EVACUSCAPE: Internet of Things-enabled emergency evacuation based on matching theory

Abstract

The effective evacuation during disaster scenarios, either physical or man-made, is critical in order to ensure the safety and survival of the victims, minimize the casualties, and facilitate the rapid and organized movement of people to safety. In this paper, the EVACUSCAPE model is introduced to optimize the matching between victims and evacuation routes during an evacuation process. Initially, the characteristics of both the victims and the evacuation routes are analyzed to establish a foundational matching mechanism among them. The Approximate EVACUSCAPE algorithm is developed to perform an initial matching between the victims and the evacuation routes by disregarding externalities that influence the victims’ decisions, such as the actions of other evacuees. Then, the Accurate EVACUSCAPE algorithm refines the matching process by incorporating the principles of coalition games to account for these externalities and ultimately derive an optimal and stable evacuation strategy. A comprehensive evaluation using real-world datasets demonstrates the effectiveness and robustness of the EVACUSCAPE model, which significantly outperforms conventional evacuation strategies where the victims select routes based solely on proximity or time-optimization in a selfish manner.