• Korean Journal of Remote Sensing
• /
• v.3 no.2
• /
• pp.121-141
• /
• 1987

Many techniques of image processing have been developed to analyse more precisely geological information obtained from satellites. SPOT, which is a recent project in France, will furnish stereoscopic image, with good resolution of surfaces(20m $\times$ 20m or 10m $\times$ 10m), and give altitudes(DEM) which can be restored automatically. One of the researches for the exploitation of this data, intends to recognize and distinguish automatically the geomorphological forms, containing important geological information from DEM. Along which the information obtained obtained from image processing, it will play an important role in the understanding of the surface of the terrain. This study was carried out in collaboration with University of Paris-6 and Ecole National des Sciences G$\'{e}$ographiques(Institute G$\'{e}$ographique National of France: IGN).

• Proceedings of the Korea Water Resources Association Conference
• /
• 2015.05a
• /
• pp.226-226
• /
• 2015

The complex climate system regarding human actions is well represented through global climate models (GCMs). The output from GCMs provides useful information about the rate and magnitude of future climate change. Especially, the temperature variable is most reliable among other GCM outputs. However, hydrological variables (e.g. precipitation) from GCM outputs for future climate change contain too high uncertainty to use in practice. Therefore, we propose a method that simulates temperature variable with increasing in a certain level (e.g. 0.5oC or 1.0oC increase) as a global warming scenario from observed data. In addition, a hydrometeorological variable can be simulated employing block-wise sampling technique associated with the temperature simulation. The proposed method was tested for assessing the future change of the seasonal precipitation in South Korea under global warming scenario. The results illustrate that the proposed method is a good alternative to levy the variation of hydrological variables under global warming condition.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.23 no.1
• /
• pp.5-26
• /
• 2012

Mapping FRSAD and other ontology models intends to suggest a higher knowledge level that is independent of any information implementation system or specific context, and to endeavor to focus on the semantics, knowledge structures, subject access, and interoperability. Providing an application of FRSAD model to information environment and representing and sharing the information within the library sector and beyond, there needs encoding scheme for knowledge representation. This study suggested an OWL based ontology architecture for FRSAD model and demonstrated the pilot FRSAD ontology model using Prot$\acute{e}$g$\acute{e}$ software.

• Journal of Korean Institute of Industrial Engineers
• /
• v.34 no.2
• /
• pp.190-204
• /
• 2008

Recently, it has been strongly required to establish a systematic and sustainable performance investigation and evaluation framework on governmental funding projects for IT small and medium-sized enterprises. In this paper, Data Envelopment Analysis (DEA) models are adopted for performance evaluation on governmental funding projects for IT small and medium-sized enterprises. A new data structure is proposed for the DEA performance evaluation. Generally, in using DEA models, DEA multipliers restriction is critical to achieve the reliability of DEA optimal solutions. Based on the outputs and inputs considered in this study, Acceptance Region (AR) constraints are generated and incorporated into the DEA models so as to improve the reliability of DEA efficiency scores. Associated with AR Type I (AR-I), AR Global Model (ARGM) constraints, DEA/ (AR-I, ARGM) models are designed and then sensitivity analysis follows investigating the robustness of DEA efficiency scores relating to AR constraints adjustment. Finally, a performance evaluation is illustrated regarding governmental direct funding projects from Ministry of Information and Communication (MIC) in Korea where each project unit (i.e. Decision Making Unit (DMU)) is determined whether it is efficient or not. By using DEA/(AR-I, ARGM) models designed in this paper, robustly efficient DMUs are gradually identified according to the successive AR constraints adjustment. Among 25 DMUs, results show that 6 DMUs such as B, E, G, Q, S, Y are determined as robustly efficient against AR constraints intermediate adjustment.

• International Journal of Highway Engineering
• /
• v.20 no.2
• /
• pp.127-135
• /
• 2018

PURPOSES : This study develops various models that can estimate the pattern of road surface temperature changes using machine learning methods. METHODS : Both a thermal mapping system and weather forecast information were employed in order to collect data for developing the models. In previous studies, the authors defined road surface temperature data as a response, while vehicular ambient temperature, air temperature, and humidity were considered as predictors. In this research, two additional factors-road type and weather forecasts-were considered for the estimation of the road surface temperature change pattern. Finally, a total of six models for estimating the pattern of road surface temperature changes were developed using the MATLAB program, which provides the classification learner as a machine learning tool. RESULTS : Model 5 was considered the most superior owing to its high accuracy. It was seen that the accuracy of the model could increase when weather forecasts (e.g., Sky Status) were applied. A comparison between Models 4 and 5 showed that the influence of humidity on road surface temperature changes is negligible. CONCLUSIONS : Even though Models 4, 5, and 6 demonstrated the same performance in terms of average absolute error (AAE), Model 5 can be considered the optimal one from the point of view of accuracy.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.60.2-61
• /
• 2017

A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.77 for flare classification and 0.83 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.

• Health Policy and Management
• /
• v.33 no.4
• /
• pp.379-388
• /
• 2023

This study aims to propose the implementation of innovative payment models in Korea in order to promote the financial sustainability of the national health insurance system by reviewing the current status of the payment system in Korea and examining other countries' experiences with various innovative payment models. Korea primarily uses a fee-for-service payment system and additionally uses various payment systems such as case payment, per diem, and pay-for-performance. However, each payment system has its limitations. Many OECD (Organization for Economic Cooperation and Development) countries have pointed out the limitations of existing payment systems and have been attempting various innovative payment models (e.g., add-on payment, bundled payment, and population-based payment). Therefore, it is essential for Korea to consider innovative payment models, such as a mixed payment model that takes into account the strengths and weaknesses of each payment system, and to design and pilot these models. This process requires stakeholders to work together to build a social consensus on the implementation of innovative payment systems and to refine legal and systematic aspects, develop an integrated health information system, and establish dedicated organizations and committees. These efforts towards innovative payment models will contribute to developing a sustainable health insurance system that ensures the public's health and well-being in Korea.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.33-48
• /
• 2024

With the advent of 5G, characterized by Enhanced Mobile Broadband (eMBB), Ultra-Reliable Low Latency Communications (URLLC), and Massive Machine Type Communications (mMTC), efficient network management and service provision are becoming increasingly critical. This paper proposes a novel approach to address key challenges of 5G networks, namely ultra-high speed, ultra-low latency, and ultra-reliability, while dynamically optimizing network slicing and resource allocation using machine learning (ML) and deep learning (DL) techniques. The proposed methodology utilizes prediction models for network traffic and resource allocation, and employs Federated Learning (FL) techniques to simultaneously optimize network bandwidth, latency, and enhance privacy and security. Specifically, this paper extensively covers the implementation methods of various algorithms and models such as Random Forest and LSTM, thereby presenting methodologies for the automation and intelligence of 5G network operations. Finally, the performance enhancement effects achievable by applying ML and DL to 5G networks are validated through performance evaluation and analysis, and solutions for network slicing and resource management optimization are proposed for various industrial applications.

• Journal of Korean Society for Atmospheric Environment
• /
• v.23 no.1
• /
• pp.14-28
• /
• 2007

This study presented the selection of ozone ($O_3$) potential factors and designed and assessed its potential prediction model using multiple-linear regression equations in Ulsan area during the springtime from April to June, $2000{\sim}2004$. $O_3$ potential factors were selected by analyzing the relationship between meterological parameters and surface $O_3$ concentrations. In addition, cluster analysis (e.g., average linkage and K-means clustering techniques) was performed to identify three major synoptic patterns (e.g., $P1{\sim}P3$) for an $O_3$ potential prediction model. P1 is characterized by a presence of a low-pressure system over northeastern Korea, the Ulsan was influenced by the northwesterly synoptic flow leading to a retarded sea breeze development. P2 is characterized by a weakening high-pressure system over Korea, and P3 is clearly associated with a migratory anticyclone. The stepwise linear regression was performed to develop models for prediction of the highest 1-h $O_3$ occurring in the Ulsan. The results of the models were rather satisfactory, and the high $O_3$ simulation accuracy for $P1{\sim}P3$ synoptic patterns was found to be 79, 85, and 95%, respectively ($2000{\sim}2004$). The $O_3$ potential prediction model for $P1{\sim}P3$ using the predicted meteorological data in 2005 showed good high $O_3$ prediction performance with 78, 75, and 70%, respectively. Therefore the regression models can be a useful tool for forecasting of local $O_3$ concentration.

• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.577-590
• /
• 2024

With increasing demand for nuclear power generation, nuclear structures are being planned and constructed worldwide. A grave safety concern is that these structures are sensitive to large-magnitude shaking, e.g., during earthquakes. Seismic response analysis, which requires P- and S-wave velocities, is a key element in nuclear structure design. Accordingly, it is important to determine the P- and S-wave velocities in the Gyeongju and Pohang regions of South Korea, which are home to nuclear power plants and have a history of seismic activity. P- and S-wave velocities can be obtained indirectly through a correlation with physical properties (e.g., N values, Young's modulus, and uniaxial compressive strength), and researchers worldwide have proposed regression equations. However, the Gyeongju and Pohang regions of Korea have not been considered in previous studies. Therefore, a database was constructed for these regions. The database includes physical properties such as N values and P- and S-wave velocities of the soil layer, as well as the uniaxial compressive strength, Young's modulus, and P- and S-wave velocities of the bedrock layer. Using the constructed database, the geological characteristics and distribution of physical properties of the study region were analyzed. Furthermore, models for predicting P- and S-wave velocities were developed for soil and bedrock layers in the Gyeongju and Pohang regions. In particular, the model for predicting the S-wave velocity for the soil layers was compared with models from previous studies, and the results indicated its effectiveness in predicting the S-wave velocity for the soil layers in the Gyeongju and Pohang regions using the N values. The proposed models for predicting P- and S-wave velocities will contribute to predicting the damage caused by earthquakes.