Measuring the rationality in evacuation behavior with deep learning

Abstract

The bounded rationality is a crucial component in human behaviors. It plays a key role in the typical collective behavior of evacuation, in which the heterogeneous information leads to the deviation of rational choices. In this study, we propose a deep learning framework to extract the quantitative deviation which emerges in a cellular automaton (CA) model describing the evacuation. The well-trained deep convolutional neural networks (CNNs) accurately predict the rational factors from multi-frame images generated by the CA model. In addition, it should be noted that the performance of this machine is robust to the incomplete images corresponding to global information loss. Moreover, this framework provides us with a playground in which the rationality is measured in evacuation and the scheme could also be generalized to other well-designed virtual experiments.

arXiv comment11 pages, 6 figures, and comments welcome

References in corpus (17)

• Social Force Model for Pedestrian Dynamics
• Simulating Dynamical Features of Escape Panic
• Statistical physics of social dynamics
• Simulation of pedestrian dynamics using a 2-dimensional cellular automaton
• How simple rules determine pedestrian behavior and crowd disasters
• Friction effects and clogging in a cellular automaton model for pedestrian dynamics
• Recognition of Crowd Behavior from Mobile Sensors with Pattern Analysis and Graph Clustering Methods
• Intrinsic group behaviour: dependence of pedestrian dyad dynamics on principal social and personal features
• Inferring Markov Chains: Bayesian Estimation, Model Comparison, Entropy Rate, and Out-of-class Modeling
• Mechanical response of dense pedestrian crowds to the crossing of intruders
• Bayesian Structural Inference for Hidden Processes
• Fluctuations around mean walking behaviours in diluted pedestrian flows
• A Trap Model for Clogging and Unclogging in Granular Hopper Flows
• Deep learning stochastic processes with QCD phase transition
• A counterintuitive way to speed up pedestrian and granular bottleneck flows prone to clogging: Can 'more' escape faster?
• Escape dynamics based on bounded rationality
• Evidence for mixed rationalities in preference formation