vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff9a1d1d0000007c10040001000200
The objective in ground resistance is to attain the most minimal ground safety esteem conceivable that bodes well monetarily and physically. An application of artificial neural networks (ANN) to presage and relegation has been growing rapidly due to sundry unique characteristics of ANN models. A decent forecast is able to capture the dubiousness associated with those ground resistance. A portion of the key instabilities are soil composition, moisture content, temperature, ground electrodes and spacing of the electrodes. Propelled by this need, this paper endeavors to develop a generalized regression neural network (GRNN) to predict the ground resistance. The GRNN has a single design parameter and expeditious learning and efficacious modeling for nonlinear time series. The precision of the forecast is applied to the Athens seasonal variation of ground resistance that shows the efficacy of the proposed approach.