A Drift-Compensating Novel Deep Belief Classification Network to Improve Gas Recognition of Electronic Noses

Abstract

Electronic nose (E-nose) systems have a good effect on the identification of distinct odours. However, the properties of chemical gas sensors indicate that ageing, poisoning, fluctuation of environmental conditions (moisture, temperature, etc.) and a lack of fabrication repeatability, etc. have a large impact on the sensitivity and accuracy of sensors, which leads to sensor data drift. Although previous studies have indicated the feasibility and validity of deep learning in drift compensation of gas sensor data, the actual performances of these deep learning models are less impressive compared with some existing methods. Thus, we intend to further explore a novel deep learning model for drift compensation for E-noses. In this paper, we investigate the drift compensation effect of E-nose data based on a deep belief network (DBN) and constructed a Gaussian deep belief classification network (GDBCN) model by cascading a Gaussian-Bernoulli restricted Boltzmann machines based DBN with a softmax classifier layer to compensate for sensor drift at the decision level. The merits of our method are as follows: 1) it is a unified classification model for drift auto-compensation at the decision level rather than a feature extractor; 2) it couples unsupervised and supervised techniques by modelling the intrinsic distribution of the data from different domains in an unsupervised manner and fine-tunes the model parameters by leveraging the label information of the source domain; 3) the supervised fine-tuning process for the coupled GDBCN model fits well with the nature of the supervised task and guarantees that the parameters of the DBN will be useful for classification; 4) the GDBCN model is a classification model and thus automatically compensates for drift without manually setting specific model rules for domain alignment before classification. Experimental results on real sensor datasets demonstrate the effectiveness and superiority compared with several existing control methods.

Breath VOC analysis and machine learning approaches for disease screening: a review

“…Recurrent neural network (RNN), which is most commonly used in the domain of natural language processing, was utilized by Zou et al [167] on a real-life sensor drift dataset and performed several experiments. In another study by Yutong Tian et al, a deep belief network (DBN), a generative graphical model, was utilized for drift compensation [168].…”

Review–Modern Data Analysis in Gas Sensors

“…128 A multi-dimensional CNN ensembling technique was adopted by Chaudhri et al 129 which outperformed simpler classifiers such as SVM providing a robust classification for drifted gas sensors. A decision level drift compensation scheme was proposed by Tian et al 130 where a unified classification model was implemented incorporating a Gaussian deep belief classification network.…”

Multi-Classifier Tree With Transient Features for Drift Compensation in Electronic Nose

“…Some recent ML approaches presented in the scientific literature for drift compensation are mainly based on subspace learning/domain transformations [22]- [24], deep neural networks [25], transfer learning [26], feature selection [27] and semi-supervised learning [16], [28]. Almost all the ML methods presented in literature are able to handle the sensors drift to some extent but still there exists a room for improving the accuracy of these models.…”