Application of neural network to electrostatic fields distribution pattern: A case study.

This paper presents the application of neural network to the electrostatic field distribution pattern modeling: a case study of Non-harmattan seasons in Zaria, Nigeria. The data was captured through an online mechanism for twenty four months (February, 2007–February, 2009) by the computer; the focus of the analysis is determining the effect of environmental factors such as temperature, pressure and relative humidity on the static electric field during the Non-harmattan season. The plots of the electrostatic field against the variation of the environmental factors were used as the qualitative analytical tools and yielded a non-linear relationship. The data was analyzed using Neural Network version 3.24 Software, to establish predictive model for the Non-harmattan period. The result of the analyses yielded good neural statistical values of Root Mean Square Error (RMSE) of 0.05, Pearson R value of 0.087 and RMSE of 0.04, R of 0.83 respectively for Non-harmattan, inside and outside Scenarios, which are reflections of a good models. The result was further buttressed by the plot of the Neural Network based Electrostatic Fields distribution pattern modeling of the experimental and predicted parameters. With the insignificant values of the RMSE, Pearson R value which are reflections of the closeness of the predicted and the experimental parameters, hence the model could be relied upon to predict the electrostatic fields during Non-harmattan season in Zaria, Nigeria. [ABSTRACT FROM PUBLISHER]