Resilience of healthy cities in the post-pandemic era: Findings based on internet of things data and artificial intelligence algorithms

Abstract

This study aims to improve urban resilience in the face of public health emergencies. Therefore, based on the urban resilience development theory, a resilience evaluation index system for healthy cities is constructed. In addition, the Back Propagation Neural Network (BPNN) algorithm and entropy method are combined to empirically evaluate 7 representative cities in the Yangtze River Delta urban agglomeration. Linear regression analysis is carried out on the index weight of the evaluation system, relative proximity degree, and score of urban resilience. The results reveal that social environment and infrastructure are two important factors in the resilience evaluation of healthy cities. Nanjing and Shanghai have relatively good resilience, while Ma'anshan has the worst resilience. It is also found that economic status is the most critical factor affecting urban resilience. Thus, this study enriches the theories related to urban resilience, expands the evaluation system of urban resilience, and opens up a new approach to the quantitative evaluation of urban resilience.