Data mining for pesticide decontamination using heterogeneous photocatalytic processes

Abstract

Pesticides are chemical compounds used to kill pests and weeds. Due to their nature, pesticides are potentially toxic to many organisms, including humans. Among the various methods used to decontaminate pesticides from the environment, the heterogeneous photocatalytic process is one of the most effective approaches. This study focuses on artificial intelligence (AI) techniques used to generate optimum predictive models for pesticide decontamination processes using heterogeneous photocatalytic processes. In the present study, 537 valid cases from 45 articles from January 2000 to April 2020 were filtered based on their content collected and analyzed. Based on cross-industry standard process (CRISP) methodology, a set of four classifiers were applied: Decision Trees (DT), Bayesian Network (BN), Support Vector Machines (SVM), and Feed Forward Multilayer Perceptron Neural Networks (MLP). To compare the accuracy of the selected algorithms, accuracy, and sensitivity criteria were applied. After the final analysis, the DT classification algorithm with seven factors of prediction, the accuracy of 91.06%, and sensitivity of 80.32% was selected as the optimal predictor model.