• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.230-237
• /
• 2022

It is difficult to predict industrial accidents in the construction industry because many accident factors, such as human-related factors and environment-related factors, affect the accidents. Many studies have analyzed the severity of injuries and types of accidents; however, there were few studies on the prediction of injured body parts. This study aims to develop a classification model to predict the part of the injured body based on accident-related factors. Construction accident cases from June 2018 to July 2021 provided by the Korea Construction Safety Management Integrated Information were collected through web crawling and then preprocessed. A naïve Bayes classifier, one of the supervised learning algorithms, was employed to construct a classification model of the injured body part, which has four categories: 1) torso, 2) upper extremity, 3) head, and 4) lower extremity. The predictor variables are accident type, type of work, facility type, injury source, and activity type. As a result, the average accuracy for each injured body part was 50.4%. The accuracy of the upper extremity and lower extremity was relatively higher than the cases of the torso and head. Unlike the other classifications, such as spam mail filtering, a naïve Bayes classifier does not provide a good classification performance in construction accidents. The reasons are discussed in the study. Based on the results of this study, more detailed guidelines for construction safety management can be provided, which help establish safety measures at the construction site.

• 한국재난정보학회 논문집
• /
• 제16권2호
• /
• pp.310-317
• /
• 2020

연구목적: 본 연구에서는 2014년부터 2019년까지 최근 6년간 발생한 화학사고 중 유해화학물질 운송차량사고의 특성을 분석하여, 운송과정에서 발생하는 화학사고를 예방하고자 하였다. 연구방법: 환경부 화학물질종합정보시스템의 통계자료를 활용하여, 운송차량에 의한 화학사고 사고유형, 사고원인, 차량종류로 나누어 조사하였다. 연구결과: 총 506건의 화학사고 중 운송차량에 의한 사고는 105건으로 조사되었으며, 전체 사고의 20% 이상 상회하는 수치를 보였다. 사고유형은 유·누출에 의한 사고가 대부분이었으며, 사고 주요 원인으로는 교통사고와 차량관리소홀이 각각 49건, 29건으로 전체 운송차량사고의 74%이상으로 나타났다. 차량유형별로는 탱크로리(57건, 54%)에서 가장 많이 발생하였으며, 화물트럭(39건, 37%), 트레일러(9건, 9%) 순으로 빈번하게 발생하였다. 결론: 운송차량 사고의 예방을 위해서는 운송차량의 철저한 점검 및 운전자의 안전운행이 요구된다. 또한 정부는 운송차량의 실시간 모니터링을 확대하고, 소관 부처별로 상이한 제도를 통합적으로 관리할 필요성이 있다.

• 한국화재소방학회논문지
• /
• 제30권6호
• /
• pp.23-30
• /
• 2016

본 연구는 화학물질 운송 화학사고를 대상으로 각 연도별 사고현황, 사고유형, 사고원인 등의 화학사고 특성을 분석하였다. 그 결과 77건의 운송 화학사고 중 74건이 유 누출 유형에 의한 사고였으며, 사고 원인으로는 41건이 교통사고에 의한 화학사고였다. 또한, 사고다발 화학물질 조사에서는 46건의 사고가 유해화학물질에 의한 사고인 것으로 조사되었다. 화학물질 운송 화학사고의 예방 및 대응을 위해서는 화학물질 유 누출과 화학물질의 운송 교통사고에 의한 화학사고에 대한 예방책의 보완이 필요하며, 운송 화학사고가 발생되었을 경우 방재가 시스템적으로 신속히 이루어질 수 있도록 범국가적이고 체계적인 화학물질 운송안전 시스템을 구축하여 화학물질 운송에 적용하는 것이 필요하다.

• 한국안전학회지
• /
• 제24권6호
• /
• pp.111-118
• /
• 2009

As the construction project gets bigger in scale, the actual construction itself is becoming more complex. The construction accidents occupy 26.18 percent of total death disaster according to the accidents report in 2007. It is the highest figure among the entire industry, and it shows how serious the construction accident is. In order to reduce accidents occurred in the construction industry, we should find the accident characteristics of construction workers by age. In this study, we investigated 589 cases of fatal accidents, and classified them by trades, type of works, the things that caused the accident, how they occurred, and size. We then identified accident characteristics for each group by analysing them in accordance with workers age. The result of analysis showed that in carpenter and common laborer, the number of death accidents increased as the workers age increased. Another characteristics were that the number of death accidents increased as the age increased in finishing work and reinforced concrete construction and in a smaller-scale businesses, respectively. Common labor was the trade with the highest number of death accidents and the laborers of 50 age or higher in age in finishing working type were the most vulnerable to death accidents.

• 한국산학기술학회논문지
• /
• 제21권7호
• /
• pp.616-624
• /
• 2020

본 연구의 목적은 노인 운수사고 입원 환자의 운수사고 유형과 사망 사이의 연관성을 분석하여, 노인 운수사고 입원 및 사망 환자를 줄이기 위한 운수사고 유형에 따른 체계적이고 효과적인 정책 개발 및 수립에 기여하기 위함이다. 본 연구의 방법은 2013-2017년의 질병관리본부 퇴원손상심층조사 데이터세트 중 운수사고를 입은 노인 입원환자를 추출하여 기술통계분석, 카이제곱검정과 다중 로지스틱 회귀분석을 실시하였다. 인구사회학적, 의료기관, 의료이용 특성을 보정한 상태에서 분석한 결과 운수사고로 인한 노인의 입원 사망은 승용차 사고에 비하여 보행자 사고(OR : 2.522 95% CI 1.291-4.927), 자전거/카트 사고(OR : 2.809 95% CI 1.328-5.942), 오토바이 사고(OR : 2.330 95% CI 1.126-4.819)로 인한 사망이 각각 통계적으로 유의하게 높았다. 이와 같이 노인의 경우 승용차 사고로 인한 사망에 비하여 다른 유형의 운수사고로 인한 사망의 위험이 높지만, 우리나라 노인의 운수사고 관련 정책은 승용차 사고에 집중되어 있다. 따라서 증가하는 노인 집단의 운수사고 사망자를 줄이기 위하여 노인 집단의 운수사고 유형별 특성에 따른 효과적인 정책적 고려가 필요할 것으로 사료된다.

• 대한안전경영과학회지
• /
• 제25권2호
• /
• pp.39-48
• /
• 2023

Recently, the crisis of demographic extinction is rising in Korea more than any other country, and it is difficult for industrial sites to maintain without 'foreign workers'. Industrial accidents and accident deaths of foreign workers account for 7.6% and 12.3% of the total, through an in-depth analysis of fatal accidents in the manufacturing industry, differences and similarities between fatal accidents of foreign workers and all fatal accidents were confirmed in terms of occurrence type, workplace size, length of service, employment type, etc. In this study, customized countermeasures were found.

• 대한안전경영과학회지
• /
• 제24권1호
• /
• 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.

• 한국건축시공학회지
• /
• 제7권3호
• /
• pp.115-122
• /
• 2007

As buildings become higher, larger, and more complex, safety issues for construction workers working at such environments become more important. We analyzed 83 critical accident cases reported to the KOSHA(Korea Occupational Safety & Health Agency) for construction cranes by types of cranes and by patterns of accidents and causes. There are more number of accidents related to mobile cranes than that related to tower cranes, but the numbers of dead were similar in both cases. The most dominant cause of crane accidents was "fall of materials". We also analyzed the cases of crane accidents using the FMEA(Failure Mode and Effect Analysis) in order to set up a priority for safety management and also to prioritize research and development items relating tower cranes. In the process, we tried to eliminate subjective indexes such as an expert group survey and use objective and quantitative indexes. As a result, it was found that critical crane accidents occurs most during the "lifting and translating" activity.

• 한국안전학회지
• /
• 제20권4호
• /
• pp.130-137
• /
• 2005

Decision tree algorithm is one of the data mining techniques, which conducts grouping or prediction into several sub-groups from interested groups. This technique can analyze a feature of type on groups and can be used to detect differences in the type of industrial accidents. This paper uses C4.5 algorithm for the feature analysis. The data set consists of 24,887 features through data selection from total data of 25,159 taken from 2 year observation of industrial accidents in Korea For the purpose of this paper, one target value and eight independent variables are detailed by type of industrial accidents. There are 222 total tree nodes and 151 leaf nodes after grouping. This paper Provides an acceptable level of accuracy(%) and error rate(%) in order to measure tree accuracy about created trees. The objective of this paper is to analyze the efficiency of the C4.5 algorithm to classify types of industrial accidents data and thereby identify potential weak points in disaster risk grouping.

• 한국항공운항학회지
• /
• 제12권2호
• /
• pp.59-70
• /
• 2004

Most of studies on aircraft accidents have been conducted mainly for fixed-wing aircraft, while the studies on helicopter accidents have been done less even though the helicopter accidents occurred quite more than those of the fixed-wing. There are lots of differences between helicopter and fixed-wing accidents, in aspect of causes and occurrence of accidents as well as aerodynamics and operation. In Korea, helicopter accidents have occurred 2 or 3 times annually since 2000, while the number of fixed-wing aircraft accidents has been reduced considerably. The goal of this study is to solve the present safety problems in helicopter accidents by reviewing the characteristics of past accidents and comparing differences between two types of aircraft.