• IE interfaces
• /
• v.15 no.4
• /
• pp.426-431
• /
• 2002

In many cases, the result of a road traffic accident can be described with more than one response variables. Nonetheless, most of the existing road accident data analysis deal with only one response variable and try to explain why it occurs. In this paper, we train association rules for a set of more than two response variables conditional on personal, environmental and vehicular/behavioral aspects of accident. Association rules are derived at 8% support and 70% confidence from the 1996 data of three police stations in Korea. We expect that these rules can contribute to effective safety practice in Korea.

• Journal of the Korea Safety Management & Science
• /
• v.14 no.3
• /
• pp.21-31
• /
• 2012

This study was conducted in order to assist with infusing safety consciousness and resolving insensitivity towards safety for industrial accident in workers, managers and executives of chemical companies. Among many industrial accident prevention methods, Korea has been mostly taking an engineering approach of preventing industrial accidents by replacing old machines with risks of an accident and through new facilities and equipments. Through an attitude survey of workers in large scale chemical companies, this study wished to examine the fact that the biggest reason why the accident rate for the past 10 years has not decreased is because safety consciousness has not been established yet.

• Journal of Preventive Medicine and Public Health
• /
• v.12 no.1
• /
• pp.31-37
• /
• 1979

By evaluating the health status of 152 male workers engaged in a metal-product factory by Cornell Medical Index in conjunction with their experience of industrial accident, I attempted to find out whether any health condition may effect on the occurence of industrial accident. Differences in frequency of complaints in each section of CMI between control workers and accident workers were statistically tested by T-test. On the other hand, influence of neuropsychiatric factors (section M-R) on the occurence of accidents was analyzed by $X^2-test$ with Fukamachi's classification. The followings were the results obtained in this study. 1. The average number (26.42) of physical complaints in accident group is significantly more than in control group (18.70). 2. The average number (17.70) of mental complaints in accident group is very significantly more than in control group (11.70). 3. Differences in frequencies of complaints by sections between accident group and control group was all significant except C (cardiovascular system), H (genitourinary system), I (fatigue) & J (frequency of disease). 4. frequency rate of neurotic workers who were identified by Fukamachi's classification was significantly higher in accident group (72%) than in control group (51%).

• Journal of the Ergonomics Society of Korea
• /
• v.36 no.3
• /
• pp.221-230
• /
• 2017

Objective: The purpose of this study is to draw the accident prevention model using the signal detection theory, and to implement accident prevention program, based on a health promotion and support activities in a shipbuilding company. Background: Workers' health management is perceived important from the human resource management perspective, as well as from the personal perspective. Method: This study developed an accident prevention model by analyzing the correlation between 704 workers' health examination variables, and reviewed the verification of the model through a follow-up survey on the control variables and status of hazards targeting 650 workers for four years from 2007 to 2010. Also, a health promotion program was implemented targeting a production division to improve alcohol habits, smoking, musculoskeletal pain complaints and hearing control indices, which are the control variables of the model. Results: As a result of four years' implementation, the following effects were obtained: the days away from work fell 87.5%, and accident rate dropped 71.5% in 2010, respectively, compared to 2006, before the activity was implemented. Conclusion: This study shows that the accident prevention activities based on workers' health promotion activities are effective to prevent industrial accidents and injuries. Application: The research findings will serve as a practical guideline for establishing preventive measures in the shipbuilding company.

• Journal of the Society of Disaster Information
• /
• v.5 no.2
• /
• pp.140-152
• /
• 2009

Recently the occurrence ratio of mechanical accidents in industrial disaster of korea is increased, but very little accident information has been given regarding the prevention of mechanical accidents. In this study, mechanical accidents by the analysis of industrial accident case was examined. And it was proposed the risk assessment method and building database for investigation of risk factors in mechanical accident. As a result, from mechanical accidents database, it was found that the occurrence ratio of mechanical accident by constriction and falling etc. is very high and death ratio by mechanical accident is larger than that of usual accident. And we applied the quantitative risk assessment method proposed by this study in the mechanical accident analysis of a domestic manufacturer. From the results, the risk factors due to constriction, curling, falling and scattering are principal causes of mechanical accidents. These result is similar to that of the analysis of mechanical accidents for recent 12 years in korea.

• Journal of the Korea Safety Management & Science
• /
• v.16 no.2
• /
• pp.63-70
• /
• 2014

As preventive measures have received tremendous attention to prevent any possible accident in advance, many work places have introduced safety and health management systems. However despite of this government's effort, the industrial accident rate of small-scale businesses with less than 50 employees does not decline, which is mainly because the projects are not differentiated according to the risk level of individual business. To evaluate the risk level of small-scale businesses with less than 50 employees and then establish effective safety and health management systems according to the risk level, this study has conducted the following processes. The small-scale businesses with less than 50 employees were evaluated through accident type, and potential accident risk factor was evaluated through location, business type, and business size. The results of this analysis are expected to make contribution to improving the effectiveness of the safety and health management supports to small-scale businesses with less than 50 employees.

• Journal of Korean Institute of Industrial Engineers
• /
• v.26 no.4
• /
• pp.354-362
• /
• 2000

Increasing amount of road tragic in 90's has drawn much attention in Korea due to its influence on safety problems. Various types of data analyses are done in order to analyze the relationship between the severity of road traffic accident and driving conditions based on traffic accident records. Accurate results of such accident data analysis can provide crucial information for road accident prevention policy. In this paper, we apply several data fusion, ensemble and clustering algorithms in an effort to increase the accuracy of individual classifiers for the accident severity. An empirical study results indicated that clustering works best for road traffic accident classification in Korea.

• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.56-63
• /
• 2021

The narrative texts of industrial accident reports help to identify accident risk factors. They relate the accident triggers to the sequence of events and the outcomes of an accident. Particularly, a set of related keywords in the context of the narrative can represent how the accident proceeded. Previous studies on text analytics for structuring accident reports have been limited to extracting individual keywords without context. We proposed a context-based analysis using a Natural Language Processing (NLP) algorithm to remedy this shortcoming. This study aims to apply Word2Vec of the NLP algorithm to extract adjacent keywords, known as word embedding, conducted by the neural network algorithm based on supervised learning. During processing, Word2Vec is conducted by adjacent keywords in narrative texts as inputs to achieve its supervised learning; keyword weights emerge as the vectors representing the degree of neighboring among keywords. Similar keyword weights mean that the keywords are closely arranged within sentences in the narrative text. Consequently, a set of keywords that have similar weights presents similar accidents. We extracted ten accident processes containing related keywords and used them to understand the risk factors determining how an accident proceeds. This information helps identify how a checklist for an accident report should be structured.

• Journal of the Korean Institute of Gas
• /
• v.15 no.6
• /
• pp.44-50
• /
• 2011

This study is to investigate the role of the private institution which has the essential resources to solve an urgent problem for the decreasing and prevention of the industrial accident and to suggest the reinforcing model of reliability, expertise, competency of private institution. And the result of this study will be judged to present a milestone to establish a role essentially for preventing industrial accident among government agencies, public institutions and private institutions. It will also help the vitalization of an industrial safety and health market and can be utilized for the revision of Industrial Safety and Health Law and a state affairs plan.

• Journal of the Ergonomics Society of Korea
• /
• v.35 no.5
• /
• pp.465-472
• /
• 2016

Objective:This study is on the characteristics of motorcycle accidents occurring in the mail delivery process by skill level. Background: The tendency of delivery postmen's driving in a hurry may become the cause of accidents since there is a constraint that delivery should be completed within a limited time. Method: This study analyzed the traffic accident data of 259 delivery postmen, who had been approved as occupation-related industrial accident victims from 2009 to 2012, by their work experience in view of season, day of the week of an accident occurrence, accident occurrence time, accident cause, collision type, and driving situation. Results: Accident characteristics of delivery postmen show that the ratio of accidents occurring to those who had less than 10 years of work experience was high. There were many motorcycle collisions in winter and summer by season and an unexpected object, along with road condition, took up 70.7% of the accident sources. There were no differences in accident occurrence time, the day of the week, season, accident source, and collision type between the group of delivery postmen with less than 10 years of work experience and those with 10 years or more of work experience. However, there was a difference in distribution of driving condition. Conclusion and Applications: The results of this study can be used to present the policies or guidelines for the accident prevention of delivery postmen since the results show the characteristics of the injured and accident occurrence characteristics in relation with the delivery postmen's motorcycle collisions.