Classification and quantification of binary mixtures of gases/odors using thick-film gas sensor array responses

Abstract

This paper presents the results of experiments done for classification and quantification of two volatile organic compounds (VOCs), namely, acetone (CH3COCH3) and 2-Propanol (CH3CHOHCH3) in their single as well as in mixture forms. A sensor array consisting of four sensor elements was fabricated in our lab using thick-film fabrication technology. The steady-state responses of the sensor array were collected for the mentioned VOCs in their single as well as in mixture form. A hierarchical system consisting of gating network and three quantification networks was designed to classify and subsequently quantify the individual and mixture of VOCs. The classification accuracy results of gating network have been ensured using back-propagation neural network (BPNN) and support vector machine (SVM). For quantification multioutput support vector regression method was used in slave networks for single as well as binary mixture data. $k$ -fold cross validation scheme was adopted for all the experiments. The average classification accuracy of gating network for the mixture data in raw form was 89.5% using BPNN and 94.7% using nu-SVM. With principal component analysis preprocessed data, the average accuracy was 95.6% with BPNN and 100% using nu-SVM, respectively. For quantification, good 0.9828 and 0.9764 correlation coefficients for the predicted versus real concentration of acetone and 2-Propanol, respectively, in mixture form were obtained. Thus, we report a promising approach for binary mixture of gases/odors analysis using thick-film gas sensor array responses. © 2014 IEEE.