• 한국안전학회지
• /
• 제37권6호
• /
• pp.96-101
• /
• 2022

The Occupational Safety and Health Act holds that industrial safety helmets can be used as protective equipment to prevent the risk of injury in fall accidents. To better understand the importance given to PPE for the head, we analyzed the relevant regulations and guidelines in developed countries and reviewed the guidelines on testing safety helmets. The PPE regulations in Korea were notably different from those in other countries. First, except in Korea and Japan, safety helmets were used for protection against falling objects, flying objects, impact, or electric shock. However, the regulations did not recognize safety helmets as a PPE against fall hazards. Second, the impact energy applied on the helmet was within the range 50-100 J, and the helmet could protect only the upper part of the head against hazards such as the impact of falling objects, flying objects, etc. Third, in Korean regulations, the term "fall" was used in relation to the parts where the safety helmet was specified as a fall hazard PPE, unlike in other countries. We propose that the term "fall" should be revised to "shock" in Korean regulations for the safety helmet.

• 센서학회지
• /
• 제31권2호
• /
• pp.96-101
• /
• 2022

As the elderly population gradually increases, the risk of fatal fall accidents among the elderly is increasing. One way to cope with a fall accident is to determine the fall direction before impact using a wearable inertial measurement unit (IMU). In this context, a previous study proposed a method of classifying fall directions using a support vector machine with sensor velocity, acceleration, and tilt angle as input parameters. However, in this method, the IMU signals are processed through several processes, including a Kalman filter and the integration of acceleration, which involves a large amount of computation and error factors. Therefore, this paper proposes a machine learning-based method that classifies the fall direction before impact using IMU raw signals rather than processed data. In this study, we investigated the effects of the following two factors on the classification performance: (1) the usage of processed/raw signals and (2) the selection of machine learning techniques. First, as a result of comparing the processed/raw signals, the difference in sensitivities between the two methods was within 5%, indicating an equivalent level of classification performance. Second, as a result of comparing six machine learning techniques, K-nearest neighbor and naive Bayes exhibited excellent performance with a sensitivity of 86.0% and 84.1%, respectively.

• 한국해양공학회지
• /
• 제35권1호
• /
• pp.91-97
• /
• 2021

Marine accidents caused by ships have brought about economic and social losses as well as human casualties. Most of these accidents are caused by small and medium-sized ships and are due to their poor conditions and insufficient equipment compared with larger vessels. Measures are quickly needed to improve the conditions. This paper discusses a video-integrated collision prediction and fall detection system to support the safe navigation of small- and medium-sized ships. The system predicts the collision of ships and detects falls by crew members using the CCTV, displays the analyzed integrated information using automatic identification system (AIS) messages, and provides alerts for the risks identified. The design consists of an object recognition algorithm, interface module, integrated display module, collision prediction and fall detection module, and an alarm management module. For the basic research, we implemented a deep learning algorithm to recognize the ship and crew from images, and an interface module to manage messages from AIS. To verify the implemented algorithm, we conducted tests using 120 images. Object recognition performance is calculated as mAP by comparing the pre-defined object with the object recognized through the algorithms. As results, the object recognition performance of the ship and the crew were approximately 50.44 mAP and 46.76 mAP each. The interface module showed that messages from the installed AIS were accurately converted according to the international standard. Therefore, we implemented an object recognition algorithm and interface module in the designed collision prediction and fall detection system and validated their usability with testing.

• 한국안전학회지
• /
• 제13권4호
• /
• pp.221-229
• /
• 1998

This study, with a view point to prevent accidents arising from steel structure, construction process, has taken an approach of reviewing related materials and construction safety guidelines, conducting questionnaire surveys and on field surveys. This study has also analyzed and classified accident cases and disclosed elements concerned with those accidents. A comparative analysis of the disclosed elements against the statutory provisions regarding industrial safety and it showed that strict observance of safety rules of the accident prevention measures in industrial safety standards will result in a decrease in accidents. It is concluded, however, that additional accident prevention measures, as suggested below, should be implemented for performing of more practical and positive accident prevention. 1) Thorough review and preparation at pre-working stage at sites : Such elements of fall preventing facilely as supporting ropes and steel fabrications for safety guard rails should be initially reflected on detailed drawings and shop drawings so that they can be installed in advance at fabricating plants. 2) Sets of steel frame stairs for work platform should be installed or secured with priority and temporary installation of such prefabricated platform as scaffolds should be installed in advance with those platform attached to the frame members on the ground whenever possible before they are lifted. 3) A decrease in the rate of accident by more than 10% on Tuesdays and Thursdays, has been shown from the accident analysis so schedule of construction process should consider possible weekday of high risk of accidents such as Tuesday and Thursday. 4) An array of systemized safety activities should be adopted, such as legal installation of safety facilities based on advance safety management plan, maintenance of safety for machinery and construction equipment, and strict compliance of safety rules by workers.

• 한국건설관리학회논문집
• /
• 제22권5호
• /
• pp.29-38
• /
• 2021

정부와 기업이 건설업의 산업재해를 줄이기 위해 지속적으로 노력하고 있지만, 재해는 크게 줄어들지 않고 있다. 본 연구는 건설 재해에 영향을 미치는 요인들 간의 연관성을 정량적으로 규명하고자 하였다. 산업안전공단에서 공개한 중대재해 사례 1,197건을 대상으로, 데이터마이닝 기법 중 하나인 연관성 분석을 이용하여 연구를 수행하였다. 산업안전공단에서 제공하는 데이터와 외부 변수를 포함하여 재해 발생 형태, 건설업종, 작업내용, 기인물, 체감온도, 사고 시간대, 추락높이의 변수로 아이템을 구성하여 분석하였으며, 떨어짐 재해와 그 외의 재해로 구분하여 연관규칙을 도출하였다. 떨어짐 재해의 경우 향상도가 1.38 이상인 64개의 연관규칙을 도출하였으며, 떨어짐을 제외한 재해의 경우 향상도가 1.54 이상인 59개의 연관규칙을 도출하였다. 도출된 연관규칙을 재해요인 간의 연관성에 초점을 두고 해석한 후, 고찰에서 연구의 한계와 건설재해 요인 간의 관련성을 파악할 때 연관성 분석 기법을 적용함에 있어 유의사항을 제시하였다. 본 연구는 건설 재해에 영향을 미치는 요인들 간의 연관성을 정량적인 수치로 제시하여 추후 근로자들과 현장관리자가 건설현장에서 적절한 안전대책을 마련하는 기초자료를 제공하였다는 점에서 의미를 찾을 수 있다.

• 한국건설관리학회논문집
• /
• 제22권5호
• /
• pp.73-85
• /
• 2021

본 연구는 딥러닝 기반의 텍스트 데이터 분류 모델의 성능 고찰을 통해 한국어 건설 재해사례의 효율적 관리방향을 제안한다. 이를 위해 비정형 텍스트 문서인 건설 재해 보고서를 활용해 건설 사고의 대표적 유형인 추락, 감전, 낙하, 붕괴, 협착의 5개 범주로 분류하는 딥러닝 모델을 구현하였다. 초기 모델 테스트 결과, 추락 재해의 분류 정확도가 상대적으로 높게 도출되며 타 유형을 추락 재해로 분류하는 경우가 많이 발생한다는 특징이 나타났다. 원인 분석 결과, 1) 구체적인 사고 유발 행동, 2) 유사한 문장 구조, 3) 여러 유형에 해당되는 복합사고가 위의 특징에 영향을 미치는 것으로 분석되었으며, 이 중 추가 실험을 통해 검증이 가능한 복합사고에 대한 두 가지 정확도 개선 실험을 진행하였다: 1) 재분류, 2) 제외. 실험 결과, 복합사고 제외 시 분류 성능이 185.7% 향상되었으며, 이를 통해 여러 사고 유형에 대한 내용을 동시에 포함하는 복합사고의 다중공선성(multicollinearity)이 해소되었음을 알 수 있다. 결론적으로 본 연구에서는 향후 사고에 대한 상황을 상세히 서술하는 체계를 마련함과 동시에 복합사고를 독립적으로 관리할 필요성을 시사한다.

• 한국전문물리치료학회지
• /
• 제30권1호
• /
• pp.1-7
• /
• 2023

Background: Like many other countries, falls and related injuries in older adults are great concerns in South Korea. In particular, falls are common in medical institutions, often causing the increase of the length of hospitalization. Objects: The purpose of this review was to help understand and address falls in hospitalized individuals in South Korea. Methods: The review was conducted on literature published in Korean from 2010 to 2022, searched in the Korea Citation Index and PubMed. Keywords used for the search were as follows: falls, fall risk, fall risk assessment, hospital, inpatient, intervention, Korea, and prevention. Results: A total of 54 articles were found and reviewed. The most common place of fall accidents was the inpatient room, where there were many cases of falls while walking. Loss of balance was the most common cause of falls, and many falls occurred in patients admitted to the internal medicine. Furthermore, a risk of falling increased with the type of medications taken. In terms of tools to assess patients' fall risk, the Morse Fall Scale (MFS) was commonly used. Patient-specific fall prevention activities were common to address falls, and they decreased the frequency of falls and the fear of falling. Factors influencing the effectiveness of the fall prevention activities included attitudes toward falls, education, environmental factors, patient safety culture, and self-efficacy in preventing falls. Conclusion: Our results should help understand and address falls and injuries in medical institutions.

• 한국정밀공학회지
• /
• 제28권11호
• /
• pp.1330-1338
• /
• 2011

Social activities of the elderly have been increasing as our society progresses toward an aging society. As their activities increase, so does the occurrence of falls that could lead to fractures. Falls are serious health hazards to the elderly. Therefore, development of a device that can detect fall accidents and prevent fracture is essential. In this study, we developed a portable fall detection system for the fracture prevention system of the elderly. The device is intended to detect a fall and activate a second device such as an air bag deployment system that can prevent fracture. The fall detection device contains a 3-axis acceleration sensor and two 2-axis tilt sensors. We measured acceleration and tilt angle of body during fall and activities of daily(ADL) living using the fall detection device that is attached on the subjects'. Moving mattress which is actuated by a pneumatic system was used in fall experiments and it could provide forced falls. Sensor data during fall and ADL were sent to computer and filtered with low-pass filter. The developed fall detection device was successful in detecting a fall about 0.1 second before a severe impact to occur and detecting the direction of the fall to provide enough time and information for the fracture preventive device to be activated. The fall detection device was also able to differentiate fall from ADL such as walking, sitting down, standing up, lying down, and running.

• 한국식품영양학회지
• /
• 제30권6호
• /
• pp.1299-1309
• /
• 2017

The aim of this study was to investigate status of safety accidents of school foodservice cooks in Daegu and to analyze the factors affecting the occurrence of the accidents in order to seek effective ways for preventing safety accidents in school foodservice. The survey showed that the most frequent safety accidents were 'bruises', followed by 'burns', 'contact with harmful substances such as disinfectants', 'fall-off ' and 'sprains'. The mental fatigue perception of the respondents was generally lower than the physical fatigue perception. The means of the perception levels of work intensity, cooking environment of the foodservice place, and safety-related behaviors, and consciousness were 3.15, 2.99, and 4.06 out of 5 points, respectively. In addition, the annual average of the number of participating in the accident prevention training per person was 17.34 times, that is, the respondents received the training at least once a month on average. A multiple regression analysis was conducted to investigate the variables affecting the occurrence of safety accidents that happened to foodservice cooks. It revealed that the work intensity perception and the cooking environment perception influenced the frequency of safety accidents.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2014년도 춘계 학술논문 발표대회
• /
• pp.38-39
• /
• 2014

In order to reduce fatal accidents, a systematic safety management should be performed at a construction site. A lot of researches on direct causes of fatal accidents and indirect causes which affect the direct causes have been conducted for effective safety management. In the previous studies, these causes are considered separately because of the difficulty of recognition of indirect causes. It is also hard to measure the negative impact of these causes and notice their occurrence the perception of its problem. However, a study on identification of complicated relationship between these two types of causes is necessary since an accident occurs due to the chain reaction that indirect causes trigger the direct causes which lead to the fatal accidents. Therefore, this study proposes a safety management plan that considers indirect and direct causes of fatal accidents cases in the Korean construction industry. Then this paper suggests a plan of safety management by identifying major causes of the accidents.