• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.9 s.351
• /
• pp.25-31
• /
• 2006

In this paper, a fatality model of car accident using data mining is proposed with the goal of reducing fatality of traffic accident. The analysis results with a proposed fatality model are utilized to improve a technology and environment for driving. For this, traffic accident data are collected, a data mining algorithm is applied to this data, and then, a fatality model of car accident is developed based on the analysis. The training data as well as test data are utilized to develop the fatality model. The important factors to cause fatality in traffic accidents can be investigated using the model. If these factors are taken into account in traffic policies and driving environment, it is expected that the fatality rate of traffic accident can be reduced hereafter.

• Proceedings of the KSR Conference
• /
• 2005.11a
• /
• pp.246-251
• /
• 2005

Accident scenarios analysis is a course to understand, analyze, and describe a process of an accident and behavior pattern of the parties to an accident. The method of accident scenarios is that we described patterns represented between accidents and hazardous conditions, and then provide data to prevent the accident. We have carried out scenarios analysis in various fields so far, but it was not taking account of system. In this research, we made a study on technology of accident scenarios analysis using QFD (Quality Function Deployment) to analyze systematically and evaluate quantitatively types of hazards and scenarios of railway accident. And we analyses accident scenarios of a subject of work-related fatality accident to railway employee and conducted risk assessment for different scenarios. Also we defined relation between unsafe events and hazardous conditions caused to work-related fatality accident, and attempted to quantitatively assess work-related fatality accident and the parties to accidents. The results of this research will be used in analyzing for important causes and contributing factors of work-related fatality accidents at the step of risk assessment of railway system, and quantitatively assessing frequency of work-related accidents and risk.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.28 no.3
• /
• pp.312-318
• /
• 2018

Objectives: This study is aimed to illustrate the status of the occupational accident rate, fatality rate, and musculoskeletal disorder rate by safety and health management type in workplaces. Methods: In order to analyze the status of the occupational accident rate, fatality rate, and musculoskeletal disorder rate of different safety and health management types in workplaces, selected data from the Occupational Safety and Health Research Institute were used. Results: The occupational accident rate in workplaces where safety and health managers had been appointed was lower than in those where safety and health management was entrusted to other organizations, while the result was the opposite in regards to the fatality rate per 10,000 workers caused by accident. However, the occupational fatality rate per 10,000 workers in workplaces where safety and health managers have other roles was 426% higher than those where safety and health management was entrusted to other organizations. Moreover, the musculoskeletal disorder rate of the workplaces where safety and health managers have other roles was 15% higher than those where health management was entrusted to other organizations. Conclusions: It is necessary to review the effectiveness of systems in which safety and health managers can concurrently engage in other roles.

• Proceedings of the Safety Management and Science Conference
• /
• 2011.04a
• /
• pp.177-183
• /
• 2011

Korea has performed strategies for the third industrial accident prevention in order to minimize industrial accident. However, the occupational fatality rate and industrial accident rate appears to be stagnated for 11 years. Therefore, this paper forecasts the occupational fatality rate and industrial accident rate for 10 years. Also, this paper applies regression method (RA), exponential smoothing method (ESM), double exponential smoothing method (DESM), autoregressive integrated moving average (ARIMA) model and proposed analytical function method (PAFM) for trend of industrial accident. Finally, this paper suggests fundamental strategies for industrial accident prevention by forecasting of industrial accident rate in the long term.

• Journal of the Korea Safety Management & Science
• /
• v.24 no.4
• /
• pp.41-47
• /
• 2022

A reliable prediction model of national occupational accident fatality rate can be used to evaluate level of safety and health protection for workers in a country. Moreover, the socio-economic aspects of occupational accidents can be identified through interpretation of a well-organized prediction model. In this paper, we propose a machine learning based relative comparison methods to predict and interpret a national occupational accident fatality rate based on socio-economic indicators. First, we collected 29 years of the relevant data from 11 developed countries. Second, we applied 4 types of machine learning regression models and evaluate their performance. Third, we interpret the contribution of each input variable using Shapley Additive Explanations(SHAP). As a result, Gradient Boosting Regressor showed the best predictive performance. We found that different patterns exist across countries in accordance with different socio-economic variables and occupational accident fatality rate.

• Journal of the Korean Society of Safety
• /
• v.35 no.3
• /
• pp.72-78
• /
• 2020

The accident fatality rate has decreased by more than 90% compared to 2006, due to the safety management and safety investment based on the Rail Safety Act. Most railway safety indicators, including fatality rates, have improved significantly from 60% to 80%, reaching the level of developed countries in terms of most railway safety indicators. However, the only staff fatality rate at work is not improved, and it is 3 to 5 times higher than that of developed countries. Most of the fatality occurred during employee's work recently occurred due to accidents hit by train while track work. In principle, when operating track need to check or maintenance, the operation of the train should be stopped and the work carried out. However, in Korea, due to the highest passenger density and train operating density in the world, it is caused by a structural problem that requires workers to enter the track while the train is running and perform various tasks such as maintenance and inspection. In this study, we analyzed the risk of accidents caused by hit by trains on the track, which is the biggest cause of staff fatality, using the main statistics of the last 10 years. In detail, the scenarios of the main causes of hit by trains and workers were formed to suggest the effectiveness of the current preventive measures and supplementary.

• Journal of the Korean Society of Safety
• /
• v.33 no.4
• /
• pp.111-118
• /
• 2018

Korea is facing a surge in the aging population, showing that population aged 65 and above will be accounted for 42.5% of the total population in 2065 with the emphasis on the over-80 population consisting of 19.2%. In response to this abrupt change in population structure, the number of traffic fatality accident referring to older driver as aged 65+ years had been increasing from 605 fatalities in 2011 to 815 fatalities in 2015 resulting in increases in 34.7% in oppose to happening to decreases in 17.2% about non-older driver. With Logit analysis based on Newton-Raphson algorithm utilizing older driver's traffic fatality data for the 2011-2015 years, it was found that the likelihood of an accident resulting in a fatality for super older driver aged 80 years and above considerably increased compared to other older driver with aging classification: 2.24 times for violation of traffic lane, 2.04 times for violation of U-turn, 1.48 times for violation of safety distance, 1.35 times for violation of obstacle of passing; also average annual increase of traffic accident cost related to super older driver was fairly increased rather than other older driver groups. Hence, this study proposes that improving and amending transport safety system and Road Traffic Act for super older driver needs to be urgently in action about license management, safe driving education, etc. when considering the increase of over-80 population in the near future. Also, implementing a social agreement with all ages and social groups to apply with advanced driver assistance system for older driver groups will be able to become a critical factor to enhance safe driving over the face of the country.

• Nuclear Engineering and Technology
• /
• v.37 no.3
• /
• pp.245-258
• /
• 2005

This paper addresses two types of uncertainty: stochastic uncertainty and subjective uncertainty in probabilistic accident consequence assessments. The off-site consequence assessment code OSCAAR has been applied to uncertainty and sensitivity analyses on the individual risks of early fatality and latent cancer fatality in the population outside the plant boundary due to a severe accident. A new stratified meteorological sampling scheme was successfully implemented into the trajectory model for atmospheric dispersion and the statistical variability of the probability distributions of the consequence was examined. A total of 65 uncertain input parameters was considered and 128 runs of OSCAAR with 144 meteorological sequences were performed in the parameter uncertainty analysis. The study provided the range of uncertainty for the expected values of individual risks of early and latent cancer fatality close to the site. In the sensitivity analyses, the correlation/regression measures were useful for identifying those input parameters whose uncertainty makes an important contribution to the overall uncertainty for the consequence. This could provide valuable insights into areas for further research aiming at reducing the uncertainties.

• Safety and Health at Work
• /
• v.7 no.3
• /
• pp.213-217
• /
• 2016

Background: The objective of this study is to identify high-risk groups for industrial accidents by setting up 2003 as the base year and conducting an in-depth analysis of the trends of major industrial accident indexes the index of industrial accident rate, the index of occupational injury rate, the index of occupational illness and disease rate per 10,000 people, and the index of occupational injury fatality rate per 10,000 people for the past 10 years. Methods: This study selected industrial accident victims, who died or received more than 4 days of medical care benefits, due to occupational accidents and diseases occurring at workplaces, subject to the Industrial Accident Compensation Insurance Act, as the study population. Results: According to the trends of four major indexes by workplace characteristics, the whole industry has shown a decreasing tendency in all four major indexes since the base year (2003); as of 2012, the index of industrial accident rate was 67, while the index of occupational injury fatality rate per 10,000 people was 59. Conclusion: The manufacturing industry, age over 50 years and workplaces with more than 50 employees showed a high severity level of occupational accidents. Male workers showed a higher severity level of occupational accidents than female workers. The employment period of < 3 years and newly hired workers with a relatively shorter working period are likely to have more occupational accidents than others. Overall, an industrial accident prevention policy must be established by concentrating all available resources and capacities of these high-risk groups.

• International Journal of Safety
• /
• v.3 no.1
• /
• pp.47-52
• /
• 2004

Current OSH system was analyzed in this paper to explain why high fatal incidents and disasters are continuously repeated for recent years in Korea. It was found that we have Dichotomous Perceptional Misconception of prevention before accident and compensation after accident and there is a significant lack of proper feed­back reward system for OSH performance. It was assumed that no reduction of accident rate and fatality rate have not been achieved recently despite of a great effort and increased resource allocations. Some statistics for proving weak punishment were analyzed. In the current system, the will of administrative agency would have been very limited particularly in the legal aspects. The Industrial Safety and Health Act is not suitable to after-injury punishment for employer and/or corporate since it is based on a framework for enforcement of prevention. Based on these analyses, it was concluded that there was a need to consider a special law for Corporate Accountability for Fatal Accidents. Because it is necessary to consider seriously for introduction of a new legal system for after injury punishment to repair the current system where it was found lack of proper feedback system. Also, there was no proper sanction measures for corporate with the current OSH legal system, and the most urgent problem in OSH area is the high fatality rate. it is necessary to consider seriously for introduction of a new legal system for after injury punishment. Also, there is no proper sanction measures for corporate with the current OSH legal system, and the most urgent problem in OSH area is the high fatality rate.