• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.3
• /
• pp.957-964
• /
• 2013

This research is on the methodology of flood risk assessment using flooding characteristic values. Necessity of design magnitude for flood control considering floods was judged by plotting peak flow with respect to frequency and duration, and flooding magnitude was defined with 6 flooding characteristic values which were proposed to be significant factors when assessing flooding magnitude. Precipitation data used in the assessment modeling were applied by combining all the possible precipitation events. After overlapping the simulated results with precipitation matrix by flooding characteristic values, contour map was drawn, and Flooding characteristic contour graph for possible rainfall events were suggested in respect of all possible precipitation. Flooding characteristic contour graph for possible rainfall events was confirmed that reducing of damage magnitude of each flood characteristic value was figured out easily. The flood risk assessment methods suggested in this study would be a good reference for urban drainage system design, which only focuses on pipe conduit.

• Journal of the Korean Society of Safety
• /
• v.31 no.2
• /
• pp.90-97
• /
• 2016

The objective of this study is to evaluate the operator's safety for the risk assessment method of impulsive noise division. Literature reviews on the basis of the impulsive noise study, the measuring methods and procedures, based on the results of the analysis process presents a risk assessment methods. In this study, analysis of the MIL-STD-1474D, B-duration graph for the peak noise level to cross the line from the measurement results is limited by the risk retracted. It is possible to determine whether there is quick can be determined whether the risk. Measurement positions measured by the microphone is installed on the risk of applying results are so located within the tolerance impulsive noise in the measurement position can interpret subjective safety is ensured. In addition, Proportional Dose technology was the proposed by the Patterson with the risk assessment method was applied to the indoor-impulsive noise. As results of this study, results for the same value of applying the technique of Proportional Dose technology results calculated by MIL-STD-1474D methods allows 1 count once increased in comparison to the result obtained.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.419-437
• /
• 2023

As the number of thin filers in Korea surpasses 12 million, there is a growing interest in enhancing the accuracy of assessing their credit default risk to generate additional revenue. Specifically, researchers are actively pursuing the development of default prediction models using machine learning and deep learning algorithms, in contrast to traditional statistical default prediction methods, which struggle to capture nonlinearity. Among these efforts, Graph Neural Network (GNN) architecture is noteworthy for predicting default in situations with limited data on thin filers. This is due to their ability to incorporate network information between borrowers alongside conventional credit-related data. However, prior research employing graph neural networks has faced limitations in effectively handling diverse categorical variables present in credit information. In this study, we introduce the Transformer embedded Graph Convolutional Network (TeGCN), which aims to address these limitations and enable effective default prediction for thin filers. TeGCN combines the TabTransformer, capable of extracting contextual information from categorical variables, with the Graph Convolutional Network, which captures network information between borrowers. Our TeGCN model surpasses the baseline model's performance across both the general borrower dataset and the thin filer dataset. Specially, our model performs outstanding results in thin filer default prediction. This study achieves high default prediction accuracy by a model structure tailored to characteristics of credit information containing numerous categorical variables, especially in the context of thin filers with limited data. Our study can contribute to resolving the financial exclusion issues faced by thin filers and facilitate additional revenue within the financial industry.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.5
• /
• pp.892-898
• /
• 2012

Rough classification methods are used to improving the recognition speed in many character recognition problems. In this case, some irreversible result can occur by an error in rough classification. Methods for duplicating each model in several classes are used in order to reduce this risk. But the errors by rough classfication can not be completely ruled out by these methods. In this paper, an recognition method is proposed to increase speed that matches models selectively without any increase in error. This method constructs a model graph using similarity between models. Then a search process begins from a particular point in the model graph. In this process, matching of unnecessary models are reduced that are not similar to the input pattern. In this paper, the proposed method is applied to the recognition problem of handwriting numbers and upper/lower cases of English alphabets. In the experiments, the proposed method was compared with the basic method that matches all models with input pattern. As a result, the same recognition rate, which has shown as the basic method, was obtained by controlling the out-degree of the model graph and the number of maintaining candidates during the search process thereby being increased the recognition speed to 2.45 times.

• Journal of the Korea Safety Management & Science
• /
• v.13 no.3
• /
• pp.1-8
• /
• 2011

The overall goal of a safety based railroad system is either to eliminate hazards in designing or to minimize the possibility of it. In order to indicate system safety or low risk although it may not be possible to achieve zero risk conditions, first, it shall ensure that any disasters would occur due to system operation because the prescribed specifications are properly fulfilled and there are no failures of any kind. Second, the risk of faults or failures leading to a mishap must be eliminated or minimized by using fault-tolerance or fail-safe procedures. This paper will attempt to summarize the personal and social risk criterion at widely scattered points, presently used as a safety approach in all over EU, in order to establish the step by step procedures of the detailed standard for railway facilities. In addition, we present the new safety analysis method using the SIL-based evaluation standard and the Reachability Graph of the Petri Net.

• Journal of Acupuncture Research
• /
• v.25 no.6
• /
• pp.67-76
• /
• 2008

Objectives : The 7-zone-diagnostic system is a diagnostic device to predetermine bodily locations by measuring the energy of body. This study was to investigate the relation between the different patterns of Zone 1, 2, 3 of Factor AA in CP-6000A(VEGA, Germany), 7-zone-diagnostic system and clinical parameters. The purpose of this study was relation Korean traditional medicine and western medicine with the data from 7-zone-diagnostic system and the clinical parameters. Methods : This study was carried out with the data from some clinical parameters. We made three groups according to the Factor AA patterns of CP-6000A. The Factor AA pattern of Group A is that the red bar graph of zone 1, 2, 3 were higher than the normal range and the others were the normal range. The Factor AA pattern of Group B was that the red bar graph of zone 1, 2, 3 was the normal range and the others were the normal range. The Factor AA pattern of Group C was that the red bar graph of zone 1, 2, 3 was lower than the normal range and the others were the normal range. After the data from clinical parameters to correspond with conditions of each group were selected, the data from clinical parameters among each groups analyzed statistically. Results : The values of GOT, GPT, r-GPT, Triglyceride, BUN, Uric acid of group A was higher than group C. Gastroscope of group A and B was higher than group C. Conclusions : It is thought that the red bar graph of zone 1, 2, 3 is higher, the group has the higher energy and the energy has a character of fire(熱). Those patterns have a high risk of hyperlipermia and liver, stomach disease.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.607-610
• /
• 2015

소프트웨어 테스팅의 표준인 위험 기반 테스팅은 품질에 영향을 미칠 것으로 예상되는 위험들을 식별하고 분석한 결과를 바탕으로 효과적인 테스트 전략을 세우는 방법이다. 성공적인 위험 기반 테스팅을 위해서는 위험을 조기에 식별하는 것이 중요하다. 위험 식별은 하나의 프로그램 혹은 프로젝트에 따라 이해관계자의 리뷰를 통해 주관적으로 추출하는 방법을 주로 사용한다. 그러나 이는 짧은 개발주기 안에서 변화되는 위험을 즉시적으로 식별하기 어렵다. 본 논문에서는 위험 기반 호출 그래프를 이용하여 위험을 초기에 식별할 수 있는 방법을 제안한다.

• Journal of Navigation and Port Research
• /
• v.28 no.1
• /
• pp.17-22
• /
• 2004

The paper describes implementation of three-dimensional visualization system that is to provide comprehensive meaning of the statistical prediction results on the marine casualties. Graphical User Interface (GUI) and Web based Virtual Reality (VR) technology are mainly introduced in the system development. To provide daily forecasting, time based casualty prediction model and risk level index are developed in this work. As operating test results of the system, complicated statistical meaning can be shown in the three-dimensional virtual space using simple color. In addition, daily risk levels can be shown on the bar-graph.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1281-1291
• /
• 2015

Compared to the past, people can control end devices via open channel. Although this open channel provides convenience to users, it frequently turns into a security hole. In this paper, we propose a new human-centered security risk analysis method that puts weight on the relationship between end devices. The measure derives from the concept of entropy rate, which is known as the uncertainty per a node in a network. As there are some limitations to use entropy rate as a measure in comparing different size of networks, we divide the entropy rate of a network by the maximum entropy rate of the network. Also, we show how to avoid the violation of irreducible, which is a precondition of the entropy rate of a random walk on a graph.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.10 no.4
• /
• pp.37-51
• /
• 2014

In this study, we propose a scheme for providing the consumer of Korea and China with more effective information about the safety of the food to understand easily. Among these countries and consumers, we proposed the graphical displays to help you understand the factors disturbing to think of pesticide residues in common. In the form of a one-dimensional graphical display, whether to provide a safety-related information in the form of conventional foods character, as compared to the graph representation of the larger amounts of information than a two-dimensional character which easily measures the effect of promoting the understanding of the most appropriate information, were reviewed. As a result, in the case of Korea, text and graphs utilizing the standards of pesticide residues than the information provided in a one-dimensional form'Text + Graphics Display'to take advantage of the information provided with the relevant safety standards form the three was found that easy to show. On the other hand, Chinese, between the character and graph form with the advantage that the information providing service type information using the graphic display shown in one dimension could not see the difference between the evaluation and understanding.