• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2015.10a
• /
• pp.193-195
• /
• 2015

해양사고 원인의 70 % 이상을 차지하는 인적오류 예방은 해양안전에 가장 중요한 이슈이다. 인적오류는 확률기반의 인적 모델을 구축하여 평가함으로써 예상되는 위기의 수준을 과학적으로 예측할 수 있다. 확률기반 인적 모델을 구축하기 위해서는 사건의 원인과 결과 사이에 연계성을 갖고 있는 통계 데이터가 필요하다. 본 연구에서는 이러한 연계 데이터 확보를 위한 것으로, 해양안전심판원의 통계 데이터 사이의 연계성 확보 방안을 주로 검토하였다. 그리고 이러한 통계 데이터를 인적 모델에 적용하는 방법과 전략도 검토하였다. 인적 모델은 회사, 선박, 해기사 관련 요소들이 총체적으로 반영될 필요가 있음을 알았고, 이러한 세 가지 요소로 구성된 통합 모델을 설계하기 위한 방안도 검토하였다. 특히, 각 요소들에 포함될 데이터 사이의 연계성 확보를 위해서 해양사고 연계 체인(Chain)을 도입하였다. 확보한 데이터는 사고의 가장 근본원인인 Hazard부터 사고의 영향을 나타내는 Impact까지의 6 단계 분석 방법을 적용하여 통계 데이터에 결합되어 있는 원인과 결과 사이의 연계성을 확보할 수 있는 방안을 수립하였다. 본 연구는 중장기적으로 추진할 과제이기 때문에 향후 본 연구 내용을 토대로 인적 모델을 개발하여 해양사고 예방에 적극 기여하고자 한다.

• Korean Journal of Construction Engineering and Management
• /
• v.25 no.5
• /
• pp.25-31
• /
• 2024

The purpose of this study is to propose a model development framework to predict the risk of safety accidents for foreign workers based on a deep learning algorithm for systematic safety management of foreign workers in the construction industry. Many past studies have shown that foreign workers working at construction sites are relatively more vulnerable to safety accidents than non-foreign workers, but quantitative research on the risk of safety accidents among foreign workers working at construction sites is lacking. Furthermore, due to a lack of predictive research on safety accidents, realistic and systematic safety management for foreign workers is not possible. Therefore, in order to complement this, this study proposes a deep learning algorithm-based model that collects, analyzes, and predicts safety accident data occurring at construction sites for systematic safety management of foreign workers at construction sites. The results and framework of this study can be used to analyze and predict various safety accident risks that occur at construction sites, and ultimately can serve as an important guideline for safety management of foreign workers at construction sites.

• Journal of the Korean Society for Railway
• /
• v.20 no.4
• /
• pp.482-490
• /
• 2017

This study is a railway accident investigation statistic study with the purpose of prediction and classification of accident severity. Linear regression models have some difficulties in classifying accident severity, but a logistic regression model can be used to overcome the weaknesses of linear regression models. The logistic regression model is applied to escalator (E/S) accidents in all stations on 5~8 lines of the Seoul Metro, using data mining techniques such as logistic regression analysis. The forecasting variables of E/S accidents in urban railway stations are considered, such as passenger age, drinking, overall situation, behavior, and handrail grip. In the overall accuracy analysis, the logistic regression accuracy is explained 76.7%. According to the results of this analysis, it has been confirmed that the accuracy and the level of significance of the logistic regression analysis make it a useful data mining technique to establish an accident severity prediction model for urban railway casualty accidents.

• Journal of the Korean Institute of Gas
• /
• v.18 no.1
• /
• pp.8-16
• /
• 2014

In this study, the number of gas accidents prediction model was suggested by analyzing the gas accidents occurred in Korea. In order to predict the number of gas accidents, simple moving average method (3, 4, 5 period), weighted average method and exponential smoothing method were applied. Study results of the sum of mean-square error acquired by the models of moving average method for 4 periods and weighted moving average method showed the highest value of 44.4 and 43 respectively. By developing the number of gas accidents prediction model, it could be actively utilized for gas accident prevention activities.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.194-194
• /
• 2012

본 연구에서는 자연하천에서 Rhodamine-WT를 이용하여 추적자 실험을 수행하고 이를 바탕으로 오염사고대응예측모델에 대한 검증을 실시하고자 하였다. 최근 국내에서는 다양한 형태와 규모의 수질오염사고가 매년 수십건 이상 발생하고 있으며, 따라서 수치모형 기반의 수질오염 사고 대응 예측시스템에 대한 높은 신뢰성이 요구되고 있다. 수질사고에 노출되어 있는 지표수를 각종 용수로서 안전하게 공급하기 위해서는 정확한 수질예측이 필수적이며, 이를 위해서 수십 년간 연구되어 온 수질모델을 오염사고 대응예측시스템에 적합하도록 정확성과 신뢰성을 갖추기 위한 연구가 진행되어야 한다. 수치 모형을 이용한 물질의 이송 및 확산 모의에서는 오염물질 도달시간과 확산 농도를 결정하는 것이 가장 중요한 요소이므로 이송 및 확산 모의에 대한 검증 기법 개발 및 적용이 필요하다. 본 연구에서는 낙동강수계 지류하천인 감천에서 추적자 실험을 4회 실시하여 측정한 수리량과 농도 실측치를 이용하여 분산계수를 종 횡분산계수 산정이 가능한 2차원 유관추적법을 적용하여 산정하였다. 각 단면에 유속은 ADV-3차원 유속계인 Flow-Tracker를 사용하여 도섭으로 측정하였으며 하천의 흐름 방향의 직각으로 측선을 설치하고 펌프를 이용하여 채수를 한 다음 Rhodamie WT의 농도를 측정하였으며 측선의 위치 보정은 GPS를 통하여 보정하였다. 측정 자료를 이용하여 2차원 유관추적법으로 분산계수를 산정한 결과 각각의 측선에 따라서 다소 차이가 발생하였으며, 일부 구간에서는 이론식으로 계산한 분산계수와 근사한 값이 나타났다. 이는 사주가 매우 발달하고 만곡이 많은 실험구간의 특성상 Elder와 Fischer 식으로 계산한 값과 차이가 발생할 가능성이 높은 구간이기 때문인 것으로 판단된다. 또한 하폭에 대한 수심비가 커질수록 분산계수도 증가하고 평균유속에 대한 전단유속에 비에 비례하는 것으로 나타났다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.1
• /
• pp.16-24
• /
• 2023

Accidents are greatly reduced through projects to improve frequent traffic accidents. These results show that safety facilities play a big role. Traffic accidents are caused by various causes and various environmental factors, and it is difficult to achieve improvement effects by installing one safety facility or facilities without standards. Therefore, this study analyzed the improvement effect of each accident type by combining the two safety facilities, and suggested a method of predicting the combination of safety facilities suitable for a specific point, including environmental factors such as road type, road type, and traffic. The prediction was carried out by selecting an XGBoost technique that creates one strong prediction model by combining prediction models that can be simple classification. Through this, safety facilities that have had positive effects through improvement projects and safety facilities to be installed at points in need of improvement were derived, and safety facilities effect analysis and prediction methods for future installation points were presented.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.7
• /
• pp.257-262
• /
• 2021

Accidents caused by black ice occur frequently every winter, and the fatality rate is very high compared to other traffic accidents. Therefore, a systematic method is needed to predict the black ice formation before accidents. In this paper, we proposed a black ice prediction model based on heterogenous and multi-type data. To this end, 12,574,630 cases of 46 types of land, infrastructure, transport public data and meteorological public data were collected. Subsequently, the data cleansing process including missing value detection and normalization was followed by the establishment of approximately 600,000 refined datasets. We analyzed the correlation of 42 factors collected to predict the occurrence of black ice by selecting only 21 factors that have a valid effect on black ice prediction. The prediction model developed through this will eventually be used to derive the route-specific black ice risk index, which will be utilized as a preliminary study for black ice warning alart services.

• Fire Science and Engineering
• /
• v.33 no.6
• /
• pp.72-79
• /
• 2019

Through this study, we developed a model for predicting chemical accidents lead to casualties. The model was derived from the logistic regression analysis model and applied to the variables affecting the accident. The accident data used in the model was analyzed by studying the statistics of past chemical accidents, and applying independent variables that were statistically significant through data analysis, such as the type of accident, cause, place of occurrence, status of casualties, and type of chemical accident that caused the casualties. A significance of p < 0.05 was applied. The model developed in this study is meaningful for the prevention of casualties caused by chemical accidents and the establishment of safety systems in the workplace. The analysis using the model found that the most influential factor in the occurrence of casualty in accidents was chemical explosions. Therefore, there is an urgent need to prepare countermeasures to prevent chemical accidents, specifically explosions, from occurring in the workplace.

• Journal of the Korea Institute of Building Construction
• /
• v.23 no.6
• /
• pp.831-839
• /
• 2023

This study aims to develop a framework for an accident prediction model leveraging a deep neural network algorithm, specifically tailored for small-scale construction sites. Notably, the incidence of accidents in the construction sector is markedly higher compared to other industries, with a significant contribution from small-scale sites. The challenging nature of construction in urban settings, coupled with the increasing frequency of adverse weather conditions, is likely to escalate accident risks at these sites. Anticipating and mitigating accidents at small-scale construction sites is therefore crucial to decrease the overall industry accident rate. Consequently, this research introduces a Deep Neural Network-based model for forecasting accidents at small-scale construction sites. The framework and findings of this study are poised to serve as a guideline for the safety management of small-scale construction projects, ultimately aiding in the realization of safer, more sustainable construction practices at these sites.

• Journal of the Korean Institute of Gas
• /
• v.16 no.1
• /
• pp.33-38
• /
• 2012

Analysis on gas accidents by types occurred has been made to prevent the recurrence of accidents, through analysis of past history of gas accident occurring environment. The number of gas accidents has been decreasing, but still accidents are occurring steadily. Gas-using environment and gas accidents are estimated to be closely connected since gas-using types are changing by time period, weather, etc. in terms of accident contents. As a result of analysing gas accidents by 7 meteorological elements, such as the mean temperature, the highest temperature, the lowest temperature, relative humidity, the amount of clouds, precipitation and wind velocity, it has been found out that gas accidents are influenced by temperature or relative humidity, and accident occurs more frequently when the sky is clean and wind velocity is slow. Possibility of gas accidents can be provided in real time, using the proposed model made to predict gas accidents in connection with the weather forecast service. Possibility and number of gas accidents will be checked real time by connecting to the business system of Korea Gas Safety Corp., and it is considered that it would be positively used for preventing gas accidents.