• 국제학술발표논문집
• /
• The 6th International Conference on Construction Engineering and Project Management
• /
• pp.313-316
• /
• 2015

Construction is one of the most dangerous job sectors, which reports tens of thousands of time-loss injuries and deaths every year. These disasters incur delays and additional costs to the projects. The safety management needs to be on the top primary tasks throughout the construction to avoid fatal accidents and to foster safe working environments. One of the safety regulations that are frequently violated is the wearing of personal protection equipment (PPE). In order to facilitate monitoring of the compliance of the PPE wearing regulations, this paper proposes a vision based method that automatically identifies whether workers wear hard hats and safety vests. The method involves three modules - human body detection, identification of safety vest wearing, and hard hat detection. First, human bodies are detected in the video frames captured by real-time on-site construction cameras. The detected human bodies are classified into with/without wearing safety vests based on the color features of their upper parts. Finally, hard hats are detected on the nearby regions of the detected human bodies and the locations of the detected hard hats and human bodies are correlated to reveal their corresponding matches. In this way, the proposed method provides any appearance of the workers without wearing hard hats or safety vests. The method has been tested on onsite videos and the results signify its potential to facilitate site safety monitoring.

• PNF and Movement
• /
• 제22권1호
• /
• pp.43-54
• /
• 2024

Purpose: Falls among persons older than 65 years are a significant concern due to their frequency and severity. This study aimed to develop a vest-type embedded artificial intelligence (AI) system capable of detecting and predicting falls in various scenarios. Methods: In this study, we established and developed a vest-type embedded AI system to judge and predict falls in various directions and situations. To train the AI, we collected data using acceleration and gyroscope values from a six-axis sensor attached to the seventh cervical and the second sacral vertebrae of the user, considering accurate motion analysis of the human body. The model was constructed using a neural network-based AI prediction algorithm to anticipate the direction of falls using the collected pedestrian data. Results: We focused on developing a lightweight and efficient fall prediction model for integration into an embedded AI algorithm system, ensuring real-time network optimization. Our results showed that the accuracy of fall occurrence and direction prediction using the trained fall prediction model was 89.0% and 78.8%, respectively. Furthermore, the fall occurrence and direction prediction accuracy of the model quantized for embedded porting was 87.0 % and 75.5 %, respectively. Conclusion: The developed fall detection and prediction system, designed as a vest-type with an embedded AI algorithm, offers the potential to provide real-time feedback to pedestrians in clinical settings and proactively prepare for accidents.

• 한국의료질향상학회지
• /
• 제30권1호
• /
• pp.88-104
• /
• 2024

Purpose: This study explored the suitability of interventions for medication interruption and intervention preferences. Methods: Two rounds of Delphi surveys were conducted with 18 expert panels comprising staff (or charge) nurses, nursing managers, and Quality Improvement (QI) team nurses working in a tertiary general hospital. For 47 situations involving the location of interruption, medication step, and source of interruption, the suitability of three interventions (no-interruption zone, medication safety vest, and education) was evaluated using a 5-point scale. Results: A total of 51 interventions for each situation were found appropriate by satisfying the degree of convergence and consensus. Patients or caregivers, peer nurses, doctors, telephones, and call bells were sources of interruption and were identified as appropriate for the application of interventions. 'Responding to requests and inquiries' by patients or caregivers showed high overall suitability. The nurses' preferred color for the intervention design (no-interruption zone, medication safety vest) is blue text on a yellow background. The priority groups for education related to medication interruptions were patients or caregivers, nurses, and non-nursing staff, in that order. Conclusion: Effective implementation of tailored intervention strategies that consider the specific characteristics of medication interruptions is crucial for mitigating interruptions and enhancing patient safety. Comprehensive educational programs aimed at reducing medication interruptions by improving awareness are necessary. Moreover, future research should evaluate these strategies in clinical settings to ensure their effectiveness in enhancing patient safety.

• 한국산학기술학회논문지
• /
• 제22권1호
• /
• pp.372-378
• /
• 2021

방탄조끼는 전투원의 안전과 생명에 직결되는 군수품으로서, 방탄성능에 대한 요구조건의 충족여부가 무엇보다 중요하다. 우리 군에서는 방탄조끼의 요구 성능을 미 법무성 사업연구소(National Institute of Justice, NIJ)에서 발간한 NIJ STD-0101.06에서 규정하는 Level IIIA 수준으로 요구하고 있으며, 매 로트마다 수락시험을 진행하고 있다. 방탄성능을 평가하는 요소로 사격 시 관통여부 뿐만 아니라, 미 관통 시에도 후면 지지재료의 후면변형 기준인 44 mm 이하에 대한 충족여부도 고려하여 요구 성능에 대한 일치/불일치를 평가하고 있다. 후면변형은 지지재료의 물리적 성질과 탄속에 따른 충격량의 변화 등과 같이 다양한 시험요인이 시험 결과에 영향을 미치게 되는데, 본 연구에서는 이러한 외부인자의 영향성을 제거하기 위한 데이터 처리 시 분산분석을 도입하여 동일한 조건을 갖는 데이터를 추출 하였고, 이를 통해 방탄성능에 대한 분석을 수행하였다. 분석결과, 후면변형과 탄속, 환경처리 유/무 그리고 방호면적과의 상관관계를 확인하였을 뿐만 아니라, 로트별 후면변형 구간 추정을 통해서 양산 공정분석을 수행하였다. 이를 통해서 방탄성능평가에 대한 새로운 방법론을 제시하고, 향후 품질보증 관련 활동에 적용하기 위한 새로운 패러다임을 제시하고자 하였다.

• 전기전자학회논문지
• /
• 제16권1호
• /
• pp.62-68
• /
• 2012

본 논문에서는 해양인명구조 시스템에서 송신부인 구명조끼의 무선 송신기로부터 송신된 조난 신호를 효과적으로 수신하기위한 426MHz 대역 패널 형태의 평판형 마이크로스트립 안테나를 설계 및 제작하였다. 제작이 용이하고, 가벼우며, 적은 제작비용이 장점인 마이크로스트립(Microstrip) 안테나 구조를 이용하였으며, 협대역, 저이득, 큰 사이즈 특성을 극복하기 위하여 IDMA(Identical Dual Patch Microstrip Antenna with Air-Gap) 구조를 응용하여 설계하였다. 안테나는 유전율 4.3, 두께 1.6mm를 갖는 FR4를 사용하여 제작하였으며, 측정된 안테나의 대역폭은 $S_{11}=-10dB$ 이하에서 28.7MHz(약 6.6%), 이득은 426MHz에서 3.04dBi로 우수한 특성을 얻었다. 또한, 상용 송수신모듈을 사용한 거리측정 실험을 통하여 5km 이상의 송수신거리의 안정적인 통신성능을 확인하였다. 본 논문에서 제안한 안테나는 향후 UHF 대역 통신시스템의 기지국분야에 다양하게 응용될 수 있을 것이다.

• 감성과학
• /
• 제23권4호
• /
• pp.105-116
• /
• 2020

본 연구의 목적은 형광직물과 재귀반사 소재만으로 제작, 보급되고 있는 현 안전의복에, LED 부착으로 시인성을 높여 야간이나 기상악화 시 안전사고로부터 작업자나 보행자를 보호하고, 기울기 센서와 소리신호를 탑재하여 의식불명자의 구명에 도움을 주는데 있다. 이를 위하여 공학적 하이테크를 적용하여 설계·제작한 산업용 서스펜더형 안전벨트 및 기울기 센서와 소리신호가 탑재된 안전조끼형 벨트를 개발하였다. 그 효과로 첫째, 서스펜더형 안전벨트는 필름에 접착된 자동 점멸 LED에 의해 빛을 방출하도록 설계하여 벨트 착용자의 신체는 LED와 재귀반사를 통해 멀리서 인식되어 사고예방에 도움이 된다. 또한 야간에 실시하는 도로변이나 고지대에서의 작업, 구조대원 활동, 스포츠 활동 시사고를 예방하거나, 비상상황이 발생할 경우 LED 발광을 변화시키는 신호로 사고 지점을 빨리 발견할 수 있어 인명구조에 도움이 된다. 둘째, 착용자가 조난사고 등으로 인하여 의식불명으로 쓰러질 경우, 조난신호를 발생하는 첨단 디바이스를 개발하여 감지 및 신호 장치를 탑재한 결과 제어부의 기울기 센서가 인체의 각도를 자동 감지하였다. 동시에 조끼형의 벨트 형태로 제작함으로써 탈착이 용이하도록 하여 활용도를 높였다. 사고로 착용자가 쓰러지면 이 벨트의 기울기 센서가 각도를 감지하고 제어기가 고주파 음과 LED 점멸신호를 동시에 발생시킨다. 기존의 안전 조끼의 경우 주변 조명이 없을 때는 조끼를 착용한 사람을 감지하는 것이 거의 불가능 하였지만, 본 연구에서는 안전벨트의 음향과 빛 신호로 주변 조명이 없을 때에도 100 m 이내에서 착용자를 발견할 수 있었다. 그러므로 본 연구에서 LED 부착과 기울기 센서, 소리신호 소자를 부착한 스마트 안전의류의 개발은 사고발생 감소와 구명에 이바지할 수 있을 것이다.

• 한국의류학회지
• /
• 제46권5호
• /
• pp.760-771
• /
• 2022

This study sought to develop clothing for a companion animal that can provide stable ECG measurements. A pattern for the smart clothing of a companion dog was manufactured using the replica method to select a location and method that best suited the stable measurement of ECG and improved the clothing's fitness. The smart clothing was developed as the following three types: strap type, top type, and combined top and vest type with a detachable wireless ECG monitor. The detection abilities of these were observed using the PQRST rate taken after ECG measurements while the three companion dogs were tested while resting and moving. The results revealed that apart from using an electrode, applying a gel pad is the most effective way to achieve stable ECG measurements, and the central chest region is more reliable than the left armpit for providing steady readings. The combined top and vest type showed the highest average ECG PQRST detection number, meaning that the ECG signal measurement was steady. These results may contribute to the measurement of ECG in smartwear for U-Healthcare to measure other biometric data of a companion dog.

• Human Ecology Research
• /
• 제56권4호
• /
• pp.347-360
• /
• 2018

We surveyed 223 road workers between 2017 July-August about wearing and satisfaction in order to find basic data to develop safety clothing that enhances visibility of motion and comfort while meeting international standards. It was found that most of the current warning clothing owned by road cleaners and about 2/3 of policemen clothes were provided by public institutions. The purpose of wearing, color, properties, satisfaction and protectiveness differed significantly by occupation. Second, the most popular response for the type and quantity of warning clothing was 2 sets of spring/autumn, summer, and winter type for road cleaners, whereas policemen chose 2 sets of all types plus a safety vest. Therefore, a top-level (3rd class) warning clothing study is required. Third, satisfaction ranked Moderate>Good>Poor; in addition, the main reason for satisfaction was that 'retroreflective tape increases safety at night (54.4%)' for road cleaners and 'the fluorescent color stands out (43.7%)' for policemen. Thus, it was accepted that visibility contributed to safety. Fourth, body-protectiveness was evaluated higher compared to wearing satisfaction, and it was recognized more by road cleaners than policemen. Overall satisfaction was higher for road cleaners versus policemen both in Seoul than Incheon. Fifth, the main dissatisfaction in both groups was 'low sweat absorbency' showing improving the air permeability, moisture regain and permeability was the highest priority. Finally, those working 8 hours a day tended to evaluate more positively the 6 properties of the material.

• 스마트미디어저널
• /
• 제9권3호
• /
• pp.25-30
• /
• 2020

본 논문에서는 산업 시설에서 작업자의 안전을 실시간으로 감시하는 딥러닝 기반 영상 분석 시스템을 구현하는 데 목적을 둔다. 작업자의 복장을 안전모, 안전조끼, 안전벨트 착용 여부에 따라 총 여섯 가지의 클래스로 나누고, 총 5,307개의 영상을 학습데이터로 이용하였다. 실험은 속도와 정확도가 준수한 YOLO v4를 이용하였으며, 총 645장의 영상에 대해 학습 반복 수에 따른 가중치를 적용했을 때의 mAP를 비교함으로써 수행되었다. 학습 반복 수 6,000에서의 mAP가 60.13%로 제일 높았으며, 테스트셋이 가장 많은 클래스의 AP가 가장 높음을 확인하였다. 추후 데이터셋과 객체 검출 모델을 최적화함으로써, 정확도와 속도를 개선할 예정이다.

• 한국가구학회지
• /
• 제23권4호
• /
• pp.364-371
• /
• 2012

I designed a dietary life kitchen utensils which is focused by the shape of split bamboo that has meaning of health and safety and the shaman who is the religion and incantation performer, and who solve problems, which are impossible to solve in common methods, by borrowing the power and granting the meaning which is connected with transcendent existence and principal. Having closest relation with human being's diet culture is being changed with adding beauty instead of the part of simple practical aspect in our normal life. I tried to show incantation effect with keeping the characteristic of kitchen utensils by granting the symbolic meaning of shamanism which is the shelter that is projected the desire of human beings. the materials were produced of an ebony and steel and varnished with lacquer for coloring. For hand shape, which is hard to treat in irregular forms, the religious image of shamanism was formed by casting which expresses the touch of an ebony and the cold characteristic of metal. an overall design doesn't detail excessively distort or largely transform the form of dietary utensils, keeps its individuality, and emphasizes the image by figuring a grip part which a human can see and a body can approach. in addition, I try to show a point that shamanism has affected human life for long time and symbolic meaning of bamboo-shape shows health and safety. And these things vest with each dietary life tools and should be the role of enzyme about the effect of human life.