• Journal of the Korea Safety Management & Science
• /
• v.8 no.3
• /
• pp.1-9
• /
• 2006

Recently data mining techniques have been used for analysis and classification of data related to industrial accidents. The main objective of this study is to compare algorithms for data analysis of industrial accidents and this paper provides an optimal predicting model of 5 kinds of algorithms including CHAID, CART, C4.5, LR (Logistic Regression) and NN (Neural Network) with ROC chart, lift chart and response threshold. Also, this paper provides an approximation model for an optimal predicting model based on NN. The approximation model provided in this study can be utilized for easy interpretation of data analysis using NN. This study uses selected ten independent variables to group injured people according to a dependent variable in a way that reduces variation. In order to find an optimal predicting model among 5 algorithms, a retrospective analysis was performed in 67,278 subjects. The sample for this work chosen from data related to industrial accidents during three years ($2002\;{\sim}\;2004$) in korea. According to the result analysis, NN has excellent performance for data analysis and classification of industrial accidents.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.3 no.1
• /
• pp.127-139
• /
• 1993

In order to obtain basic information for the extablishment of effectivce industrial safety programmes in heavy industries & construction companies, accident records for 366 injured workes were collected from January, 1989 to December 1991 and analyzed. The results were as follows : 1. The over-all incidence rate of industrial accidents was 2.98% per year 2. Accidents were common in the workers who are in thirties and twenties. 3. According to the duration of services, the workers with jobs on above than 3 years was the most frequent victims (64.2%) 4. According to the view point of working time, the highest incidence was observed just before the end of the work (17:00-19:00). 5. According to the month of year, the incidence was higher in August(14.0%) and May(14.2%), and lowest in January (3.3%) 6. The most common type of accidents was overexertion (24.9%). 7. According to the job, the highest incidence was observed fabrication. 8. According to the site of injuries, the incidence was higher the truck (27.0%) and fingers (25.1%).

• Proceedings of the KIEE Conference
• /
• 2005.05b
• /
• pp.35-40
• /
• 2005

Many industrial disasters and safety-accidents are occurred constantly in current industrial society of domestic country. Although there are many attempts to reduce the occurrence of various industrial disasters and safety-accidents through exhaustive safety trainings and strict rules applied to fieldwork in electrical construction, still those accidents are not eradicated completely. The purpose of this study is to take counter measures against similar or same safety-accidents by analyzing the types of accidents and reasons among critical accident cases, which are occurred in electrical construction field.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1995.06a
• /
• pp.55-63
• /
• 1995

Press accidents are one of the most popular industrial accidents. Two factors are considered to lead to press accidents, one is human, the other press machine itself. Accident itself is analyzed and concluded to be due to incomplete interaction between press and human. A press design considering safety as a methodology is introduced to reduce the industrial accidents by press machine, that is micro-inching locking system.

• Journal of the Korean Institute of Rural Architecture
• /
• v.16 no.1
• /
• pp.95-102
• /
• 2014

The number of industrial accident victims in the construction industry accounts for 1/3 of those in the entire industries and about 30% of the total compensation costs are spent in the construction industry. As such, the construction industry is a typical industry causing numerous safety accidents. This study analyzes the status of industrial accidents in small scale construction sites to build maximum five-story buildings by examining statistical data for the past five years, investigating those construction sites and conducting interviews with the workers. This study also seeks the causes of and measures for industrial accidents in the small scale construction industry through comparison with relevant systems. The findings are as follows: (1) To reduce hazard rate, shaping the working environment and safety measures that take into account the physically weak classes of the middle aged and the aging are urgently required, because 62.9% of the industrial accidents in the construction industry occurred to those who are 50 years of age or older. (2) The hazard rate at small scale construction sites with less than 10 construction workers accounts for 55% of that of the entire industries. The government, in this context, needs to support finance or technology and improve system by selecting the small scale construction sites, where industrial accidents occur frequently. (3) Because the hazard rate of unskilled workers with less than 6 months of work experience accounts for 90.95% of the total, safety education needs to be concentrated on those unskilled workers. (4) The relevant standards need to be segmented and revised and bolstered, given that 64.79% of death disaster in the construction industry occurs in the temporary structures including scaffolds and ladders.

• Journal of the Korean Society of Safety
• /
• v.27 no.2
• /
• pp.42-48
• /
• 2012

The present study was motivated by the needs to make diversified scientific approaches toward influential factors like human, technical, organization, policy and environmental on the basis of the specialized information concerning the cause for industrial accidents in a measure to prevent the falling accident which has the biggest priority among the three major frequent industrial accidents. In this connection, diverse policies have been practiced in the meantime, with little effects in fact to reduce occurrence of industrial accidents, seemingly because such policies have been practiced on the direct dimension, instead of tries to nip in the bud of fundamental causes. This study was thus conducted with a view to determine the causes that have influence on falling accidents from the overall context and unearth the factors requiring management with priority. For this aim, "Fall from Height"(2003), a study by HSE, UK was applied to various conditions of korea as an experiment to search for fundamental causes for falling accidents. The major findings of this study might be summed up as exploring a main critical path that has influence upon falling accidents and suggesting effective ways to cut down through the critical path.

• Journal of the Ergonomics Society of Korea
• /
• v.34 no.4
• /
• pp.353-362
• /
• 2015

Objective: This study aims to analyze occupational accidents of moving helpers by work place type which means the type of residence where moving operation is done. Background: Most efforts have been focused on the industry base comprising various occupational spectrum and provided industry general preventative policies. But occupation specific policies are required for the workers involved and will reduce the occurrences of occupational accidents for the workers subject to similar working environment and process. Method: This study analyzes 208 non-motor vehicle collision related occupational accidents of moving helpers working for used household and office goods moving industry occurring from 2010 to 2012. Accident Type, agencies, event or exposure, parts of body affected are characterized by work places according to the work environment. Results: Accidents characteristics showed the difference between high-rise type and low-rise type on the size of enterprise, age, gender and work experience of the injured. Also the accident type, source of accident and parts of body affected are different between the two work place types. Finally, Accidents occurred on the specific operational processes of moving service also showed different characteristic between the two types. Conclusion and Application: The findings of accident characteristics according to workplace types and operational process of moving service can be used as baseline data for establishing systemized preventative policies for occupational accidents of moving helpers.

• Journal of the Korea Safety Management & Science
• /
• v.24 no.1
• /
• pp.91-98
• /
• 2022

Since cranes are a kind of complex human-machine systems, it is almost impossible to completely secure safety with current technologies. Therefore, managerial interventions to prevent human errors are needed for safely operating a crane. The Occupational Safety and Health law states that cabin-type crane operators should have crane drivers' licence and crane-related operators (e.g., pendent-type crane operators, slinging workers) should take a special safety training. However, statistics on industrial accidents showed that fatalities due to crane accidents (185 accidents occurred during 2013~2017) were the highest among hazardous machinery and equipment. To effectively control the crane-related accidents, voices of crane workers need to be analyzed to investigate the current status. This study surveyed perceived causes of crane accidents and status of special safety training for crane workers of 387. The survey revealed that 24.3% of the respondents experienced crane accidents and 31.4% eye-witnessed crane accidents. 79% of the respondents pointed human errors such as improper crane operation and improper slinging as the first cause. Lastly, only 16.7% of the respondents took a professional special safety training; but the rest took lecture-based or incomplete education. The findings of the present study can be applied to improve crane-related policies and special safety training systems.

• Journal of the Korea Safety Management & Science
• /
• v.8 no.2
• /
• pp.51-59
• /
• 2006

So far, there is no technique of quantitative evaluation on danger related to industrial accidents. Therefore, as an endeavor for obtaining technique of quantitative evaluation, this study presents feature analysis of industrial accidents in manufacturing field using QUEST algorithm. In order to analyze feature of industrial accidents, a retrospective analysis was performed in 10,536 subjects (10,313 injured people, 223 deaths). The sample for this work chosen from data related to manufacturing businesses during three years $(2002\sim2004)$ in Korea. The analysis results were very informative since those enable us to know the most important variables such as occurrence type, company size, and occurrence time which can affect injured people. Also, it is found that classification using QUEST algorithm which was performed in this study is very reliable.

• Journal of the Korean Society of Safety
• /
• v.31 no.1
• /
• pp.1-6
• /
• 2016

Severity and frequency of industrial accidents are typically used to assess the "absolute" risk associated with the industrial machines and devices ("items") which are subject to safety certification or self-declaration of conformity. However, the "relative" risk associated with a particular item can further be assessed based on unit severity and unit frequency where the total number of item in use is taken into account. This study first attempts to estimate the total number of each item in use which was recently selected for safety certification or self-declaration of conformity. The appropriateness of such selection is recapitulated based on the relative risk involved. Analysis results indicate that depending on items, the relative risk is differentiated from the absolute risk. Recent selection of items for safety certification or self-declaration of conformity is then revisited for its validity. The relative risk based on unit severity and unit frequency of industrial accidents, together with the absolute risk, may be used to further categorize items for safety certification or self-declaration of conformity in the future.