Department of Computer and Information Technology, Ahrar Institute of Technology and Higher Education, Iran
Abstract: (1408 Views)
Coronavirus disease 2019 (COVID-19) is a contagious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). The first case was identified in Wuhan, China, in December 2019. The number of confirmed cases is increasing daily and reached 101 million on 28 January 2021. This paper attempts to propose a new hybrid intelligent method for the prediction of confirmed cases of COVID-19 in the upcoming ten days based on the previously confirmed cases recorded. To forecast future cases, wavelet full decomposition of time series analysis served as input data for Adaptive Network-based Fuzzy Inference System (ANFIS). In addition, to tune the ANFIS membership functions, Quantum-behaved Particle Swarm Optimization (QPSO) was used. During the data preprocessing phase, all kinds of Wavelet Transform functions were tested for the best result. The proposed method was found to be very efficient in forecasting confirmed cases of COVID-19 in the upcoming ten days. The proposed model is an improved adaptive neuro-fuzzy inference system (ANFIS) using QPSO and Wavelet Decomposition. The WT-QPSO-ANFIS model is evaluated using the World Health Organization (WHO) official data on the outbreak of COVID-19 to forecast the confirmed cases in the upcoming ten days. More so, the WT-QPSO-ANFIS model is compared to several existing models, and it showed better performance in terms of Mean Absolute Percentage Error (MAPE), Root Mean Squared Relative Error (RMSRE), Root Mean Squared Relative Error (RMSRE), coefficient of determination (R2), and computing time.
Faridi Masouleh M, Akbari A, Bagheri A, Nezamivand Cheghin S. Wavelet transform and ANFIS network-based prediction technique for forecasting confirmed cases of Covid-19 in Iran. International Journal of Applied Operational Research 2023; 11 (1) :47-55 URL: http://ijorlu.liau.ac.ir/article-1-632-en.html