Particle swarm optimization is a population-based optimization algorithm form on the social behavior of animals living in swarms such as birds, ants, fish, and bees.
Published in Chapter:
Prediction of Capacity Utilization Rate for Turkey Using Adaptive Neuro-Fuzzy Inference System With Particle Swarm Optimization and Genetic Algorithm
Didem Guleryuz (Bayburt University, Turkey)
Copyright: © 2022
|Pages: 22
DOI: 10.4018/978-1-7998-7979-4.ch013
Abstract
This chapter aims to propose prediction models to estimate Turkey's manufacturing sector's capacity utilization rate between 2008-2019 monthly basis using the adaptive neuro-fuzzy inference system (ANFIS) with genetic algorithm (GA) and particle swarm optimization (PSO) via determined indicators. The model's accuracy will be tested using some of the performance evaluation criteria, namely mean absolute error (MAE), root mean square error (RMSE), and the coefficient of determination (R2) values were used to compare the prediction ability. The coefficient of determination for GA-ANFIS, PSO-ANFIS, and ANFIS models are 0.9787, 0.9786, and 0.9679 in the training phase and 0.9591, 0.7677, and 0.7264 in the testing phase, respectively. The study results showed that the GA-ANFIS model showed better predictive ability with the least prediction error among other models. As a result, ANFIS, whose parameters are adjusted with GA, can predict the Turkish capacity utilization rate in the manufacturing industry with high accuracy.