Fuzzy Logic, Pairwise Comparison, and Q-learning Methods to Investigate the Pandemic Infection Risk for Health Monitoring of Airports

A pandemic virus infection risk in air travel by fuzzy logic, pairwise comparison, and q-learning methods is investigated in this study. the vastness of airports and the shortage of health monitoring devices for covering all of the airports were one of the problems of general aviation. in this way, this study proposed a risk assessment analysis to find a distribution policy to allocate the health monitoring devices based on the airports' infection risk score. in this paper, kish airline's transportation regarding different flight destinations is considered as a case study. furthermore, fuzzy logic, pairwise comparison, and q-learning methods were considered for the pandemic infection risk. furthermore, the infection risk score related to the pandemic infection risk by pearson correlation coefficient was investigated. also, flight destinations located in the studied area with a higher infection risk score compared to other areas were analyzed by fuzzy logic, pairwise comparison, and q-learning methods. moreover, the three mentioned methods were compared and the results demonstrated that fuzzy logic overcomes the pairwise comparison and q-learning methods for this study. finally, results showed this study will be efficient for the next pandemic virus in general aviation.