• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.145-150
• /
• 2023

The subway is a public transportation that many people use every day. Line 2 especially has the most crowded stations during the day. However, the risk of crush accidents is increasing due to high congestion during rush hour and this reduces the safety and comfort of passengers. Subway congestion prediction is helpful to forestall problems caused by high congestion. Therefore, this study proposes machine learning classification models that predict subway congestion during commuting time. To predict congestion in Line 2 based in machine learning, we investigate variables that affect subway congestion through previous research and collect a dataset of subway congestion on Line 2 during rush hour from PUBLIC DATA PORTAL. The proposed model is expected to establish the subway operation plane to make passengers safe and satisfied.

• Journal of Food Hygiene and Safety
• /
• v.14 no.4
• /
• pp.319-326
• /
• 1999

Recently, it is continuously rising to concern about the health risk being induced by microorganisms in food such as Escherichia coli O157:H7 and Listeria monocytogenes. Various organizations and regulatory agencies including U.S.FPA, U.S.DA and FAO/WHO are preparing the methodology building to apply microbial quantitative risk assessment to risk-based food safety program. Microbial risks are primarily the result of single exposure and its health impacts are immediate and serious. Therefore, the methodology of risk assessment differs from that of chemical risk assessment. Microbial quantitative risk assessment consists of tow steps; hazard identification, exposure assessment, dose-response assessment and risk characterization. Hazard identification is accomplished by observing and defining the types of adverse health effects in humans associated with exposure to foodborne agents. Epidemiological evidence which links the various disease with the particular exposure route is an important component of this identification. Exposure assessment includes the quantification of microbial exposure regarding the dynamics of microbial growth in food processing, transport, packaging and specific time-temperature conditions at various points from animal production to consumption. Dose-response assessment is the process characterizing dose-response correlation between microbial exposure and disease incidence. Unlike chemical carcinogens, the dose-response assessment for microbial pathogens has not focused on animal models for extrapolation to humans. Risk characterization links the exposure assessment and dose-response assessment and involve uncertainty analysis. The methodology of microbial dose-response assessment is classified as nonthreshold and thresh-old approach. The nonthreshold model have assumption that one organism is capable of producing an infection if it arrives at an appropriate site and organism have independence. Recently, the Exponential, Beta-poission, Gompertz, and Gamma-weibull models are using as nonthreshold model. The Log-normal and Log-logistic models are using as threshold model. The threshold has the assumption that a toxicant is produce by interaction of organisms. In this study, it was reviewed detailed process including risk value using model parameter and microbial exposure dose. Also this study suggested model application methodology in field of exposure assessment using assumed food microbial data(NaCl, water activity, temperature, pH, etc.) and the commercially used Food MicroModel. We recognized that human volunteer data to the healthy man are preferred rather than epidemiological data fur obtaining exact dose-response data. But, the foreign agencies are studying the characterization of correlation between human and animal. For the comparison of differences to the population sensitivity: it must be executed domestic study such as the establishment of dose-response data to the Korean volunteer by each microbial and microbial exposure assessment in food.

• 한국IT서비스학회:학술대회논문집
• /
• 2006.11a
• /
• pp.232-239
• /
• 2006

최근 전 세계적으로 서비스 산업의 노동력 비중이 늘어나고 서비스업 뿐만 아니라 농업 및 제조업 분야에서도 서비스의 가치 비중이 높아지고 있다. 그러나 최근까지 서비스는 대부분 제공자의 직관과 경험에 의존하여 운영되었기 때문에 서비스의 성과와 고객 만족도는 미미한 수준에 그칠 수밖에 없었다. 이에 따라 서비스의 생산성을 향상시키고 서비스 수준을 혁신하는 방법을 찾는 것이 산업 사회의 주요 현안으로 떠올랐고 이러한 배경 하에 서비스업의 본질을 과학적으로 규명하여 서비스 분야의 혁신을 이루기 위해 경영학, 사회과학, 산업공학 등 여러 분야의 지식을 종합하여 서비스 과학(Services Science)이라는 새로운 학문 분야를 만들려는 움직임이 일기 시작했다. 서비스 과학의 목적은 공급자와 고객 사이에 가치를 창출하는 일련의 과정인 서비스를 보다 과학적인 방법을 통하여 측정하고 예측할 수 있는 것으로 변환시킴으로써 서비스의 미래 가치와 위험을 정량적으로 예측하고 나아가 서비스의 성과와 만족도를 높이는 것이라고 할 수 있다. 본 연구에서는 U-city 건설에 중추적 역할을 할 것으로 기대되는 지리정보시스템(GIS)의 비즈니스 모델을 대상으로, GIS 정보 서비스의 특성을 규명하여 이러한 정보 서비스가 높은 생산성을 갖기 위한 방안으로서 다학제적 관점의 공유를 통해 다양한 학문 분야의 지식을 종합 적용하고 서비스의 특성을 고려하여 직관과 경험이 아닌 과학적인 도구와 방법론을 통해 GIS 정보 서비스를 관리할 것을 제안한다.

• Journal of Korean Society of Transportation
• /
• v.21 no.5
• /
• pp.73-81
• /
• 2003

The Government presented improvement plans such as "Traffic Accident Frequent Point" and "Hazardous Roads" to reduce traffic accidents on the increase after 1980s. In case of the hazardous roads, they are expressed by grades which are marked by geometric elements such as width, radius, grade. sight distance. and other environmental factors. As each business for improving roads goes by only focusing on improvement of geometric elements, excessive expense can be invested too much nowadays causing economical waste. Therefore, as improvement plans approached by economic access are needed, this paper shows the cost-effective improvement of the business to keep safety related to traffic accident and economical waste. The hazardous roads which authorized by Gwang-ju National Road Preservation Office of Construction and Transportation Ministry in 1995 for business for improvement of roads, were investigated before 1999. First of all, estimating traffic accident models are presented by using existed data statistically. The models help to maximize traffic accident decrease through control of the presented factor. Secondly, optimum construction cost of improvement is presented to prevent overcapitalization. However, this paper is limited because it was difficult to sort the data with various areas and to approach various ways.

• The Journal of Engineering Geology
• /
• v.18 no.1
• /
• pp.69-81
• /
• 2008

Landslide researches are divided to a method of interrelationship for various factors, method of predicting landslide possibility, and method of estimating landslide risk which are occurring landslides in the natural slope. Most of landslides occurred in natural slope are caused by a heavy rainfall in summer season. Weathered soil layer located in upper side of rock mass was occurred. As well as, they are announced to have an influence to geometry, geology, soil characteristics, and precipitation in the natural slope. In order to investigate and interpret the variety of landslides from field investigation to risk analysis, landslide analysis process due to geotechnical and geological opinions are systematically demanded. In this research, the study area is located in Macheon area, Gyeongsangnam-do and performed the landslide investigation. From the results of landslide investigation and analysis, optimized standard model based on natural landslide is proposed to high technical method of landslide investigation and interpretation.

• Journal of Advanced Technology Convergence
• /
• v.1 no.1
• /
• pp.1-6
• /
• 2022

Since 2015, the government has been making efforts to distribute Korean smart farms. However, the supply is limited to large-scale facility vegetable farms due to the limitations of technology and current cultivation research data. In addition, the efficiency and reliability compared to the introduction cost are low due to the simple application of IT technology that does not consider the crop growth and cultivation environment. Therefore, in this paper, data analysis services was performed based on public and external data. To this end, a data-based target smart farm system was designed that is suitable for the situation of farms growing in facilities. To this end, a farm risk information notification service was developed. In addition, light environment maps were provided for proper fertilization. Finally, a disease prediction model for each cultivation crop was designed using temperature and humidity information of facility farms. Through this, it was possible to implement a smart farm data service by linking and utilizing existing smart farm sensor data. In addition, economic efficiency and data reliability can be secured for data utilization.

• Aerospace Engineering and Technology
• /
• v.4 no.2
• /
• pp.163-170
• /
• 2005

According to the KSLV program of KARI, it is planed to develop various launch vehicle and satellite 10 years hereafter. Large-scale test facilities, such as ReTF and PTA-II, are needed to fulfill this launch vehicle/satellite development project. The authors intend to arrange and describe various indexes that are needed in test facility design, construction and operation process. This technical paper is describing model analysis of damage prediction of accident in KSLV Integrated Propulsion System Test Facility based on propellant storage quantity and layout. In addition, the result can be used to produce safer design of test facility.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.8
• /
• pp.524-535
• /
• 2006

With rapid development of Internet technology, business management in an organization or an enterprise depends on Internet-based technology for the most part. Furthermore, as dependency and cohesiveness of network in the communication facilities are increasing, cyber attacks have been increased against vulnerable resource in the information system. Hence, to protect private information and computer resource, research for damage propagation is required in this situation. However the proposed traditional models present just mechanism for risk management, or are able to be applied to the specified threats such as virus or worm. Therefore, we propose the probabilistic model of damage propagation based on the Markov process, which can be applied to diverse threats in the information systems. Using the proposed model in this paper, we can predict the occurrence probability and occurrence frequency for each threats in the entire system.

• Journal of the Korean Society for Computer Game
• /
• v.31 no.4
• /
• pp.145-155
• /
• 2018

This study aims to extract additional elements to the existing game value evaluation using Delphi technique to 23 game experts. As a result of reviewing the characteristics of the development model using the evaluation model of the existing game contents, it was found that the evaluation factor was selected when selecting the content. The Delphi analysis was conducted two times, the first was the expert FGI and the second was the Delphi questionnaire. More detailed elements were presented in the related items such as results, technology transfer and dissemination, and details for promoting commercialization. Through focus group interviews, we extracted additional factors and predicted market size, growth potential, regulatory and market appeal and risk through market analysis of content success in the game industry. This will allow the industry to understand market size, growth potential, regulation, market appeal and risk through a market analysis of its success targets. This study suggests that the proposed evaluation factors can be applied to the entire game and cultural contents industry and will also help to construct market factors such as market value evaluation of contents, goal and goal setting, selection of entry method, and strategic factors.

• Journal of Korean Society of Transportation
• /
• v.27 no.3
• /
• pp.81-90
• /
• 2009

The safety management of a road network comprises four basic inter-related components：identification of sites(black spot) requiring safety investigation, diagnosis of safety problems, selection of feasible treatments for potential treatment candidates, and prioritization of treatments given limited budgets(Persaud, 2001). Identification process of selecting black spot is very important for efficient investigation of sites. In this study, the accident prediction model for EB method was developed by using accident data and geometric conditions of black spots selected from four-leg signalized intersections in In-cheon City for three years (2004-2006). In addition, by comparing the rank nomination technique using EB method to that by using accident counts, we managed to show the problems which the existing method have and the necessity for developing rational prediction model. As a result, in terms of total number of accidents, both the counts predicted by existing non-linear regression model and that by EB method have high good of fitness, but EB method, considering both the accident counts by sites and total number of accident, has better good of fitness than non-linear poison model. According to the result of the comparison of ranks nominated for treatment between two methods, the rank for treatment of almost sites does not change but SeoHae intersection and a few other intersections have significant changes in their rank. This shows that, with the technique proposed in the study, the RTM problem caused by using real accident counts can be overcome.