Comparative Analysis Among Various Soft Computing Classifiers for Nutrient Removal from Wastewater

Abstract

The purpose of this study is to predict nutrient removal from wastewater by using different soft computing classifiers. A comparison of different classifiers, e.g., linear regression, nonlinear regression and artificial neural network (ANN) is done. ANN shows promising results as compared to linear and nonlinear regression. In this study, the data is collected from previous research papers. Out of the collected data, 75% is used to train the models and residual 25% is used for the validation of the models. The model accuracy is depending upon three evaluation parameters which are coefficient of determination (R2), root mean square error (RMSE), and means absolute error (MAE). The result shows that the ANN model is more accurate to predict the nutrient removal from wastewater as compared to linear and nonlinear models.