In this work, we propose a novel Deep Convolutional Neural Network (DCNN) tailored for gas classification. Inspired by the great success of DCNN in the field of computer vision, we designed a DCNN with up to 38 layers. In general, the proposed gas neural network, named GasNet, consists of: six convolutional blocks, each block consist of six layers; a pooling layer; and a fully-connected layer. Together, these various layers make up a powerful deep model for gas classification. Experimental results show that the proposed DCNN method is an effective technique for classifying electronic nose data. We also demonstrate that the DCNN method can provide higher classification accuracy than comparable Support Vector Machine (SVM) methods and Multiple Layer Perceptron (MLP).

In this paper, we present a novel one-dimensional deep convolutional neural network (1D-DCNN) with a multilabel way based algorithm for comprehensively and automatically extracting features and classifying mixture gases. Although a number of pattern recognition methods have been used to analyze the mixed gases, the performances of these methods highly depend on the hand-crafted feature engineering. By contrast, the proposed implementation, based on one-dimensional convolution, is capable of automatically extracting features and distinguishing the individual component of binary mixture gases composed of Ethylene, CO and Methane. To the best of our knowledge, the proposed 1D-DCNN algorithm is firstly applied in the mixture gases recognition. In addition, the proposed 1D-DCNN with multilabel way not only significantly reduces the label dimension but also quantifies the probability of each component in mixed gases. Compared with the conventional pattern recognition algorithms including support vector machine (SVM), artificial neural network (ANN), k-nearest neighbor (KNN) and random forest (RF), the proposed 1D-DCNN exhibits higher recognition accuracy (96.30%) based on our extensive experimental results using 10- fold cross validation.

Fast recognition of flammable and toxic gas species within very short response time is a challenging task for the gas sensing devices adopted in a wide range of applications. The recognition accuracies of previous implementations are always constrained by the limited feature or dynamic information extracted from the short transient gas response curves. In order to address this issue, in this paper, we propose a novel hybrid approach with both convolutional and recurrent neural networks combined, which is based on the long short–term memory module. Featuring the capability of learning the correlations of time-series data, the proposed deep learning method is well-suited for extracting the valuable transient feature contained in the very beginning of the response curve. As a result, within a response time as short as 0.5s, the proposed implementation is capable of recognizing the gas species with an accuracy of 84.06%. In addition, the aforesaid accuracy can be further improved by increasing the response time with the step of 0.5s. According to our extensive experimental results, the recognition accuracy can be elevated up to 98.28% at the response time of 4s, where it typically needs 40s for the response curve to achieve saturation. The reported accuracy dramatically outperforms the previous algorithms, including gradient tree boosting (GTB), random forest (RF), support vector machine (SVM), k-nearest neighbor (KNN) and linear discriminant analysis (LDA). Moreover, various standard drift related experiments are conducted, of which the results validate our proposed algorithm’s superior robustness for the wide range of real-life applications.