An evaluation of machine learning algorithms coupled to an electronic olfactory system: a study of the mint case

Abstract

The aim of this investigatation is to compare the utility of machine learning algorithms in distinguishing between untreated and processed mint beside in predicting the spray day of the insecticide. Within seven days, mint treated samples with the malathion insecticide are collected, and their aromas are Studied using a laboratory-manufactured sensor array system based on commercial metallic semiconductor (MOS) gas sensors. To distinguish the mint type, some results of machine learning algorithms were compared to know the decision trees (DT), Naive Bayes, support vector machines (SVM), and ensemble classifier. Furthermore, to predict the treatment day support vector machines regression (SVMR) and partial least squares regression (PLSR) were compared. Regarding the best results, in the discrimination case, a success rate of 92.9% was achieved by the ensemble classifier while in the prediction case, a correlation coefficient of R=0.82 was reached by the SVMR. Good results are achieved if the right gas sensor array system is designed and realized coupled with a good choice of the appropriate machine learning algorithms.