“…The mean average relative error of the model was 2.48%. Since then, several other computer-aided data-driven models have been developed by considering different intelligent modeling approaches, including fuzzy C-means clustering-based adaptive neuro-fuzzy system (FCM-ANFIS), hybrid self-organizing polynomial neural networks (PNN) based on group method of data handling (GMDH), least-square support vector machine (LSSVM), radial basis function neural networks (RBF-NN), genetic algorithm-polynomial neural network (GA-PNN), multilayer perceptron neural networks (MLP-NNs), gene expression programming (GEP) [ 8 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 , 35 ]. However, the most accurate model with a wide range of applicability for the prediction of viscosity of nanofluids was developed by Hemmati-Sarapardeh et al [ 1 ], based on a committee machine intelligent system (CMIS).…”