• 지역사회간호학회지
• /
• 제18권4호
• /
• pp.643-650
• /
• 2007

Purpose: This study was to obtain information regarding to agricultural accidents in farm workers in the Kyungpook area. Methods: A questionnaire survey was carried out for 528 workers from the 1st to 31st of March, 2007. Frequency, percentage, mean and chi-square test with the SPSS program were used to analyze the data. Results: The causes of agricultural accidents include falling(29.0%), overseeing(18.9%), traffic accident(17.4%), putting between machinery(11.7%), crashing(5.3%), fire (0.6%) in the order of frequency. Injuries from agricultural accidents include fracture(44.7%) cerebral bleeding (10.4%), amputation(7.0%), airway obstruction (2.3%) burn(1.9%), drug addiction(1.9%) in the order of frequency. The largest proportion of the subjects of hospital treatment were in their 50s and belonged to the group of high-level economic state. Agricultural machinery collision was the most frequent cause among the subjects of hospital treatment. Conclusion: These results suggest that carelessness can be a potential risk factor for agricultural accidents in farm workers. These findings may give useful information for developing agricultural accident prevention programs for farm workers.

• 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.

• 방사성폐기물학회지
• /
• 제17권1호
• /
• pp.95-106
• /
• 2019

원전 해체를 준비함에 있어 정성적 또는 정량적 위험도 평가는 필수요소이다. 해체 공정간 발생하는 방사선학적 및 비방사선학적 위험요소는 해체 작업자 및 대중의 안전을 보장하기 위해 사전에 평가되어야 한다. 현재 해체 경험이 많은 미국의 기존 사업자들 및 NRC의 경우 위험의 중대성만 평가하는 결정론적 위험도 평가에 집중하고 있다. 하지만 최근 IAEA는 위험도 매트릭스를 활용한 위험도평가를 결정론적 위험도 평가의 대체안으로 제안하고 있다. 따라서 본 연구에서는 위험도평가에 앞서 해체 공정 별 해체 활동을 Risk Breakdown Structure에 맞추어 정리하였고, 미국 20여개 해체 원전에서 해체 공정별 위험도 평가 시행 중 선정한 해체 활동간 잠재적 사고를 해체 활동에 맞게 체계적으로 정리하였다. 그리고 복합 리스크 매트릭스를 개발 및 활용하여 해체 공정간 방사선학적 및 비방사선학적 위험요소의 위험도를 평가하여 정량적으로 수치화 하였다.

• 한국융합학회논문지
• /
• 제10권9호
• /
• pp.179-186
• /
• 2019

건설 현장의 잠재적 사고 파악은 건설업계의 주요 관심사이며 사고 위험을 줄이기 위한 사전 안전대책이 필요하다. 한국산업안전공단에 따르면 특히, 장비로 인한 안전사고의 사망 비율이 2016년 기준 19.8%로 매우 높은 부분을 차지하고 있다. 4차산업에서 사물인터넷(IoT)은 스마트한 새로운 제조 환경을 제공하고 있다. 그러나 건설 현장에서는 IoT가 광범위하게 적용되지 못하고 있는 실정이다. IoT는 건설사고 관리에 더 정확하고 유용한 정보를 전달하는 운영체계의 구축이 가능하다. 이에 본 연구는 건설 장비로 인한 안전사고를 예방하고 관리할 수 있는 IoT 기반 건설 장비 안전 사고 예방 시스템을 제안한다. 향후 본 시스템의 개선을 통하여 작업자의 안전뿐만 아니라 효율적인 장비와 인력 운용에도 기여할 것으로 판단된다.

• 국제학술발표논문집
• /
• The 10th International Conference on Construction Engineering and Project Management
• /
• pp.1284-1284
• /
• 2024

Leveraging large language models and safety accident report data has unique potential for analyzing construction accidents, including the classification of accident types, injured parts, and work processes, using unstructured free text accident scenarios. We previously proposed a novel approach that harnesses the power of fine-tuned Generative Pre-trained Transformer to classify 6 types of construction accidents (caught-in-between, cuts, falls, struck-by, trips, and other) with an accuracy of 82.33%. Furthermore, we proposed a novel methodology, saliency visualization, to discern which words are deemed important by black box models within a sentence associated with construction accidents. It helps understand how individual words in an input sentence affect the final output and seeks to make the model's prediction accuracy more understandable and interpretable for users. This involves deliberately altering the position of words within a sentence to reveal their specific roles in shaping the overall output. However, the validation of saliency visualization results remains insufficient and needs further analysis. In this context, this study aims to qualitatively validate the effectiveness of saliency visualization methods. In the exploration of saliency visualization, the elements with the highest importance scores were qualitatively validated against the construction accident risk factors (e.g., "the 4m pipe," "ear," "to extract staircase") emerging from Construction Safety Management's Integrated Information data scenarios provided by the Ministry of Land, Infrastructure, and Transport, Republic of Korea. Additionally, construction accident precursors (e.g., "grinding," "pipe," "slippery floor") identified from existing literature, which are early indicators or warning signs of potential accidents, were compared with the words with the highest importance scores of saliency visualization. We observed that the words from the saliency visualization are included in the pre-identified accident precursors and risk factors. This study highlights how employing saliency visualization enhances the interpretability of models based on large language processing, providing valuable insights into the underlying causes driving accident predictions.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.2941-2948
• /
• 2011

Rialway passengers and public, workers typically have high potential on death and injury accidents, because they are to be frequently adjacent to train or train operation. In order to effectively reduce the risks associated with the passengers, the public, and the workers, a systematic risk assessment should be performed to evaluate the hazards that contribute to the accidents. This paper describes the effect of risk assessment web base system and the extension need of the classification of "The regulation of railway accident report and information in Korea", application for national or railway safety operator, sharing railway safety information.

• 한국철도학회논문집
• /
• 제12권2호
• /
• pp.260-266
• /
• 2009

위험도분석은 철도사고해석에 주로 사용되는 이론이다. 위험도 분석의 목적은 전설공사전체 과정에서 주요사고부 사고요인과 잠재적인 원인 및 기여정도 등을 조사 분석하는 것이다. 본 논문은 건설공사 현장에서 발생하는 사고원인과 패턴을 분석하고 사고빈도와 심각도를 고려한 위험도 지수를 계산하여 상대적인 위험도 평가를 제공하고자 하는 것이다. 이를 기반으로 사고 위험도 지수의 일관성을 유도하고 위험도 평가를 위한 정량적인 기준을 제공하고자 하였다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2006년도 추계학술대회 논문집
• /
• pp.1046-1052
• /
• 2006

Railway works on or near the line, or trackside works, typically have high potential of accidents, as the works have to be frequently performed during the train operation. In order to reduce the risks associated with the railway trackside works effectively, a systematic risk assessment must be performed considering the hazards that contribute to the accidents. In this study, hazards are identified for railway trackside works by analysing data from Korea Railroad for accidents that have occurred between the year of 2000 and 2006. The hazard list produced in this study is expected to be effectively used for the risk assessment of the trackside works.

• 한국안전학회지
• /
• 제11권1호
• /
• pp.121-128
• /
• 1996

Estimating the cost of injuries and "accidents" to an organization is very important to figure out about how much well each organization has run his company and how much efficiently he has got the results using a certain amount of the expense for safety. Despite the potential usefulness to management of information as to the cost of a company's "accidents", it is not customary accounting practice to make these data available. Of the two general kinds of costs forced on a company by its occupational injuries and "accidents", the insurance cost and uninsured cost, -the former is by far the easier to find out. But actually, this uninsured cost should be figured out at each company. Authors have designed the generalized model to figure out the above problem costs to establish its efficient safety control. One construction company has been a pilot for this study. It is found that efficient safety control cost should be 1.2%~l.3% of total selling amount by analyzing actual data for three years.g actual data for three years.

• 한국안전학회지
• /
• 제26권4호
• /
• pp.41-46
• /
• 2011

The purpose of this paper is to analyze the causes of accidents related to the 3 phase 170 kV gas insulated switchgear of a power system collected from accident sites to secure data for the prevention of similar accidents and provide important points of view regarding diagnosis for the prevention of accidents involving gas insulated switchgears. The analysis results of the causes of accidents involving gas insulated switchgears showed deformation of the manipulation lever installed at the S-phase, disconnection of the insulation rod connection, melting of the upper conductor, a damaged tulip, damage to the lower spacer and the spacer at the breaker, etc. It is believed from this result that the potential for accidents has expanded due to accumulated energy as a result of repeated deterioration. The carbonization depth of a GIS was formed near the screw (T2, T3) used to secure the lower pole of the S-phase tulip. It is not known what has caused the screws to be extruded and melted. However, it is thought that an unbalanced electromagnetic force, micro-discharge, surface discharge, etc., have occurred at that point. In addition, even though 16 years have passed since its installation, there was no installation defect, act of arson, accidental fire, etc. General periodical inspection and diagnosis failed to find the factors causing the accidents. As a system contained in a closed metal container, it has a high risk factor. Therefore, it is necessary to design, install and operate a GIS in accordance with the standard operational procedure (SOP). In addition, it is necessary to apply conversion technology for periodical SF6 gas analysis and precision safety diagnosis. It is expected that tracking and managing these changes in characteristics by recording the results on the history card will provide a significant accident prevention effect.