• International Journal of Safety
• /
• 제9권2호
• /
• pp.6-10
• /
• 2010

The flash point of liquid solution is one of the most important flammability properties that used in hazard and risk assessments. Minimum flash point behaviour (MFPB) is showed when the flash point of a liquid mixture is below the flash points of the individual components. In this paper, the lower flash points for the flammable binary system, n-decane+n-octanol, were measured by Pensky-Martens closed cup tester. This binary mixture exhibited MFPB. The measured flash points were compared with the values calculated by the Raoult's law and the optimization method using van Laar and UNIQUAC equations. The optimization method were found to be better than those based on the Raoult's law, and successfully estimated MFPB. The opimization method based on the van Laar equation described the experimentally-derived data more effectively than was the case when the prediction model was based upon the UNIQUAC.

• 전자통신동향분석
• /
• 제34권1호
• /
• pp.111-122
• /
• 2019

As society develops, the demand for safety and security services increases. Developed nations such as the United States use advanced technology to lower crime rate and promote intelligent security services. First, this article examines intelligent systems that are used for monitoring and detecting crimes and dangerous situations. Recently, we have been studying technologies that enable preemptive responses through prediction of crime and hazardous situations. In this paper, we examine the cases of security services based on a crime/risk prediction model and explain the structure and major technologies of an intelligent security system. In addition, we propose a direction for technological development for achieving future security services.

• International Journal of Internet, Broadcasting and Communication
• /
• 제12권3호
• /
• pp.149-155
• /
• 2020

Air pollution is a problem of environmental health risk in big cities. Recently, researchers have proposed using various artificial intelligence technologies to predict air pollution. The proposed model is Cooperative of Artificial Neural Network (ANN) and Fuzzy Inference System (FIS), to predict air pollution of Korean cities using Python. Data air pollutant variables were collected and the Air Korean Web site air quality index was downloaded. This paper's aim was to predict on the health risks and the very unhealthy values of air pollution. We have predicted the air pollution of the environment based on the air quality index. According to the results of the experiment, our model was able to predict a very unhealthy value.

• Journal of Information Technology Applications and Management
• /
• 제17권4호
• /
• pp.39-56
• /
• 2010

We are sometimes interacting with people who we know nothing and facing with the difficult task of making decisions involving risk in social network. To reduce risk, the topic of building Web of trust is receiving considerable attention in social network. The easiest approach to build Web of trust will be to ask users to represent level of trust explicitly toward another users. However, there exists sparsity issue in Web of trust which is represented explicitly by users as well as it is difficult to urge users to express their level of trustworthiness. We propose a fuzzy-based inference model for Web of trust using user behavior information in social network. According to the experiment result which is applied in Epinions.com, the proposed model show improved connectivity in resulting Web of trust as well as reduced prediction error of trustworthiness compared to existing computational model.

• 한국데이타베이스학회:학술대회논문집
• /
• 한국데이타베이스학회 2010년도 춘계국제학술대회
• /
• pp.277-287
• /
• 2010

We are sometimes interacting with people who we know nothing and facing with the difficult task of making decisions involving risk in social network. To reduce risk, the topic of building Web of trust is receiving considerable attention in social network. The easiest approach to build Web of trust will be to ask users to represent level of trust explicitly toward another users. However, there exists sparsity issue in Web of trust which is represented explicitly by users as well as it is difficult to urge users to express their level of trustworthiness. We propose a fuzzy-based inference model for Web of trust using user behavior information in social network. According to the experiment result which is applied in Epinions.com, the proposed model show improved connectivity in resulting Web of trust as well as reduced prediction error of trustworthiness compared to existing computational model.

• 한국응용약물학회:학술대회논문집
• /
• 한국응용약물학회 1995년도 제3회 추계심포지움
• /
• pp.135-136
• /
• 1995

Resent advances in computer technology have introduced a sophisticated capability for computing the biological fate of toxicants in a biological system. This methodology, which has drastically altered risk assessment skill in toxicology, is designed using all the mechanistic information, and all claim better accuracy with extrapolating capability Iron animal to people than conventional pharmacokinetic methods. Biologically based mathematical models in which the specific mechanistic steps governing tissue disposition(pharmacokinetics) and toxic action (pharmacodynamics) of chemicals are constructed in quantitative terms by a set of equations loading to prediction of the outcome of specific toxicological experiments by computer simulation. pharmacokinetic and pharmacodynamic models are useful in risk assessment because their mechanistic biological basis permits the high-to-low dose, route to route and interspecies extrapolation of the tissue disposition and toxic action of chemicals.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2018년도 춘계 학술논문 발표대회
• /
• pp.122-123
• /
• 2018

Recently, CM at Risk delivery system(CM@R) that could solve the problems of Design Bid Build delivery(DBB) system has been emerging. In the CM@R delivery system, the contractor negotiates for a maximum guaranteed price(GMP) with the client at the design stage, and the contractor carries out the construction within the GMP. In CM @ R, the construction company with expertise in construction participates from the design stage to reflects the construction know-how in the design. On the other hand, the modification design frequently occurs due to the change of the construction cost when negotiating the GMP. In addition, uncertainties are inherent in the GMP calculation because the calculation is based on unfinished drawings and documents. This study proposes a probabilistic GMP estimation method applying MCS to the BIM - based cost prediction model, in order to extract the accurate quantity information when estimating the GMP and to cope with the change of the construction cost inherent in uncertainty.

• 한국통신학회논문지
• /
• 제38C권12호
• /
• pp.1095-1105
• /
• 2013

본 논문에서는 헬스 케어 시스템에서 효율적으로 질병을 관리할 수 있는 RDMS(Rough Set Theory based Disease Monitoring System)을 제안한다. RDMS는 DCM(Data Collection Module), RDRGM(RST based Disease Rule Generation Module), HMM(Healthcare Monitoring Module)로 구성된다. DCM은 바이오센서로부터 환자의 생체 정보를 수집하고, 데이터 처리 절차에 따라 RDMS DB에 저장한다. RDRGM은 RST의 코어와 속성의 지지율을 이용하여 질병 규칙을 생성한다. HMM은 DCM에 의해 수집된 환자 정보를 이용하여 환자의 질병에 대한 위험지수뿐만 아니라 질병에 대한 합병증에 관한 위험지수까지 분석함으로써 환자의 질병을 예측하고, 환자의 위험지수에 따라 환자, 주치의 등에 시각화된 환자의 정보를 전달한다. 또한, RDRGM에 의해 생성된 규칙들에 따라 환자의 의료정보, 현재의 환자건강상태, 환자 가족력 등을 비교분석하여 환자의 질병을 예측하고, 예측결과에 따라 환자 맞춤형 의료 서비스와 의료 정보를 신속하고 신뢰성 있게 제공할 수 있다.

• 한국지능시스템학회논문지
• /
• 제27권2호
• /
• pp.113-118
• /
• 2017

선박 충돌 사고를 예방하기 위해 충돌위험도를 미리 추정하여 알려주는 다양한 연구들이 꾸준히 소개되고 있고, 일부 항해장비에 적용되고 있다. 하지만, 충돌위험을 미리 알려주었을 때, 실제 운항자는 충분히 피항 가능한 상황인데 위험성을 알린다고 판단하여 위험 경고를 무시하거나 장비의 알람 기능을 꺼놓는 경우도 많은 것으로 알려져 있다. 선박 충돌 위험 예측이 운항자들에게 좀 더 유용해지기 위해서는 실제 선박들의 습관화된 충돌 회피 동작을 고려할 필요가 있다. 이 연구는 선박에서의 충돌 회피 조치가 어떻게 이루어지고 있는지 조우 유형별로 분석하고 이력을 관리하기 위한 시스템을 제안한다. 특히, 충돌회피를 위한 초기대응에 대한 적절성을 판단하는 핵심 모듈을 뉴로-퍼지 기반 추론 형태로 상세히 설계하고 테스트함으로써 제안하는 시스템의 타당성을 보인다.

• 융합보안논문지
• /
• 제21권1호
• /
• pp.93-100
• /
• 2021

지능형 사이버 공격으로 인한 피해는 시스템 운영 중단과 정보 유출뿐만 아니라 엄청난 규모의 경제적 손실을 동반한다. 최근 사이버 공격은 공격 목표가 뚜렷하며, 고도화된 공격 도구와 기법을 활용하여 정확하게 공격 대상으로 침투한다. 이러한 지능적인 사이버 공격으로 인한 피해를 최소화하기 위해서는 사이버 공격이 공격 대상의 핵심 시스템까지 침입하지 못하도록 공격 초기 또는 과정에서 차단해야 한다. 최근에는 빅데이터나 인공지능 기술을 활용하여 사이버 공격 경로를 예측하고 위험 수준을 분석하는 보안 기술들이 연구되고 있다. 본 논문에서는 자동화 사이버 공격 경로 예측 시스템 개발을 위한 기초 메커니즘으로 공격 트리와 RFI 기법을 활용한 사이버 공격 경로 분석 방법을 제안한다. 공격 트리를 활용하여 공격 경로를 가시화하고 각 공격 단계에서 RFI 기법을 이용하여 다음 단계로 이동할 수 있는 경로를 판단한다. 향후에 제안한 방법을 기반으로 빅데이터와 딥러닝 기술을 활용한 자동화된 사이버 공격 경로 예측 시스템의 메커니즘으로 활용할 수 있다.