Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

2-2018

Abstract

Effective emergency (medical, fire or criminal) response iscrucial for improving safety and security in urban environments. Recent research in improving effectiveness of emergency management systems (EMSs) has utilized data-drivenoptimization models for efficient allocation of emergency response vehicles (ERVs) to base locations. However, thesedata-driven optimization models either ignore the dispatchstrategy of ERVs (typically the nearest available ERV is dispatched to serve an incident) or employ myopic approaches(e.g., greedy approach based on marginal gain). This resultsin allocations that are not synchronised with the real evolution dynamics on the ground or can be improved significantly.To bridge this gap, we make the following contributions: (1)We first provide a novel exact optimization model for allocation of ERVs that incorporates the non-linear real-worlddispatch strategy as linear constraints and ensures that optimization exactly imitates the real-world dynamics of EMS;(2) In order to improve scalability, we then provide two novelheuristic approaches to solve problems with large number ofemergency incidents; and (3) Finally, using two real-worldEMS data sets, we empirically demonstrate that our heuristic approaches provide significant improvement over the bestknown benchmark approach.

Keywords

Emergency response, Constraint optimization, Heuristics, Data-driven modelling

Discipline

Computer Sciences | Medicine and Health Sciences | Operations Research, Systems Engineering and Industrial Engineering

Research Areas

Intelligent Systems and Optimization

Publication

Proceedings of the 32nd AAAI Conference on Artificial Intelligence 2018, February 2-7, New Orleans

First Page

775

Last Page

783

Publisher

AAAI Press

City or Country

Menlo Park, CA

Download

Share

COinS