Optimization of Markov Weighted Fuzzy Time Series Forecasting Using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO)

The Markov Weighted Fuzzy Time Series (MWFTS) is a method for making predictions based on developing fuzzy time series (FTS) algorithm. MWTS has overcome certain limitations of FTS, such as repetition logic relationships and weight considerations relationships. main challenge the MWFTS absence standardized rules determining partition intervals. This study compares model to methods Genetic Algorithm-Fuzzy K-Medoids clustering (GA-FKM) clustering-Particle Swarm Optimization (FKM-PSO) solve problem interval develop an Optimal optimization. GA optimization algorithm’s performance GA-FKM depends optimizing FKM obtain most significant interval. Implementing PSO algorithm FKM-PSO involves maximizing length following procedure. proposed was applied Anand Vihar, India’s air quality data. combined with partitioning reduced mean absolute square error (MAPE) from 17.440 16.85%. While results forecasting using in conjunction were able reduce MAPE percentage 9.78% 7.58%, still 9.78%. Initially, root (RMSE) score technique 48,179 47,01. After applying method, initial RMSE 30,638 24,863. Doi: 10.28991/ESJ-2022-06-06-010 Full Text: PDF