Emergency treatment mechanism of laboratory safety accidents in university based on IoT and context aware computing

In recent years, safety accidents in university laboratories have occurred frequently. Not only do the accidents result in property damage, but also in injuries. Real-time environmental monitoring of the laboratory through IoT enables early detection of potential safety risks such as high temperatures, high humidity and gas leaks, and timely action to reduce the likelihood of accidents. To ensure laboratory safety, in the paper, an emergency treatment mechanism for laboratory safety accidents was proposed based on IoT and context perception. The mechanism uses sensors to collect environmental information and fill a feature characterization architecture for unified safety management. Subsequently, the meta-rule algorithm is used to discover services in the prior knowledge model to form a workflow engine, so as to drive the security business management. Additionally, based on the standard measurement model, we normalize the fuzzy uncertainty measurement model with different granularities and define the fuzzy uncertainty of different emergency decision-making knowledge. Based on this, a knowledge fusion method for emergency decision-making under different fuzzy uncertainties is proposed, which improves laboratory safety emergency response performance based on situational awareness. The implementation of the proposed mechanism in a chemical laboratory demonstrates its efficacy in optimizing operational processes and discovering operational flow through multi-dimensional information analysis. This capability significantly aids safety administrators in their daily laboratory safety management.