M²FL-CCC: Multibranch Multilayer Feature Leaning and Comprehensive Classification Criterion for Gas Sensor Drift Compensation

Abstract

Gas sensor drift, which has the characteristics of randomness and nonlinearity, is an inevitable problem in electronic nose (E-nose) systems. In this study, a domain-adaptive deep neural network (DNN) framework, called M <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> FL-CCC, is proposed to suppress sensor drift and improve E-nose performance. This framework mainly contains two key parts: multibranch multilayer feature learning (M <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> FL) and a comprehensive classification criterion (CCC). In terms of the network structure, a multibranch multilayer structure is designed for customized and joint sensor feature extraction. To fuse the full features of different levels in the network, a joint training strategy is leveraged for multilayer classifiers. Regarding the classification strategy design, a CCC is proposed to fuse the prediction results of the base classifiers and the separation degree between a specific target sample and the source samples. In addition, to optimize the training process, we adopt an improved additional margin softmax classifier with nonlinear dynamic parameter adjustment. Experiments are conducted on public E-nose drift data, and the results show that the M <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> FL-CCC framework is superior to other compared methods.