Improving gas identification accuracy of a temperature-modulated gas sensor using an ensemble of classifiers

Data processing methods commonly used in conjunction with the array- and quasi-array-based gas identification systems generally include a dimension reduction followed by categorization using a classifier. Here, we have applied an ensemble of classifiers, directly to the high dimensional feature vectors and fused their verdicts by majority voting. The quasi-array investigated is a metal oxide sensor temperature-modulated with different rectangular heating voltage pulses. The experimental database was developed by recording the temporal responses obtained at different conditions to methanol, ethanol and 1-butanol vapors. Features related to each response were extracted by wavelet transform. The classification rates achieved with traditional methods were compared to that obtained using an ensemble of classifiers. The classification rate was improved by majority voting among the classifiers, each trained on different feature subsets, for the classification verdict.