Content area
Full Text
Abstract ID: 3426
Abstract
Most pedestrian evacuation models have restrictive assumptions that do not allow one to accurately depict the wide array of responses in the event of a tsunami. This work will describe the use of survey data on the at-risk population in Rincón, PR in order to relax an assumption found in most pedestrian evacuation models-all individuals evacuate immediately. It is well known that there are a variety of factors that will prevent this from happening. For example, a single mother separated from her children might choose to pick them up at school before evacuating, as opposed to evacuating immediately if she were with them at the time. In this work, a prediction model will be used to predict the evacuation response of individuals. The factors that will be considered in the model include: age group, gender, resident status (resident of Rincón vs. tourist), the individual's total number in household, and whether the individual is with his or her dependent population in the event of an evacuation. After evaluating a variety of standalone classifiers and meta learners, results in a five-fold cross validation setting indicate the random forest learner is the top performer.
Keywords
Pedestrian evacuation model, classification, tsunami, supervised learning, data mining
(ProQuest: ... denotes formulae omitted.)
1.Introduction
The detrimental effects of floods and tsunamis are well known [1,2] and, in order to develop effective mitigation strategies, it is key for emergency responders to understand the population they are serving. In order to prepare for a tsunami threat, emergency responders need to be aware that some subpopulations are more willing to evacuate immediately than others. Some, even after recognizing the signals of an imminent threat, will refuse to evacuate. Others, even when they would like to evacuate, would not be able to do so without significant assistance. What characteristics could make any given subpopulation more willing to evacuate immediately and less likely to contribute to the casualties count after a flood or tsunami event?
A robust pedestrian evacuation model (PEM) can be a powerful tool to help answer all of these questions. It can be used to understand how a population can escape from a hazard-prone area, how much time it would take an individual to evacuate, and how many individuals...