Integrating PSO-GA with ANFIS for predictive analytics of confirmed cases of COVID-19 in Iran
نویسندگان
1 Department of Industrial Engineering, K.N Toosi University of Technology, Tehran, Iran
2 Department of Industrial Engineering, K.N Toosi University of Technology, Tehran, Iran
doi
چکیده
The first case of the unknown coronavirus, referred to as COVID-19, was detected in Wuhan, China, in late December 2019, and spread throughout China and globally. The total confirmed cases globally are rising day by day. This study proposes a novel prediction model to estimate and predict the total confirmed cases of COVID-19 in the next two days, according to Iran’s confirmed cases reported before. The proposed model is an improved adaptive neuro-fuzzy inference system (ANFIS) using a co-evolutionary PSO-GA algorithm. PSO-GA is generally used to strike a balance between exploration and exploitation capabilities enhanced further by integrating the genetic operators, i.e., mutation and crossover in the PSO algorithm. The proposed model (i.e., PSO-GA-ANFIS) thus aims to enhance the efficiency of the ANFIS model by determining ANFIS parameters using PSO-GA. The model is assessed by utilizing epidemiological data provided by John Hopkins University to forecast the COVID-19 epidemic prevalence trend of Iran in 02.20.2020-06.10.2020-time window. A comparison was also made between the proposed model and a couple of available models. The results indicated that the proposed model outperforms the other models regarding MSE, RMSE, MAPE, and R2.