The consequences of rapid industrial advancement, diversified types of business and unexpected industrial accidents have caused a lot of damage to many unspecified persons both in a human way and a material way Although various previous studies have been analyzed to prevent industrial accidents, these studies only provide managerial and educational policies using frequency analysis and comparative analysis based on data from past industrial accidents. The main objective of this study is to find an optimal algorithm for data analysis of industrial accidents and this paper provides a comparative analysis of 4 kinds of algorithms including CHAID, CART, C4.5, and QUEST. Decision tree algorithm is utilized to predict results using objective and quantified data as a typical technique of data mining. Enterprise Miner of SAS and AnswerTree of SPSS will be used to evaluate the validity of the results of the four algorithms. The sample for this work chosen from 19,574 data related to construction industries during three years (2002~2004) in Korea.

The life change unit(LCU) models by behavior scientific approach method are very important in order to minimize industrial accident by the job stress. Especially, these models are analyzed the accident proneness concept through the LCU factors. Therefore this paper describes the analytical results between the Eastern LCU model and Western LCU model and its application. Death of parents, death of close friend, jail term, personal injury or illness between the Eastern LCU models and Western LCU models are different in the human behavior and psychological sides, whereas changes in family member s health are turned out same life ideas. In the case of Korean LCU models between the unmarried and married workers living in the middle area are approved in the order of death of parents, death of spouse, death of close family member, and death of close friend.

Many researches have been focused on the analysis of industry disasters in order to reduce them. As a similar endeavor, this paper provides a propensity analysis of injured people from various industries using classification and regression tree(CART), a data mining algorithm. The sample for this work was chosen from 25,157data related to various industries during one year ( 2003.2~2004.1 ) at Kangwon-Do in Korea. For the purpose of this paper, eight independent variables (injured date, injured time, injured month, type of Injured person, continuous service period, sex, company size, age)are taken from injured person group. According to the analysis result, it is found that five out of the eight factors that are predicted as significant have salient effects. Factors of season, time/hour, day of the week, or month which disasters happened do not show any significant effect. This paper provides common features of injured people. The provided analysis result will be helpful as a starting point for root cause analysis and reduction of industry disasters and also for development of a guideline of safety management.

고도화된 산업의 발달로 인하여 많은 업종들이 생겨나게 되었고, 그로 인해 크고 작은 사고들이 발생하게 되었다. 사고의 발생은 부상, 사망과 질병 등의 재해자들을 발생시키고, 사고로 인한 재해자의 수는 한 사업장에서도 여러 건씩 발생한다. 이러한 재해자의 공통된 특성 요소와 성향을 분석할 수 있다면, 1%의 재해자라도 더 줄일 수 있으리라 사료된다. 본 논문에서는 업종별 그룹을 통해 재해자들의 특성화 분석을 위하여 총 25,157개의 데이터를 바탕으로 데이터 Mining 기법중의 하나인 Classification and Regression Tree(CART)를 이용하여 분석을 하였다. 종속변수인 10개의 주요 업종을 중심으로 재해자들이 어떠한 성향을 나타내고 있는지 알아보고자 독립변수인 재해자 구분, 재해시간, 근속기간, 성별, 회사 규모와 연령 등 8개 항목을 채택하여 재해자 위험 그룹을 분석하고 그 결과를 제시한다.

의사 결정 나무 알고리즘은 관심이 되는 집단을 몇 개의 소집단으로 분류하거나 특성을 예측하기 위한 데이터 마이닝 분석 기법중 하나이다. 이 기법은 각 업종별 특성을 분석하여 업종별 차이점을 찾기 위해 사용되었다. 여기에서 사용되어진 의사결정 알고리즘으로는 C4.5알고리즘을 사용하였다. 트리는 이득율(Gain Ratio)에 의해서 Top-Down방식으로 구성하게 되었다. 본 연구에서 사용된 데이터는 2003년, 2004년에 발생 되어진 데이터로 총 25,159개의 데이터를 대상으로 정제과정을 거쳐 24,887개의 데이터를 사용하였고, 한 개의 종속 변수와 8개의 독립 변수로 이루어져 있다. 총 222개의 트리 노드가 만들어 졌고 최종 노드(Leaf Node)는 총 151개가 생성되었다. 생성된 트리 결과에 대한 정확성 측정을 위해 정확도(Accuracy), 오분류 확률(Misclassification Rate)을 계산하였다.

Port, one of nation's key infrastructures, is a point of road and sea transports meeting. As a key base of inter-modal transportation systems, the port is of ever increasing importance for realizing nation's vision of making Korea as an economic and logistics hub in the Northeast Asia. At present, Korean ports handle 99.7% of gross trade volumes in Korea, which requires considerable attention on its safety issues. However, due to the critical characteristics of the port and insufficient attention paid to it, the port industry meets more disasters compared to other industries. Therefore, this paper tries to analyze the disasters happened at the port to have better understanding on its reasons, further to use as learned lessons to prevent from potential disasters that may arise at the port.

Accident analyses are used to identify common factors contributing to occupational accidents and to give recommendations for accident prevention. In this study we developed a human error analysis system that can be used easily at the industries. This accident analysis system can be used to develop accident prevention programs to reduce human initiated accidents.

For the accident prevention, it is necessary to identify common factors and characteristics contributing to the industrial accidents. This study concerned with the accident characteristics by age of injured person in the manufacturing industries. To make the statistical comparisons for the accident characteristics by age group, we derived the distributions of occupational injuries in terms of accident time, accident type, activity at time of accident, injury type, injured part of body, agency of accident, and workday losses. The results show that the characteristics of the occupational injuries by age group are not significantly different in a31 characteristics investigated in this study.

기업의 성장과 더불어 일반적으로 산업재해로 인한 손실비용이 증가하는 추세이며, 이는 기업이나 국가적으로 그 만큼의 이익분에 대한 손실로 발생되어진다. 영국의 경우 재해로 인한 손실비율이 기업이익의 5∼10%를 차지하고 있는 것으로 최근 조사되고 있다. 따라서 기업의 경쟁력 향상을 위하여 재해로 인한 경제적 손실비용의 정확한 파악과 분석이 요구되어지고 있다. 따라서 본 연구에서는 재해손실 비용의 파악과 그 분석 기법의 체계적 비교 조사 하였다.

산업안전을 평가하는 지수개발은 안전 프로그램의 발전 방향에 크게 기여하기 때문에 매우 중요하다. 한국에서는 현재 사업장의 안전평가를 위해서 산업재해 평가지수로서 재해빈도를 나타내는 도수율과 재해 강도를 나타내는 강도율을 주로 사용하고 있으며 그외에 연천인율, 종합재해지수등도 사용되고 있다. 이러한 산업안전평가지수들은 근로자들이 느끼는 주관적 안전의 정도를 나타내지 못한다. 근로자들이 느끼는 안전의 정도를 도수율과 강도율의 함수로 나타낸 평가지수인 동의안전지수(동의안전지수=0.2*도수율10.8*강도율)가 최근 개발되었다. 본 논문은 동의 안전지수를 이용하여 업종별 분석을 실시하여 업종별 근로자가 느끼는 위험의 정도를 알아내고, 이를 근거로 업종별 효과적인 안전관리 방안을 제시하고자 한다.

최근 항만하역근로자의 인명사고가 지속적으로 발생함에 따라 사고관리에 대한 필요성이 증대되고 있다. 이 연구는 GRA법과 Entropy법을 이용하여 우리나라 항만에 대해 하역근로자의 재해 위험성을 평가하고 위험성이 높은 항만을 결정하기 위한 것이다. 이러한 목적을 달성하기 위해 먼저 우리나라 항만을 11개의 대상항만으로 구분하고, 브레인스토밍법으로 항만하역근로자 재해 위험성 평가를 위한 평가항목을 추출한다. 두번째는 GRA법을 이용하여 대상항만의 회색관계계수를 산정한다. 마지막으로 엔트로피법을 이용하여 산출한 평가항목의 중요도와 GRA법의 회색관계계수를 결합하여 회색관계등급을 산정하여 재해 위험성의 우선순위를 결정한다. 따라서 제안된 모델에서는 항만하역근로자수, 50세 이상 항운노조원수, 총근로시간, 하역장비수, 철재화물량, 총화물량, 사상자수, 사망자수 등 8개의 평가 항목을 추출되었다. 그 결과 부산항의 재해 위험성이 가장 높게 나타났으며 이에 따라 우선적으로 재해위험성을 경감하는 방안이 검토되어야 할 것이다.

This paper is a study on the development of a data analysis platform that constitutes a part of the development task of the constant monitoring system that can prepare against the earthquake disaster by using the regular measurement data of the old school buildings. The data analysis platform is composed of database management software that manages the metrology data acquired by using the instrument and data management software that analyzes the metrology data, analysis tools that can analyze the metrology data in various ways, A data analysis platform can be used to assess the safety of the school building and evaluate the seismic safety of the old school building to build a system for earthquake disaster.

The development of GIS technology has enabled the analysis of heavy rainfall vulnerability based on spatial analysis. In general, spatial analysis is performed based on property data and spatial data. Spatial data and attribute data differ in the generation units due to various reasons. The difference in these units can also cause problems in the results of the analysis. In particular, the Modifiable Areal Unit Problem (MAUP) that occurs according to the spatial unit setting is the most representative. The Modifiable Temporal Unit Problem (MTUP), which occurs according to the recent time unit setting, is also being raised. In this study, we analyzed the vulnerability of heavy rainfall in consideration of MAUP and MTUP. To analyze the effect of the MAUP, different administrative units were constructed and analyzed. In Seoul, Busan, and Ulsan, there was a scale effect in which disaster vulnerability was analyzed differently according to the analysis unit. In order to analyze the impact of MTUP, the range of study period was configured differently. The impact of the temporal boundary, in which overall disaster characteristics change and disaster vulnerability changes, has been identified. Analysis of regional disaster vulnerability considering MAUP and MTUP will be effective not only for the study of heavy rainfall disaster but also for setting the standard of disaster prevention policy.

According to this study, small-scale construction projects with a construction value of less than 300 million won are placed in the blind spot of safety management inspection. Therefore, it is necessary to improve the management and inspection system that reflects characteristics of small-scale construction sites.