Training Anfis System with Moth-Flame Optimization Algorithm

Abstract

Adaptive Neuro Fuzzy Inference System (ANFIS) is an adaptive network that can use the computation and learning abilities of artificial neural network together with the inference feature of fuzzy logic. The ANFIS system, which is used in the solution of many problems such as classification and estimation of deep learning applications, meets the needs in many different areas such as modeling, control, and parameter estimation. In recent years, heuristic methods have been used for the training of this network, which requires initial and result parameters by its structure. Moth-Flame Optimization Algorithm (MFO) is one of the current heuristic methods modeled by the influence of the spiral movement of the moths towards the light source. In this study, the MFO algorithm was used for the first time for the optimization of initial and result parameters in the ANFIS system. In the determination of parameters, nonlinear system identification, time series estimation, classification problems were tried to be solved. When the results obtained for the ANFIS trained with the known heuristic methods such as Particle Swarm Optimization (PSO), Genetic Algorithm (GA) and Whale Optimization Algorithm (WOA) and the results of ANFIS trained by the MFO were examined, it was observed that the MFO had lower error values.

Application of Intelligent Exercise Training Equipment in Clinical Nursing of Neurology Department

“…e motor function of lower limbs can be improved with the Contrast Media & Molecular Imaging increase of muscle strength [11][12][13][14]. Based on the theory of biofeedback and brain plasticity, repeated systematic training can stimulate and promote functional recombination of nerve cells around stroke lesions through axon regeneration, dendrite "germination," and synaptic threshold change; thus, partially damaged brain function can be restored, and the recovery of the central nervous system's autonomous muscle control ability can be promoted [15].…”

Anfis İle İlgili Yapılmış Çalışmaların İçerik Analizi İle Değerlendirilmesi: Tr Dizin

“…Temel bileşenler analizi (Gökler ve Boran, 2020), logit-probit yöntemi (Söyler ve Kızılkaya, 2018), dalgacık dönüşüm uygulanması (Taylan, 2018), korelasyon analizi (Efendı̇gı̇l ve Emin Eminler, 2017), ileri seçim yönteminin kullanılması (Moazami vd., 2016) bu çalışmalardan bazılarıdır. Bazı çalışmaların ise Anfis sisteminin eğitilmesine odaklanarak farklı algoritmaların eğitilme işleminde kullanılması üzerinde odaklandıkları tespit edilmiştir (Canayaz, 2019;Ceylan ve Bulkan, 2018;Dokur vd., 2019;Karaboǧa ve Kaya, 2017).…”

“…Anfis ile ilgili çalışmalar incelendiğinde verilerin normalize edildiği ve raporlandığı yirmi bir çalışma olduğu tespit edilmiştir. Bunlardan sadece üç tanesi standart normalizasyon tekniğini kullanırken (Canayaz, 2019;Sönmez vd., 2018;Yılmaz vd., 2020), sadece bir çalışmada ise Log-Sigmoid normalizasyon kullanıldığı görülmüştür (Şengöz ve Özdemir, 2016). Çalışmaların yüzde 79'unda ise normalizasyon ile ilgili bilgi olmadığı görülmektedir.…”

Tuning ANFIS Using a Simplified Sparrow Search Algorithm

“…Since the initial ANFIS before train always has lots of unknown parameters need to determine, for various problems researchers combine many different metaheuristic algorithms into ANFIS such as PSO, artificial bee colony (ABC) [8], genetic algorithm (GA), satin bowerbird optimizer (SBO) [9], whale optimization algorithm (WOA) [10], pigeon-inspired optimization (PIO) [11], gray wolf optimization (GWO) [12]and so on .…”