산업현장 고소작업자를 위한 스마트 안전 벨트
Smart Safety Belt for High Rise Worker at Industrial Field
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Safety management agent manages the risk behavior of the worker with the naked eye, but there is a real difficulty for one the agent to manage all the workers. In this paper, IoT device is attached to a harness safety belt that a worker wears to solve this problem, and behavior data is upload to the cloud in real time. We analyze the upload data through the deep learning and analyze the risk behavior of the worker. When the analysis result is judged to be dangerous behavior, we designed and implemented a system that informs the manager through monitoring application. In order to confirm that the risk behavior analysis through the deep learning is normally performed, the data values of 4 behaviors (walking, running, standing and sitting) were collected from IMU sensor for 60 minutes and learned through Tensorflow, Inception model. In order to verify the accuracy of the proposed system, we conducted inference experiments five times for each of the four behaviors, and confirmed the accuracy of the inference result to be 96.0%.
Abstract
Safety management agent manages the risk behavior of the worker with the naked eye, but there is a real difficulty for one the agent to manage all the workers. In this paper, IoT device is attached to a harness safety belt that a worker wears to solve this problem, and behavior data is upload to the cloud in real time. We analyze the upload data through the deep learning and analyze the risk behavior of the worker. When the analysis result is judged to be dangerous behavior, we designed and implemented a system that informs the manager through monitoring application. In order to confirm that the risk behavior analysis through the deep learning is normally performed, the data values of 4 behaviors (walking, running, standing and sitting) were collected from IMU sensor for 60 minutes and learned through Tensorflow, Inception model. In order to verify the accuracy of the proposed system, we conducted inference experiments five times for each of the four behaviors, and confirmed the accuracy of the inference result to be 96.0%.
참고문헌 (17)
- Industrial Accident Analysis, "Korea Occupational Safety & Health Agency", ~ (2016)
- J. W. Jeong, "Theory and Real of Industrial Safety and Health Management", ~ (2015)
- 김균태, "건축공사현장의 안전관리 모니터링을 위한 USN 기술 적용에 관한 연구", 한국건축시공학회지, 9(4), pp.103~109 (2009), 한국건축시공학회
- Manpower transport safety, "Korea Occupational Safety & Health Agency", ~ (2008)
- Korea Occupational Safety & Health Agency, "Standard Work Safety (Manufacturing)", ~ (2009)
- S. G. Hong, "Gait feature extraction algorithm based on useractivity recognition using inertial sensors", Master's, pp.2017
- Nils Y. Hammerla, "Deep, Convolutional, and Recurrent Modelsfor Human Activity Recognition Using Wearables", Proceedings. the Twenty-Fifth International Joint Conference on Artificial Intelligence, pp.1533~1540 (2016)
- 박근철, "가속도 및 각속도 신호를 이용한 낙상 인지 시스템 구현", 센서학회지, 22(1), pp.54~64 (2013), 한국센서학회[DOI]
- K. Y. Lee, "An Algorithm of Indoor Pedestrian Dead-Reckoning using IMU Sensor and Map Matching", Master's, pp.2012
- 정선재, "USN 기반 개인 안전벨트 모니터링 시스템의 구현", 한국정보통신학회논문지, 19(3), pp.724~730 (2015), 한국정보통신학회[DOI]
- 안병구, "IMU 및 가속도 센서를 이용한 안내견 하네스 행동 알림 시스템 구현", 융합신호처리학회 논문지, 16(1), pp.15~21 (2015), 한국융합신호처리학회[DOI]
- R. Grzeszick, "Deep Neural Network based Human Activity Recognition for the Order Picking Process", Proceedings Of The 4Th International Workshop On Sensor-Based Activity Recognition And Interaction - Iwoar '17 (2017)
- Omid Dehzangi, "IMU-Based Gait Recognition Using Convolutional Neural Networks and Multi-Sensor Fusion", Sensors, 17(12), pp.2735~ (2017), MDPI AG[DOI]
- Woo-Young Kang, "Hangeul Handwriting Recognition using Deeper Convolutional Neural Networks Based on Inception Modules", KCC, 2016(6), pp.883~885 (2016)
- "Going deeper with convolutions"[URL]
- "Deep Learning in Neural Networks: An Overview" (2014)[URL]
- Choi, Hyoungin, "A Study of Fall Detection before Impact Point usingan IMU Sensor", Master's, pp.2016