• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.11
• /
• pp.479-486
• /
• 2019

The caps foundation method can reduce the load of a building by using the arching effect, but verification of the method is still insufficient. In this paper, a model test was performed to quantitatively prove the load reduction effect by this method. The test was carried out using six conditions according to the size of caps foundation block and the area of the loading plate. The test results show that the earth pressure was the highest at the position closest to the loading point regardless of the size of caps foundation block and the area of the loading plate. At the highest earth pressure position, when the loading plate area was 30 cm × 30 cm, the earth pressure of a small block was reduced by 35.4% on average, and that of a big block was reduced by 39.7% compared to the pressure with no block. When the loading plate area was 60 cm × 60 cm, the earth pressure of the small block was reduced by 33.9% on average, and the earth pressure of the big block was reduced by 42.7%. Therefore, if the caps foundation method is applied, the load will be reduced by more than 33% for a small block and 39% for a big block.

• Information Systems Review
• /
• v.22 no.1
• /
• pp.59-72
• /
• 2020

Artificial Intelligence is establishing itself as a familiar tool from an intractable concept. In this trend, financial sector is also looking to improve the problem of existing system which includes Fraud Detection System (FDS). It is being difficult to detect sophisticated cyber financial fraud using original rule-based FDS. This is because diversification of payment environment and increasing number of electronic financial transactions has been emerged. In order to overcome present FDS, this paper suggests 3 types of artificial intelligence models, Generative Adversarial Network (GAN), Deep Neural Network (DNN), and Convolutional Neural Network (CNN). GAN proves how data imbalance problem can be developed while DNN and CNN show how abnormal financial trading patterns can be precisely detected. In conclusion, among the experiments on this paper, WGAN has the highest improvement effects on data imbalance problem. DNN model reflects more effects on fraud classification comparatively.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.2
• /
• pp.507-519
• /
• 2013

This study is to evaluate agricultural water supply capacity in Geum river basin (9,865 $km^2$), one of the 5 big river basin of South Korea using MODSIM-DSS (MODified SIMyld-Decision Support System) model. The model is a generalized river basin decision support system and network flow model developed at Colorado State University designed specifically to meet the growing demands and pressures on river basin management. The model was established by dividing the basin into 14 subbasins and the irrigation facilities viz. agricultural reservoirs, pumping stations, diversions, culverts and groundwater wells were grouped and networked within each subbasin and networked between subbasins including municipal and industrial water supplies. To prepare the inflows to agricultural reservoirs and multipurpose dams, the Soil and Water Assessment Tool (SWAT) was calibrated using 6 years (2005-2010) observed dam inflow and storage data. By MODSIM run for 8 years from 2004 to 2011, the agricultural water shortage had occurred during the drought years of 2006, 2008, and 2009. The agricultural water shortage could be calculated as 282 $10^6m^3$, 286 $10^6m^3$, and 329 $10^6m^3$ respectively.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.1
• /
• pp.135-159
• /
• 2021

The purpose of this study is to derive the implications needed to improve reading and information literacy and provide information services for students and citizens through changes in the concept of PISA 2018 Reading Literacy and its Assessment Framework analysis. The findings of the study are as follows. First, meaning of PISA Reading Literacy concept has changed along with the changes of the social and technological environments. Second, concept and assessment framework included the whole process of reading. Third, the Assessment Framework included a number of factors similar to the cognitive process of the information literacy model like Big6 Skills, but also there were differences. Fourth, the digital reading is reflected in the Assessment Framework. The PISA 2018 Reading Literacy Assessment Framework provides implications for the standards and methods required for librarians to develop reading and information literacy models and assessment frameworks to improve citizens' reading and information literacy, and to provide information services to them.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1123-1130
• /
• 2020

This study aims to classify the severity in car crashes using five classification learning models. The dataset used in this study contains 21,013 vehicle crashes, obtained from Korea Expressway Corporation, between the year of 2015-2017 and the LightGBM(Light Gradient Boosting Model) performed well with the highest accuracy. LightGBM, the number of involved vehicles, type of accident, incident location, incident lane type, types of accidents, types of vehicles involved in accidents were shown as priority factors. Based on the results of this model, the establishment of a management strategy for response of highway traffic accident should be presented through a consistent prediction process of accident severity level. This study identifies applicability of Machine Learning Models for Predicting of the Severity of Car Traffic Accidents on a Highway and suggests that various machine learning techniques based on big data that can be used in the future.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.31 no.6B
• /
• pp.515-522
• /
• 2011

The hydrodynamic models are widely used in the research for analysis of flow characteristics and design of hydraulic structure and river channel. These models need to be calibrated with observed data. But, there are few field data of two-dimensional flow velocity in flood because the direct measurement of the flood flow velocity are very dangerous. For this reason the results of two-dimensional numerical models are usually calibrated and verified with only a few observed data. Moreover, the verification of numerical models for the design flood is usually carried out using the result of one-dimensional model, HEC-RAS. In this study, using the flow velocity profile extracted from the aerial photos of a flood of the Tone River in Japan, two-dimensional numerical models, RAM2 in RAMS, RMA2 in SMS, and one-dimensional numerical model, HEC-RAS which are most widely used in research and design work are verified and the validity for verification of two-dimensional models with HEC-RAS is reviewed. The results showed that the water surface elevation of HEC-RAS, RAM2 and RMA2 models have similar results with observed data. But, the velocity results of RAM2 and RMA2 models in the floodplain have some difference with the velocity from aerial photo analysis. And the velocity result of HEC-RAS has big difference with the sectional averaged value of velocity from aerial photo analysis.

• The Journal of the Korea Contents Association
• /
• v.19 no.6
• /
• pp.10-23
• /
• 2019

Although social big data can provide a multi-faceted perspective on school bullying experiences among children and adolescents, the complexity and variety of unstructured text presents a challenge for systematic collection and analysis of the data. Development of an ontology, which identifies key terms and their intricate relationships, is crucial for extracting key concepts and effectively collecting data. The current study elaborated on the definition of an ontology, carefully described the 7 stage development process, and applied the ontology for collecting and analyzing school bullying social big data. As a result, approximately 2,400 key terms were extracted in top-, middle-, and lower-level categories, concerning domains of participants, causes, types, location, region, and intervention. The study contributes to the literature by explaining the ontology development process and proposing a novel alternative research model that uses social big data in school bullying research. Findings from this ontology study may provide a basis for social big data research. Practical implications of this study lie in not only helping to understand the experience of school bullying participants, but also in offering a macro perspective on school bullying as a social phenomenon.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.33 no.6
• /
• pp.333-344
• /
• 2021

Technique for the long-gap filling that occur frequently in ocean monitoring data is developed. The method estimates the unknown values of the long-gap by the summation of the estimated trend and selected residual components of the given missing intervals. The method was used to impute the data of the long-term missing interval of about 1 month, such as temperature and water temperature of the Ulleungdo ocean buoy data. The imputed data showed differences depending on the monitoring parameters, but it was found that the variation pattern was appropriately reproduced. Although this method causes bias and variance errors due to trend and residual components estimation, it was found that the bias error of statistical measure estimation due to long-term missing is greatly reduced. The mean, and the 90% confidence intervals of the gap-filling model's RMS errors are 0.93 and 0.35~1.95, respectively.

• Journal of Digital Convergence
• /
• v.15 no.11
• /
• pp.245-250
• /
• 2017

Flash floods is defined as the flooding of intense rainfall over a relatively small area that flows through river and valley rapidly in short time with no advance warning. So that it can cause damage property and casuality. This study is to establish the flash-flood warning system using 38 accident data, reported from the National Disaster Information Center and Land Surface Model(TOPLATS) between 2009 and 2012. Three variables were used in the Land Surface Model: precipitation, soil moisture, and surface runoff. The three variables of 6 hours preceding flash flood were reduced to 3 factors through factor analysis. Decision tree, random forest, Naive Bayes, Support Vector Machine, and logistic regression model are considered as big data methods. The prediction performance was evaluated by comparison of Accuracy, Kappa, TP Rate, FP Rate and F-Measure. The best method was suggested based on reproducibility evaluation at the each points of flash flood occurrence and predicted count versus actual count using 4 years data.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.37 no.6
• /
• pp.1033-1041
• /
• 2017

Path travel time based on departure time (PTTDP) is key information in advanced traveler information systems (ATIS). Despite the necessity, forecasting PTTDP is still one of challenges which should be successfully conquered in the forecasting area of intelligent transportation systems (ITS). To address this problem effectively, a methodology to dynamically predict PTTDP between motorway interchanges is proposed in this paper. The method was developed based on the relationships between traffic demands at motorway tollgates and PTTDPs between TGs in the motorway network. Two different data were used as the input of the model: traffic demand data and path travel time data are collected by toll collection system (TCS) and dedicated short range communication (DSRC), respectively. The proposed model was developed based on k-nearest neighbor, one of data mining techniques, in order for the real applications of motorway information systems. In a feasible test with real-world data, the proposed method performed effectively by means of prediction reliability and computational running time to the level of real application of current ATIS.