The COVID-19 pandemic spread rapidly around the world and is currently one of the most leading causes of death and heath disaster in the world. Turkey, like most of the countries, has been negatively affected by COVID-19. The aim of this study is to design a predictive model based on artificial neural network (ANN) model to predict the future number of daily cases and deaths caused by COVID-19 in a generalized way to fit different countries’ spreads. In this study, we used a dataset between 11 March 2020 and 23 January 2021 for different countries. This study provides an ANN model to assist the government to take preventive action for hospitals and medical facilities. The results show that there is an 86% overall accuracy in predicting the mortality rate and 87% in predicting the number of cases.
Airport base selection for pilot training academy is an important issue in the aviation industry because incorrect airport selection can have negative impact on flight operations for the flight academy. The aim of this article is to present a novel hybrid decision-making model based on rough numbers for the evaluation of flight training bases (airports). To select the most suitable alternative among five alternatives, a two-stage model is proposed. In the first stage, the measuring attractiveness by a categorical based evaluation technique approach is used to determine the criteria weights. In the second stage, the rough ranking of alternatives through functional mapping of criterion subintervals into a single interval approach is applied to rank the alternative airport bases. The proposed approach provides a new multicriteria framework for evaluating alternatives for the Turkish Airlines Flight Academy pilot training center in Turkey. The results obtained from the case study showed that the proposed approach could be practical for different multicriteria decision-making problems.
17 February 2020 in Neural Computing and Applications