Simultaneous prediction of acetic acid/ethanol concentrations in their binary mixtures using metalloporphyrin based opto-electronic nose for meat safety applications

Abstract

This paper presents a comprehensive study on the simultaneous prediction of volatile organic compound (VOC) concentrations in their binary mixtures (acetic acid and ethanol) using partial least square regression (PLSR) and multilayer perceptron neural network (MLP-NN). A metalloporphyrin based opto-electronic nose was developed to record the reflectance from metalloporphyrin sensing film. A ruthenium based metalloporphyrin, 2,3,7,8,12,13,17,18-octaethyl-21H, 23H-porphine ruthenium(II) carbonyl (RuOEPCO), was used as sensing material. The percent change in the reflectance (%ΔR) before and after exposure to different combinations of analyte concentrations were used as the input to the prediction models. The relative standard error of prediction (RSEP, %) of the PLS model was found to be 18.51 and 21.77% for acetic acid and ethanol prediction validated using independent test set, respectively. On the other hand, neural network (multilayer perceptron) produced an average RSEP of 7.27 and 9.13% for acetic acid and ethanol prediction validated using independent test set, respectively. Neural networks produced comparatively lower prediction errors using independent test set validation method and shows potential for further investigation and validation on larger dataset.