A Research of Gas Open-Set Identification Based on Data Augmentation Algorithm

Abstract

Significant progress has been made in convolutional neural networks (CNN) based gas recognition. However, existing electronic nose (e-Nose) algorithms all use the closed-set assumption that the test and training samples are in the same label space and can only detect objects of known classes. However, in realistic scenarios, collecting data and training for every possible gas would waste much resource. Open-set identification aims to actively reject samples from unknown classes by reducing the intra-class spacing and, thus, not misclassifying them as known classes. In this study, we propose a data preprocessing method to enhance the performance of closed-set recognition by augmenting the eigenvalues of each gas. We then implement the open-set recognition task for gases using an open-set recognition model. These methods contribute to improved recognition accuracy for gases and provide an effective means of handling unknown class samples. Experimental results show that our approach can identify unknown samples well while maintaining accuracy for available classes.