.png){kind=icon}
.png){kind=icon}
Return
Log-driven predictive analysis of remaining time for emergency response processes
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.127800.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The cross-organizational, messaging and resource attributes of emergency response processes effectively improve the accuracy of remaining time prediction. For this purpose, a log-driven analysis method for remaining time prediction of emergency response processes is proposed. Firstly, the attributes such as cross-organization, messaging and resources of the emergency response process are encoded, and then the vector representation of the emergency response process is obtained. Secondly, the vector representations of the emergency response processes are fed into a deep neural network prediction model for learning. Finally, we experimented with an emergency response process log to demonstrate the proposed method.
Keywords:
Emergency response process
Petri net
Neural network
Time prediction
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W