• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.656-659
• /
• 2018

통계적으로 일반인보다 청각장애인의 교통 사고율이 높은 것으로 나타나는데, 이는 청각 장애로 대표되는 차량을 포함한 위험 요소를 인식하기 힘든 상태나 조건에서 기인한다. 자동차가 접근하는 등의 소리를 듣지 못한다는 것은 결국 어떠한 위치에 위험요소가 존재하는지 인지하지 못함에 따라 사고로 이어질 가능성이 존재함을 의미하는데 이러한 문제점을 개선함과 동시에 대화중인 사람의 목소리를 시각화하여 정보를 제공함으로써 청각장애인으로 하여금 더 안전하고 쾌적한 삶을 누리게 하는 것이 청각장애인을 위한 사운드 정보 시각화 안경의 개발 목적이다. 위와 같은 배경을 통해 딥 러닝 기술에 기반하여 분류 과정을 거친 소리 정보의 판별을 통해 위험 요소를 인식한 후 시각화 하여 정보를 제공하는 디바이스를 제안한다.

• The Journal of Society for e-Business Studies
• /
• v.21 no.1
• /
• pp.1-14
• /
• 2016

This research proposes a method that aims to evaluate the risk levels of websites based on exposure risks of privacy information. The proposed method considers two aspects as follows. First, we define the risk levels of each privacy information according to its own inherent risk. Second, we calculate the visiting probability of a webpage to measure the expected of the actual exposure of privacy information on that webpage. In this research, we implemented an system to prove that automatically collects websites and calculates their risk levels. For the experiments, we used a real world dataset consisting of a total of websites for 4 categories such as university, bank, central government agency, and education. The experiment results show that the websites in the bank category are relatively well managed, while the others are needed to cope with the exposure of privacy information. Finally, the proposed method in this research is expected to be further utilized in establishing a priority-based approach to alleviate of the privacy information exposure problems.

• Journal of Korean Society of Transportation
• /
• v.34 no.4
• /
• pp.330-340
• /
• 2016

The main objective of study was to analyze the effectiveness of transit mall. To this end, this study compared operational status of transit malls in operation (Daegu, Seoul and Busan). For the city of Busan where the latest transit mall became operational in 2015, a discriminant model was proposed to determine user satisfaction/dissatisfaction. The outcomes of comparative study showed that each city has different operational focus - Seoul has focus on traffic demand management, Busan has focus on walking environment, and Daegu has focus on accessibility to public transportation. Also, the discriminant model indicated that market sentiment, convenience of bus service, traffic accident risk, number of pedestrian, market user number have effects on user satisfaction. These results implied that, to improve user satisfaction, measures for market revitalization such as opening events and forming consultative groups need to be prepared and traffic conditions should also be improved through expansion of curfew time, linkage with subway station.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.197-197
• /
• 2021

최근 기후변화와 하천 제방의 노후화로 인해 수재해 위험이 지속적으로 증가하고 있다. 그러나 기존의 재래적인 하천 제방의 점검은 많은 인력과 예산 소모로 비효율적이며 제방 전구간 점검의 한계, 객관성의 한계 등 많은 한계점들이 존재하여 효과적인 홍수 대응을 위해 새로운 모니터링과 예/경보 시스템의 구축이 반드시 필요한 상황이다. 따라서 본 연구는 인공위성을 이용한 하천 제방 변위 산출과 수문학적 요인과의 관계 분석을 통해 하천 제방 건강상태 모니터링 시스템 방안을 제안하고자 한다. Sentinel-1 SAR 영상과 유럽 우주국(ESA)의 위성 영상 전처리 도구인 SNAP을 이용하여 2020년 여름 붕괴된 남원시의 금곡교 제방의 봄(4~5월), 여름(7~8월)의 변위를 산출하였고, 제방의 위험도 산정을 위해 토양수분관계를 분석하였다. 선행 연구(김상우,2019)에서는 농촌진흥청에서 제공하는 TDR(Time Domain Reflectrometry) 관측값과 Sentinel-1 SAR의 후방 산란계수의 토양수분관계가 일치하는 경향을 제시하여, 본 연구에서는 이를 이용하여 제방 후 방산란계수를 산출하고 변위와 토양수분도의 상관관계를 분석하여 변위 추세와 토양수분도의 추세가 일치하는 경향을 확인하였다. 본 연구 결과를 통해 향후에는 위성을 이용하여 산출한 제방의 변위와 토양수분도의 불확실성을 보완하고 기온, 수위, 토양도, 지하수위와 같은 수문기상학적 데이터의 분석을 통해 초정밀, 자동화 하천 제방 건강상태 모니터링 시스템이 구현 가능할 것으로 기대한다.

• Journal of Korea Technology Innovation Society
• /
• v.10 no.2
• /
• pp.183-205
• /
• 2007

An investigation was undertaken of the optimal discriminant model for predicting the likelihood of insolvency in advance for medium-sized firms based on the technology evaluation. The explanatory variables included in the discriminant model were selected by both factor analysis and discriminant analysis using stepwise selection method. Five explanatory variables were selected in factor analysis in terms of explanatory ratio and communality. Six explanatory variables were selected in stepwise discriminant analysis. The effectiveness of linear discriminant model and logistic discriminant model were assessed by the criteria of the critical probability and correct classification rate. Result showed that both model had similar correct classification rate and the linear discriminant model was preferred to the logistic discriminant model in terms of criteria of the critical probability In case of the linear discriminant model with critical probability of 0.5, the total-group correct classification rate was 70.4% and correct classification rates of insolvent and solvent groups were 73.4% and 69.5% respectively. Correct classification rate is an estimate of the probability that the estimated discriminant function will correctly classify the present sample. However, the actual correct classification rate is an estimate of the probability that the estimated discriminant function will correctly classify a future observation. Unfortunately, the correct classification rate underestimates the actual correct classification rate because the data set used to estimate the discriminant function is also used to evaluate them. The cross-validation method were used to estimate the bias of the correct classification rate. According to the results the estimated bias were 2.9% and the predicted actual correct classification rate was 67.5%. And a threshold value is set to establish an in-doubt category. Results of linear discriminant model can be applied for the technology financing banks to evaluate the possibility of insolvency and give the ranking of the firms applied.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.11
• /
• pp.107-116
• /
• 2012

In this paper we propose a method that can generate the risk probability map in the form of raster shape by using Markov Chain methodology applied to the object interpretation keys and quantified risk indexes. These object interpretation keys, which are primarily characteristics that can be identified by the naked eye, are set based on the objects that comprise the spatial information of a certain urban area. Each key is divided into a cell, and then is weighted by its own risk index. These keys in turn are used to generate the unified risk probability map using various levels of crime prediction probability maps. The risk probability map may vary over time and means of applying different sets of object interpretation keys. Therefore, this method can be used to prevent crimes by providing the ways of setting up the best possible police patrol beat as well as the optimal arrangement of surveillance equipments.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.11
• /
• pp.135-144
• /
• 2009

In this paper, a methodology for the risk probability map generation of the crime prevention to be subject to the urban area in the group residential area is presented. The interpretation key is set up to the distinctive feature distinguishing with the unaided eye based on the object composing with the urban area information such as the topology, the facility, and the characteristic information of the corresponding area by analyzing the crime prevention case occurred by gone. This interpretation key is generated, and this information is applied to another area equally, and so, the risk probability map for the crime prevention and the disaster prevention is generated. At this time, the object interpretation key for the urban area information is divided into the various size cell by the crime prevention case. and the risk index according with this cell is set up. Also, the generated various risk probability map is unified, and the integration risk probability map is generated.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.2
• /
• pp.148-153
• /
• 2009

Failure Mode Effects and Criticality Analysis (FMECA) is one of most widely used methods in modem engineering system to investigate potential failure modes and its severity upon the system. FMECA evaluates criticality and severity of each failure mode and visualize the risk level matrix putting those indices to column and row variable respectably. Generally, those indices are determined subjectively by experts and operators. However, this process has no choice but to include uncertainty. In this paper, a method for eliciting expert opinions considering its uncertainty is proposed to evaluate the criticality and severity. In addition, a fuzzy expert system is constructed in order to determine the crisp value of risk level for each failure mode. Finally, an illustrative example system is analyzed in the case study. The results are worth considering while deciding the proper policies for each component of the system.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.977-985
• /
• 2013

Many situations are classified into more than two categories in real world. In this work, we consider ROC surface and VUS, which are graphical representation methods for classification models with three categories. The standard criteria of AUC for the probability of default based on Basel II is extended to the VUS for ROC surface; therefore, the standardized criteria of VUS for the classification model is proposed. The ranges of AUC, K-S and mean difference statistics corresponding to VUS values for each class of the standard criteria are obtained. The standard criteria of VUS for ROC surface can be established by exploring the relationships of these statistics.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.5
• /
• pp.915-926
• /
• 2016

The purpose of this study is to classify debris flow hazard zones in urbanized areas using multivariate statistical analyses and to suggest customized management strategies to each areal type. Using field survey data set in Seoul, 49 sample debris hazard zones are selected. Clustering and discriminant analyses show that debris flow hazard zones are classified into two types. Surrounding land use and land slope are major factors influencing to the categorization. The results suggest that, by considering the characteristics of each areal type, more customized management strategies for debris flow hazard are necessary. Particularly, in addition to traditional structural measures, non-structural measures including land use and development control for downstream built-up areas should be emphasized in urbanized areas to mitigate human and property damages from debris flow hazard more fundamentally.