Intelligent Wearable Occupational Health Safety Assurance System of Power Operation
- 42 Downloads
To improve the capacity of emergency control over on-site operation risk and effectively guarantee safety of operators in a complicated environment, a wearable safety assurance system framework for power operation is proposed. The framework centres on a wearable information processing gateway for single man and provides standardized access for vital signs monitoring, human-machine interaction and other equipment in a form of wireless ad hoc network. Using wearable vital signs monitoring equipment, the physiological parameters such as heart rate, body temperature and blood pressure can be monitored in real time. By extracting physiological parameters and SVM machine learning method, the operator’s health condition is judged. Practical application shows that the wearable safety assurance system can evaluate the life status of workers in complex environment in real time, and can detect the risk of personal safety accidents caused by abnormal physical condition in the process of operation in advance.
KeywordsWearable vital signs monitoring SVM life status assessment method Portable information processing gateway Occupational health safety
This study was funded by the Key R&D Projects of Sichuan Province (No. 2017GZ0068), Application of Basic Research Projects of Sichuan Province (No. 2017JY0338), and a project of State Grid Sichuan Electric Power Corporation (No.52199716002P).
Compliance with Ethical Standards
Conflict of Interest
Xiaona Xie declares that she has no conflict of interest. Zhengwei Chang declares that he has no conflict of interest.
This article does not contain any studies with human participants performed by any of the authors.
- 5.Sun, X., and Feng, Z., Interaction design for wearable devices. J. Decor. 250:28–33, 2016.Google Scholar
- 6.Wang, C., and Shi, J., Wireless sensor network in American war-fighter physiologic status monitoring system. Chin. Med. Equip. J. 28(11):34–36, 2007.Google Scholar
- 7.Chen, Y., Xin, Y. et al., Multi-scale wavelet entropy based method for paroxysmal atrial fibrillation recognition. Space Med. Med. Eng. 26(5):352–355, 2013.Google Scholar
- 8.Zhang, Y., Liu, C. et al., ECG quality assessment based on a kernel SVM and genetic algorithm with a feature matrix. Front. Inf. Technol. Electron. Eng. 15(7):564–573, 2014.Google Scholar
- 9.Zhang, M., Lai, Z. et al., Multi-class support vector machine classifier based on jeffries-matusita distance and directed acyclic graph. J. Harbin Inst. Technol. 20(5):113–118, 2013.Google Scholar
- 10.Sun, S., and Huang, Z., A multi-class SVM classification algorithm. Microcomput. Appl. 35(8):12–14, 2016.Google Scholar
- 11.Huang, J., Wang, Z. et al., Design of wearable multiple sign parameters monitoring system for policemen. Chin. J. Sensors Actuators 30(4):635–640, 2017.Google Scholar