An ensemble classifier based on a bionic model and SVM for machine olfaction

This paper presents a novel approach for pattern recognition in machine olfaction by constructing an ensemble classifier using a bionic olfactory neural network, namely KIII model, and support vector machine (SVM). In this approach, feature vectors are firstly processed by KIII model which stimulates information processing function of olfactory bulb, and then classified by SVM. In the experiment to classify aroma of reconstituted milk from that of fresh milk, this approach shows promising accuracy for complex data and is more robust than pure SVM.