Artificial Intelligence (AI) Based Tools for Predicting the Removal Efficiency of Heavy Metals by Adsorption

Abstract

The two most popular artificial intelligence (AI) techniques namely, artificial neural networks (ANN) and support vector machines (SVM) have been applied for predicting the removal efficiency of heavy metals like Copper (II), Arsenic (III), Lead (II), etc. in an adsorption process using low cost biosorbents. A comparison has been made between ANN, SVM and multiple linear regression (MLR) models based on the statistical parameters such as: correlation coefficient (R), average absolute relative error (AARE) etc. SVM is found to be the better predictive model than the commonly used MLR model and ANN model. Hence, its results are more accurate and generalized.