• Journal of the Korea Society for Simulation
• /
• v.25 no.4
• /
• pp.127-135
• /
• 2016

Even thought modernized marine navigation devices help navigators, marine accidents has been often occurred and ship collision is one of the main types of the accidents. Various studies on the assessment method of collision risk have been reported, and studies using fuzzy theory are remarkable for the reason that reflect linguistic and ambiguous criteria for real situations. In these studies, collision risks were assessed on the assumption that the current state of navigation ship would be maintained. However, navigators ignore or turn off frequent alarms caused by the devices predicting collision risk, because they think that they can avoid the collisions in the most of situations. This paper proposes a model of predicting ship collision risk considering the general patterns of collision avoidance, and the approach is based on fuzzy inference and discrete event system specification (DEVS) formalism.

• Fire Science and Engineering
• /
• v.24 no.3
• /
• pp.66-71
• /
• 2010

In order to evaluate the fire and explosion involved and to ensure the safe and optimized operation of chemical processes, it is necessary to know combustion properties. Explosion limit is one of the major combustion properties used to determine the fire and explosion hazards of the flammable substances. In this study, the lower explosion and upper explosion limits of esters were predicted by using the heat of combustion. The values calculated by the proposed equations agreed with literature data within a few percent. From the given results, using the proposed methodology, it is possible to predict the explosion limits of the other ester flammable substances.

• Fire Science and Engineering
• /
• v.19 no.4 s.60
• /
• pp.26-31
• /
• 2005

In order to evaluate the fire and explosion involved and to ensure the safe and optimized operation of chemical processes, it is necessary to know combustion properties. Explosion limit is one of the major combustion properties used to determine the fire and explosion hazards of the flammable substances. In this study, the explosion limits of alcohols were predicted by using the normal boiling points and the flash points based on a solution theory. The values calculated by the proposed equations agreed with literature data within a few percent. From the given results, using the proposed methodology; it is Possible to Predict the explosion limits of the other flammable substances.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.23 no.6
• /
• pp.559-575
• /
• 2021

Due to the increase in ground excavation work, the possibility of ground subsidence accidents is increasing. And it is very difficult to prevent these risk fundamentally through institutional reinforcement such as the special law for underground safety management. As for the various cases of urban ground excavation practice, the ground subsidence behavior characteristics which is predicted using various information before excavation showed a considerable difference that could not be ignored compared to the results real construction data. Changes in site conditions such as seasonal differences in design and construction period, changes in construction methods depending on the site conditions and long-term construction suspension due to various reasons could be considered as the main causes. As the countermeasures, the safety management system through various construction information is introduced, but there is still no suitable system which can predict the effect of excavation and risk assessment. In this study, a web-based system was developed in order to predict the degree of impact on the ground subsidence and surrounding structures in advance before ground excavation and evaluate the risk in the design and construction of urban ground excavation projects. A system was built using time series analysis technique that can predict the current and future behavior characteristics such as ground water level and settlement based on past field construction records with field monitoring data. It was presented as a geotechnical data visualization (GDV) technology for risk reduction and disaster management based on web-based system, Using this newly developed web-based assessment system, it is possible to predict ground excavation impact prediction and risk assessment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.8
• /
• pp.5310-5317
• /
• 2014

Landslides occur in Korea every year because it has numerous mountainous regions and approximately two-thirds of the annual rainfall falls in Summer. Therefore, it is important to predict potential areas of landslides and minimize the damage in advance to protect property and human life. Therefore, in the present study, the potential danger areas were extracted from a digital map, digital forest map, digital forest site environmental map, and digital geologic map to estimate the landslide hazard. In addition, the assessment of landslide danger was analyzed by first and second estimations based on the criteria from the Korea Forest Research Institute using a GIS technique, which was finally judged by a field investigation.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5
• /
• pp.1401-1408
• /
• 2000

Critical prediction models that determine whether a design entity is fault-prone or non fault-prone play an important role in reducing system development cost because the problems in early phases largely affected the quality of the late products. Real-time systems such as telecommunication system are so large that criticality prediction is more important in real-time system design. The current models are based on the technique such as discriminant analysis, neural net and classification trees. These models have some problems with analyzing cause of the prediction results and low extendability. In this paper, we propose a criticality prediction model using fuzzy rulebase constructed by genetic algorithm. This model makes it easy to analyze the cause of the result and also provides high extendability, high applicability, and no limit on the number of rules to be found.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1244-1253
• /
• 2021

In this paper, we propose a method for predicting in advance whether pedestrians will enter the hazardous area after the current time using the pedestrian trajectory prediction method and an efficient simplification method of the trajectory prediction network. In addition, we propose a method to apply KD(Knowledge Distillation) to a small network for real-time operation in an embedded environment. Using the correlation between predicted future paths and hazard zones, we determined whether to enter or not, and applied efficient KD when learning small networks to minimize performance degradation. Experimentally, it was confirmed that the model applied with the simplification method proposed improved the speed by 37.49% compared to the existing model, but led to a slight decrease in accuracy. As a result of learning a small network with an initial accuracy of 91.43% using KD, It was confirmed that it has improved accuracy of 94.76%.

• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.215-215
• /
• 2011

우리나라 하천의 대부분은 산지에서 발원하며 전 국토의 약 67%가 산지하천 유역에 포함된다. 최근 기후변화로 인해 여름철 집중호우가 증가하고 있는 상황에서 강우의 예측이 어렵고 경사가 급한 산지하천 유역의 피해가 가중되고 있으며 돌발홍수나 산사태와 같은 산지재해 예방을 위한 대책 마련이 시급히 요구되고 있다. 산지하천유역에서 발생하는 재해를 예방하고 피해를 저감하기 위해서는 재해위험지역에 대한 선정 및 상시 모니터링 체계의 구축이 필요하며 본 연구에서는 격자기반의 산지하천 모니터링 시스템을 구축하여 강우상황과 예측정보, 이동상황을 모니터링 할 수 있는 시스템을 구축하였다. 산지하천 모니터링 시스템은 기상청 레이더 강우를 활용한 실시간 강우자료 및 강우예측자료(MAPLE) 표출, 분포형 수문모형과 연계한 유출분석 결과의 제공, AWS를 이용한 지점강우량 표출 등으로 구성된다. 또한, 지점자료 혹은 격자자료로 이원화되어 있는 기존 하천유역 모니터링 체계를 통합하여 사용자가 원하는 유역에 대한 기상자료의 모니터링과 위험지역에 설치된 지점관측정보를 연계 운영할 수 있도록 구현된 특징이 있다. 본 시스템은 현재 강원도 인제 내린천 유역을 대상으로 시험운영 중이며 격자기반의 강우모니터링과 토석류 현장모니터링 결과를 연계한 위험지 관리에 활용되고 있다.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1255-1262
• /
• 2021

The proportion of students dropping out of universities is increasing year by year, and they are trying to identify risk factors and eliminate them in advance to prevent dropouts. However, there is a problem in the management of students at risk of dropping out and the forecast is inaccurate because crisis students are managed through the univariable analysis of specific risk factors. In this paper, we identify risk factors for university dropout and analyze multivariables through machine learning method to predict university dropout. In addition, we derive the optimization method by evaluation performance for various prediction methods and evaluate the correlation and contribution between risk factors that cause university dropout.