A Learning Real-Time Routing System for Emergency Vehicles

Vlad, R.C.; Morel, Cristina; Morel, Jean-Yves; Vlad, S.

doi:10.1109/aqtr.2008.4588950

Cited by 9 publications

(3 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While some studies have used ML, deep learning and/or artificial intelligent techniques for predicting the ambulance demand, other studies find these methods useful in predicting travel times on road network. [31][32][33][34][35][36][37][38] Boutilier and Chan 39 proposed a regression approach to estimate the distribution of ambulance travel time between two points. The method uses global positioning system data obtained from historical trips of ambulances on the given road network.…”

Section: Literature Reviewmentioning

confidence: 99%

A Sustainable Model for Emergency Medical Services in Developing Countries: A Novel Approach Using Partial Outsourcing and Machine Learning

Rathore¹,

PK²,

Parida³

2022

RMHP

View full text Add to dashboard Cite

Introduction: Unlike Western countries, many low-and middle-income countries (LMIC), like India, have a de-centralized emergency medical services (EMS) involving both semi-government and non-government organizations. It is alarming that due to the absence of a common ecosystem, the utilization of resources is inefficient, which leads to shortage of available vehicles and larger response time. Fragmentation of emergency supply chain resources motivates us to propose a new vehicle routing and scheduling model equipped with novel features to ensure minimal response time using existing resources. Materials and Methods:The data set of medical and fire-related emergencies from January 2018 to May 2018 of Uttarakhand State in India was provided by GVK Emergency Management and Research Institute (GVK EMRI) also known as 108 EMSs was used in the study. The proposed model integrates all the available EMS vehicles including partial outsourcing to non-ambulatory vehicles like police vans, taxis, etc., using a novel two-echelon heuristic approach. In the first stage, an offline learning model is developed to yield the deployment strategy for EMS vehicles. Seven well researched machine learning (ML) algorithms were analyzed for parameter prediction namely random forest (RF), convolutional neural network (CNN), k-nearest neighbor (KNN), classification and regression tree (CART), support vector machine (SVM), logistic regression (LR), and linear discriminant analysis (LDA). In the second stage, a real-time routing model is proposed for EMS vehicle routing at the time of emergency, considering partial outsourcing. Results and Discussion:The results indicate that the RF classifier outperforms the LR, LDA, SVM, CNN, CART and NB classifier in terms of both accuracy as well as F-1 score. The proposed vehicle routing and scheduling model for automated decision-making shows an improvement of 42.1%, 54%, 27.9% and 62% in vehicle assignment time, vehicle travel time from base to scene, travel time from scene to hospital, and total response time, respectively, in urban areas.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Sustainable Model for Emergency Medical Services in Developing Countries: A Novel Approach Using Partial Outsourcing and Machine Learning

Rathore¹,

PK²,

Parida³

2022

RMHP

View full text Add to dashboard Cite

show abstract

“…A shortest-time algorithm is used to plan primary and alternative routes based on distances and average expected speeds. In [ 29 ], the authors describe a modified A* algorithm called a learning routing algorithm (LRA) that uses a mix of real-time traffic and EV travel data. They report that LRA execution time is faster than that of the original A* algorithm [ 30 ].…”

Section: Related Workmentioning

confidence: 99%

“…In the next set of studies, the authors look at ways to manipulate traffic lights to increase EV route efficiency. In [ 29 ], real-time traffic data are collected by telemetry units installed in EVs and traffic lights, with an adaptive A* routing algorithm used to find minimum travel time paths. Real-time traffic data are used to train the neural network and to increase the speed of the routing protocol.…”

Section: Related Workmentioning

confidence: 99%

Impact of Vehicular Networks on Emergency Medical Services in Urban Areas

Lee

Huang

Hsiao

et al. 2014

IJERPH

View full text Add to dashboard Cite

The speed with which emergency personnel can provide emergency treatment is crucial to reducing death and disability among acute and critically ill patients. Unfortunately, the rapid development of cities and increased numbers of vehicles are preventing emergency vehicles from easily reaching locations where they are needed. A significant number of researchers are experimenting with vehicular networks to address this issue, but in most studies the focus has been on communication technologies and protocols, with few efforts to assess how network applications actually support emergency medical care. Our motivation was to search the literature for suggested methods for assisting emergency vehicles, and to use simulations to evaluate them. Our results and evidence-based studies were cross-referenced to assess each method in terms of cumulative survival ratio (CSR) gains for acute and critically ill patients. Simulation results indicate that traffic light preemption resulted in significant CSR increases of between 32.4% and 90.2%. Route guidance was found to increase CSRs from 14.1% to 57.8%, while path clearing increased CSRs by 15.5% or less. It is our hope that this data will support the efforts of emergency medical technicians, traffic managers, and policy makers.

show abstract