.png){kind=icon}
.png){kind=icon}
Return
Spatiotemporal representation learning for rescue route selection: An optimized regularization based method
.png){kind=icon}
PRE
AI
DOI：10.1016/j.elerap.2021.101065.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Emergency medical services (EMS) are emergency services that provide urgent pre-hospital treatment for serious illness and injuries. However, in most countries, EMS is faced with the problem of untimely emergency response. In this paper, we develop an Optimized Regularization based framework (OpRe-RRS) by optimizing the Rescue Route Selection problem to increase the rescue speed. Specifically, through the analysis of spatio-temporal data, we predict the ranking of road priority and select the rescue route for ambulances to lift speed. Along this line, we match the GPS data of ambulances to the correct road section through a map matching algorithm. Then, we extract different features from three perspectives: (i) basic features, (ii) POI features and (iii) traffic features. To effectively exploit the roads similarity, we develop a loss function with regularization to solve this prediction problem. Finally, experiments on real-world data demonstrate that our method can effectively reduce rescue time.
Keywords:
Spatio-temporal Data
Ambulance
Rescue Route Selection
Regularization
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
6.3
Papers:
2.4K
Citations:
5.9K