An Odor Labeling Convolutional Encoder–Decoder for Odor Sensing in Machine Olfaction

Deep learning methods have been widely applied to visual and acoustic technology. In this paper, we propose an odor labeling convolutional encoder–decoder (OLCE) for identification in machine olfaction. OLCE composes a neural network encoder decoder where the output is constrained labels. An electronic nose was used data collection of gas responses followed by normative experimental procedure. Several evaluation indexes were calculated evaluate algorithm effectiveness: accuracy 92.57%, precision 92.29%, recall rate 92.06%, F1-Score 91.96%, Kappa coefficient 90.76%. We also compared model with some algorithms The comparison result demonstrated that had best performance among these algorithms.