocean conditions like waves as well as currents. In this study, as one of the new parameters, current and long wave-influenced plume rise and initial dilution have been taken into account by using simple linear wave theory under some specific assumptions for more reliable plume behavior description. Among the improved plume models approved by EPA (Environmental Protection Agency), the RSB(Roberts-Snyder-Baurngartner) and UM(Updated Merge) models were chosen for the calculation of plume behavior, and the variation calculated by both models on the basis of long period wave was compared in terms of plume rise and initial dilution.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.285-292
• /
• 2023

Recently, the impact of fine dust on health has become a major topic. Fine dust is dangerous because it can penetrate the body and affect the respiratory system, without being filtered out by the mucous membrane in the nose. Since fine dust is directly related to the industry, it is practically impossible to completely remove it. Therefore, if the concentration of fine dust can be predicted in advance, pre-emptive measures can be taken to minimize its impact on the human body. Fine dust can travel over 600km in a day, so it not only affects neighboring areas, but also distant regions. In this paper, wind direction and speed data and a time series prediction model were used to predict the concentration of fine dust in Seoul, and the correlation between the concentration of fine dust in Seoul and the concentration in each region was confirmed. In addition, predictions were made using the concentration of fine dust in each region and in Seoul. The lowest MAE (mean absolute error) in the prediction results was 12.13, which was about 15.17% better than the MAE of 14.3 presented in previous studies.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.61-68
• /
• 2023

As global growth has gradually declined, the Customer to Customer (C2C) market has expanded. And the growth potential of the C2C market is getting higher than in the past. Therefore, in this study, we examined what factors affect the price of used products within the C2C market. In order to examine the factors, we used data provided by Kaggle, which is a data science platform, and Mercari, Japan's largest C2C community marketplace platform. In research methods, the characteristics of the products were selected such as product categories, product status, shipping costs, product brands, and the data were analyzed using a linear mixing model to predict the price of C2C used goods. As a result, the variable that most affected the price was the shipping cost. When the seller paid for the shipping cost, the price would drop more than if the buyer had to pay. This study has been shown that the shipping costs is also an important factor in the used market, which can provide practical implications for customers of real transactions.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.2
• /
• pp.45-54
• /
• 2010

The SCW numerical model described in the companion paper was used to carry out a comprehensive parametric study to evaluate the performance of the SCW. The five ground related parameters, which are porosity, hydraulic conductivity, thermal conductivity, specific heat, geothermal gradient, and five SCW design parameters, which are pumping rate, well depth, well diameter, dip tube diameter, bleeding rate, were used in the study. Two types of numerical simulations were performed. The first type was used to perform short-term (24-hour) simulation, while the second type 14 day simulation. The study results indicate that the parameters that have important influence on the performance of SCW were hydraulic conductivity, thermal conductivity, geothermal gradient, pumping rate, and bleeding rate. The thermal conductivity had the most important influence on the performance of the SCW. With the increase in the geothermal gradient, the performance increased in the heat mode, but decreased in the cooling mode. The hydraulic conductivity influenced the performance when the value was larger than $10^{-4}m/s$. The depth of the well increased the performance, but at the cost of increased cost of boring. The bleeding had an important influence on SCW, greatly enhancing the performance at a limited increased cost of operation. Overall, this study showed that various factors had a cumulative influence on the performance of the SCW, and a numerical simulation can be used to accurately predict the performance of the SCW.

• Journal of the Korean Geotechnical Society
• /
• v.38 no.3
• /
• pp.35-42
• /
• 2022

The N-value from the Standard Penetration Test (SPT), which is one of the representative in-situ test, is an important index that provides basic geological information and the depth of the bearing layer for the design of geotechnical structures. In the aspect of time and cost-effectiveness, there is a need to carry out a representative sampling test. However, the various variability and uncertainty are existing in the soil layer, so it is difficult to grasp the characteristics of the entire field from the limited test results. Thus the spatial interpolation techniques such as Kriging and IDW (inverse distance weighted) have been used for predicting unknown point from existing data. Recently, in order to increase the accuracy of interpolation results, studies that combine the geotechnics and deep learning method have been conducted. In this study, based on the SPT results of about 22,000 holes of ground survey, a comparative study was conducted to predict the depth of the bearing layer using deep learning methods and IDW. The average error among the prediction results of the bearing layer of each analysis model was 3.01 m for IDW, 3.22 m and 2.46 m for fully connected network and PointNet, respectively. The standard deviation was 3.99 for IDW, 3.95 and 3.54 for fully connected network and PointNet. As a result, the point net deep learing algorithm showed improved results compared to IDW and other deep learning method.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.3
• /
• pp.73-82
• /
• 2022

Auto-scaling is one of the most important functions for cloud computing technology. Even if the number of users or service requests is explosively increased or decreased, system resources and service instances can be appropriately expanded or reduced to provide services suitable for the situation and it can improves stability and cost-effectiveness. However, since the policy is performed based on a single metric data at the time of monitoring a specific system resource, there is a problem that the service is already affected or the service instance that is actually needed cannot be managed in detail. To solve this problem, in this paper, we propose a method to predict system resource and service response time using a multivariate time series analysis model and establish an auto-scaling policy based on this. To verify this, implement it as a custom scheduler in the Kubernetes environment and compare it with the Kubernetes default auto-scaling method through experiments. The proposed method utilizes predictive data based on the impact between system resources and response time to preemptively execute auto-scaling for expected situations, thereby securing system stability and providing as much as necessary within the scope of not degrading service quality. It shows results that allow you to manage instances in detail.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.3
• /
• pp.250-261
• /
• 2023

In this study, the noise contributions by the duct, stator and rotor, which are the propulsor components, are evaluated to identify the flow noise source in cavitation and non-cavitation conditions on pumpjet propulsion and the noise levels in both conditions are compared. The unsteady incompressible Reynolds averaged Navier-Stokes (RANS) equation based on the homogeneous mixture assumption is applied on the suboff submarine hull and pumpjet propeller in the cavitation tunnel, and the Volume of Fluid (VOF) method and Schnerr-Sauer cavitation model are used to describe the two-phase flow. Based on the flow simulation results, the acoustic analogy formulated by Ffowcs Williams and Hawkings (FW-H) equation is applied to predict the underwater radiated noise. The noise contributions are evaluated by using the three types of impermeable integral surface on the duct, stator and rotor, and the two types of permeable integral surface surrounding the propulsor. As a result of noise prediction, the contribution by the stator is insignificant, but it affects the generation of flow noise source due to flow separation in the duct and rotor, and the noise is predominantly radiated into the upward and right where the flow separations are. Also, the noise is radiated into the thrust direction due to pressure fluctuation between suction and pressure sides on the rotor blades, and the it can be seen that the cavitation effect into the noise can be considered through the permeable integral surface.

• Nuclear Engineering and Technology
• /
• v.55 no.4
• /
• pp.1460-1467
• /
• 2023

A robust approach was conducted to determining the absolute oral bioavailable (f_ab) fractions of ²³⁸U and ²³²Th in rats exposed to contaminated soil along with their hematotoxicity and nephrotoxicity. The soil sample is the International Atomic Energy Agency-312 (IAEA-312) certified reference material, whereas blood, bones, and kidneys of in vivo female Sprague-Dawley (SD) rats estimate ²³⁸U- and ²³²Th-f_ab fractions post-exposure. We predict the bioavailable concentration (C_ab) and f_ab values of ²³⁸U and ²³²Th after acute soil ingestion. The blood ²³⁸U (0.750%) and ²³²Th (0.028%) reach their maximum f_ab values after 48 h. The ²³⁸U (f_ab: 0.169-0.652%) accumulates mostly in the kidney, whereas the ²³²Th (f_ab: 0.004-0.021%) accumulates primarily in the bone. Additionally, ²³⁸U is more bioavailable than ²³²Th. Post 48 h acute ingestion demonstrates noticeable histopathological and hematological alterations, implying that intake of ²³⁸U in co-contaminated soil can lead to erythrocytes and proximal tubules damage, whereas, ²³²Th intake can harm erythrocytes. Our study provides new directions for future research into the health implications of acute oral exposures to ²³⁸U and ²³²Th in co-contaminated soils. The findings offer significant insight into the utilization of in vivo SD rat testing to estimate ²³⁸U and ²³²Th bioavailability and toxicity in exposure assessment.