Classifying smokes using an electronic nose and neural networks

We have created an electronic nose using the metal oxide sensors from two commercial brands, FIS and FIGARO. In this paper, we use this electronic nose to classify the smell from 3 types of burning materials and then we apply the standard back propagation and recurrent back propagation neural networks to train and classify those burning smells. In the experiment, we test 3 kinds of joss stick, 2 brands of cigarette, and a mosquito coil. Moreover, we also measure the difference between concentration of smoke by varying the number of burning joss sticks. The results show that it is able to classify the smoke correctly. The idea of this research can be used for making a smart smoke detector in order to detect a harmful burning material before it is too late to stop the fire.