Shear stress comprises basic information for predicting the average depth velocity and discharge in channels. With knowledge of the percentage of shear force carried by walls (% SF w ) it is possible to more accurately estimate shear stress values. The %SF w , non-dimension wall shear stress ( � t w t 0 ) and non-dimension bed shear stress ( � t b t 0 ) in smooth rectangular channels were predicted by a three methods, the Bayesian Regularized Neural Network (BRNN), the Radial Basis Function (RBF), and the Modified Structure-Radial Basis Function (MS-RBF). For this aim, eight data series of research experimental results in smooth rectangular channels were used. The results of the new method of MS-RBF were compared with those of a simple RBF and BRNN methods and the best model was selected for modeling each predicted parameters. The MS-RBF model with RMSE of 3.073, 0.0366 and 0.0354t 0 respectively, demonstrated better performance than those of the RBF and BRNN models. The results of MS-RBF model were compared with three other proposed equations by researchers for trapezoidal channels and rectangular ducts. The results showed that the MS-RBF model performance in estimating %SF w, � t w t 0 and � t b t 0 is superior than those of presented equations by researchers.