• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 한국항해항만학회 2020년도 추계학술대회
• /
• pp.105-107
• /
• 2020

수상레저활동시 구명조끼 등 안전장비 착용 의무화 배경 및 관련법률 제정 경위를 살펴보고, 현재 수상레저활동 중 안전사고 현황 및 안전장비 미착용 단속현황 분석을 통한 구명조끼 착용률을 높이기 위한 방법에 대해 고찰하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 한국컴퓨터정보학회 2024년도 제69차 동계학술대회논문집 32권1호
• /
• pp.291-292
• /
• 2024

국내의 산재 사고 사망 비율 중 대부분은 건설업이 차지하고 있으며 사망 원인 중 42.9%는 추락사가 차지하고 있다. 따라서 국내 사고 사망을 예방하기 위해서는 노동자의 생명을 지켜주는 안전 장비의 착용 여부가 중요하다. 본 논문에서는 객체 탐지에 사용되는 YOLO v4와 YOLO v4-TINY 알고리즘과 영상 처리에 사용되는 OpenCV를 이용하여 실시간 영상에서 안전모 미착용 인원을 감지하고 관리자에게 알려주는 시스템을 개발하였다. 이 시스템을 활용하여 건설 현장에서 현장 카메라로 안전모 미착용 인원을 실시간으로 검출하여 경고하므로써 작업자의 안전에 기여할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.854-855
• /
• 2023

안전벨트 미착용 혹은 통학 차량 미하차로 인한 사고를 방지하기 위해 좌석에 압력 센서와 안전벨트에 센서를 부착하여 착석하지 않은 상태, 안전 벨트 미착용, 안전 벨트 착용으로 3단계로 나누어 탑승자의 상태 정보를 운전석에 위치한 디스플레이에 정보를 표시하여 안전 사고가 발생할 가능성을 줄이고자 한다.

• Journal of the Korea Convergence Society
• /
• 제10권7호
• /
• pp.175-182
• /
• 2019

We classify topics on fall incidents occurring in construction sites using topic modeling among machine learning techniques and analyze the causes of the accidents according to each topic. In order to apply topic modeling based on latent dirichlet allocation, text data was preprocessed and evaluated with Perplexity score to improve the reliability of the model. The most common falling accidents happened to the daily workers belonging to small construction site. Most of the causes were not operated properly due to lack of safety equipment, inadequacy of arrangement and wearing, and low performance of safety equipment. In order to prevent and reduce the falling accidents, it is important to educate the daily workers of small construction site, arrange the workplace, and check the wearing of personal safety equipment and device.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.882-883
• /
• 2023

최근 문제가 제조 현장에서 안전 조치 의무 미준수로 인한 산업재해가 이슈가 되고 있다. 산업 재해는 대부분의 경우 관리 부실이 가장 큰 요인이다. 따라서 관리적 부분에서 머신 비전과 행동인식, 유사도 검색 알고리즘을 도입하여 제조현장에서 발생하는 불상사를 예방하고자 한다. 가이드라인 접근, 위험한 행동, 안전 장비 착용 수칙을 미 준수할 경우 사전에 입력된 가이드라인에 따라 관리자와 노동자에게 알림 및 경고하는 시스템을 제안하는 것을 요지로 한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제23권6호
• /
• pp.163-170
• /
• 2023

With the introduction of the law regarding severe penalties for major accidents, employers, management executives, and corporations have significantly increased the number of safety managers and invested extensively in acquiring ISO certifications to prevent accidents in industrial sites. Moreover, the implementation of the Smart Safety Management System (SSMS) has facilitated the management of personnel and safety equipment. While IoT-based management systems have been applied to safety gear such as helmets, safety harnesses, and protective clothing, the responsibility for safety shoes still primarily lies with on-site managers and individuals, leaving a vulnerability to accidents. In this study, we aim to implement a Raspberry Pi-based sensor device to proactively detect workers' safety shoe usage upon entering the site. The goal is to confirm the usage of safety shoes and prevent accidents that may occur due to non-compliance with safety shoes regulations.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.163-165
• /
• 2018

Most construction disasters are analyzed to be human factors such as not complying with the safety regulations of construction sites, not using clothing and protective equipment, safety insensitivity, and the health of workers. In order to prevent such a construction disaster, the project site management needs to check the health of workers, but it is difficult to check the condition of workers every hour. Therefore, this paper proposed the design of digital safety-helmet that can automatically identify health conditions by checking workers $SpO_2$ and pulse rates, away from simple protective features.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• 제41권3호
• /
• pp.305-316
• /
• 2021

Construction accidents occur due to a number of reasons-worker carelessness, non-adoption of safety equipment, and failure to comply with safety rules are some examples. Because much construction work is done outdoors, weather conditions can also be a factor in accidents. Past construction accident data are useful for accident prevention, but since construction accident data are often in a text format consisting of natural language, extracting construction hazards from construction accident data can take a lot of time and that entails extra cost. Therefore, in this study, we extracted construction hazards from 2,026 domestic construction accident reports using text mining and performed a seasonal analysis of construction hazards through frequency analysis and centrality analysis. Of the 254 construction hazards defined by Korea's Ministry of Land, Infrastructure, and Transport, we extracted 51 risk factors from the construction accident data. The results showed that a significant hazard was "Formwork" in spring and autumn, "Scaffold" in summer, and "Crane" in winter. The proposed method would enable construction safety managers to prepare better safety measures against outdoor construction accidents according to weather, season, and climate.

• Journal of the Korean Society of Marine Environment & Safety
• /
• 제23권6호
• /
• pp.603-612
• /
• 2017

Accidents associated with hazardous materials, including oil and HNS, in maritime transportation show increasing trend. Therefore, preventive countermeasures for such accidents should be provided. The purpose of this study is to analyze level of risk on human loss and potential damage to environment, using data on domestic marine accidents carrying hazardous materials (2002~2014), and identify high-risk accident types for urgent risk management which needs findings of accident causes and proper mitigation measures. High-risks on human loss are explosion and suffocation, occurred in process of ship maintenance and tank cleaning. On the other hand, high-risk on environmental damage is spill caused by ship accidents (collision, grounding and etc.). Especially, spill occurs during loading operation of oil and HNS onboard a ship. Strict operation supervision/management and safety education/training on a regular basis could prevent accidents, because human factors such as not wearing safety gear and careless cargo handling cause most of the marine accidents.

• Journal of the Korea Institute of Building Construction
• /
• 제20권3호
• /
• pp.269-278
• /
• 2020

In this study, we analyzed the safety accidents that occurred in the apartment construction site and the correlations between the victims according to the type of work accidents through multiple correspondence analysis. There is a lack of disaster-related studies on apartment construction sites, the third most frequent building type in Korea, and most of them have used survey techniques. Therefore, the exploratory data analysis was conducted in industrial accident cause data, and derived the correlation analysis between each disaster victim through multiple correspondence analysis. The results of the study are summarized in two as follows. First, as the number of heights increased due to the high rise and complexity of apartments, the fall rate and mortality rate were high. In addition, deaths are mostly caused by very few experienced workers or those with more than 10 years of experience, resulting from safety training, lack of experience, and insensitivity to safety. Second, multi-correspondence analysis showed that most safety accidents can be prevented by wearing safety equipment, and following proper work process and its safety action. The key factors derived from this study can be used for safety education, supervision, and management in apartment construction sites.