Novel intelligent TOPSIS variant to rank regions for disaster preparedness

Abstract

An important facet of disaster mitigation is discovering regions based on their lack of preparedness for combating disaster. Accordingly, organizations can lay down appropriate risk management strategies and guidelines to minimize loss due to disaster. "Technique for order of preference by similarity to ideal solution (TOPSIS)" is a popular multi-criteria decisionmaking (MCDM) method that is deployed for ranking alternatives based on multiple pre-specified criteria. However, the method's efficiency in ranking region as per multiple criteria for disaster management is far from the ground truth. The authors propose a novel intelligent method HCF-TOPSIS, an extension of traditional TOPSIS, to deliver an efficient ranking mechanism for regional safety assessment of disaster affected regions. HCF-TOPSIS capitalizes on entropy (H), closeness (C), and farness (F) metrics to obtain efficient ranking scores of the disaster affected regions. Extensive experimentation validates the claim and proves the superiority of HCF-TOPSIS over existing TOPSIS variants. The proposed research presents many benefits, especially to governments and stakeholders, intending to take appropriate actions to contain disasters.