A framework of training ANFIS using Chicken Swarm Optimization for solving classification problems

Abstract

The result of training parameters described Adaptive Neuro-Fuzzy Inference System (ANFIS) performance. The speed and reliability of training effect depend on the training mechanism. There have been many methods used to train the parameters of ANFIS as using GD, metaheuristic techniques, and LSE. But there are still many methods developed to achieve efficiently. One of the proposed algorithm to improve the performance of ANFIS is Chicken swarm optimization (CSO) algorithm. The experimental results of training ANFIS network for classification problems show that ANFIS-CSO algorithm achieved better accuracy.