Gas-Sensor Drift Counteraction with Adaptive Active Learning for an Electronic Nose

Gas sensors are the key components of an electronic nose (E-nose) in violated odour analysis. Gas-sensor drift is a kind of physical change on a sensor surface once an E-nose works. The perturbation of gas-sensor responses caused by drift would deteriorate the performance of the E-nose system over time. In this study, we intend to explore a suitable approach to deal with the drift effect in an online situation. Considering that the conventional drift calibration is difficult to implement online, we use active learning (AL) to provide reliable labels for online instances. Common AL learning methods tend to select and label instances with low confidence or massive information. Although this action clarifies the ambiguity near the classification boundary, it is inadequate under the influence of gas-sensor drift. We still need the samples away from the classification plane to represent drift variations comprehensively in the entire data space. Thus, a novel drift counteraction method named AL on adaptive confidence rule (AL-ACR) is proposed to deal with online drift data dynamically. By contrast with conventional AL methods selecting instances near the classification boundary of a certain category, AL-ACR collects instances distributed evenly in different categories. This action implements on an adjustable rule according to the outputs of classifiers. Compared with other reference methods, we adopt two drift databases of E-noses to evaluate the performance of the proposed method. The experimental results indicate that the AL-ACR reaches higher accuracy than references on two E-nose databases, respectively. Furthermore, the impact of the labelling number is discussed to show the trend of performance for the AL-type methods. Additionally, we define the labelling efficiency index (LEI) to assess the contribution of certain labelling numerically. According to the results of LEI, we believe AL-ACR can achieve the best effect with the lowest cost among the AL-type methods in this work.

[1]  Shankar Vembu,et al.  Chemical gas sensor drift compensation using classifier ensembles , 2012 .

[2]  Maryam Siadat,et al.  Orthogonal Signal Correction to Improve Stability Regression Model in Gas Sensor Systems , 2017, J. Sensors.

[3]  Hang Liu,et al.  Metal Oxide Gas Sensor Drift Compensation Using a Two-Dimensional Classifier Ensemble , 2015, Sensors.

[4]  Hang Zhang,et al.  Online Active Learning Ensemble Framework for Drifted Data Streams , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Fengchun Tian,et al.  Neural Network Ensembles for Online Gas Concentration Estimation Using an Electronic Nose , 2013 .

[6]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[7]  Xiang Wang,et al.  Performance Analysis of ICA in Sensor Array , 2016, Sensors.

[8]  Pere Caminal,et al.  Common principal component analysis for drift compensation of gas sensor array data , 2009 .

[9]  H. Sebastian Seung,et al.  Query by committee , 1992, COLT '92.

[10]  Tao Liu,et al.  An Active Feature Selection Strategy for DWT in Artificial Taste , 2018, J. Sensors.

[11]  Selena Sironi,et al.  Electronic Nose Testing Procedure for the Definition of Minimum Performance Requirements for Environmental Odor Monitoring , 2016, Sensors.

[12]  Shuzhi Sam Ge,et al.  Drift Compensation for Electronic Nose by Semi-Supervised Domain Adaption , 2014, IEEE Sensors Journal.

[13]  Pietro Siciliano,et al.  Odor discrimination using adaptive resonance theory , 2000 .

[14]  H. Sebastian Seung,et al.  Selective Sampling Using the Query by Committee Algorithm , 1997, Machine Learning.

[15]  Pere Caminal,et al.  Drift Compensation of Gas Sensor Array Data by Common Principal Component Analysis , 2010 .

[16]  A. Perera,et al.  On-line novelty detection by recursive dynamic principal component analysis and gas sensor arrays under drift conditions , 2003, IEEE Sensors Journal.

[17]  Hao Wu,et al.  Authenticity Tracing of Apples According to Variety and Geographical Origin Based on Electronic Nose and Electronic Tongue , 2018, Food Analytical Methods.

[18]  Isabelle Guyon,et al.  Design and analysis of the WCCI 2010 active learning challenge , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[19]  Liu Yang,et al.  Advances in Active Learning Algorithms Based on Sampling Strategy , 2012 .

[20]  Julian W. Gardner,et al.  A brief history of electronic noses , 1994 .

[21]  Shruti Asmita,et al.  A Regularized Ensemble of Classifiers for Sensor Drift Compensation , 2016, IEEE Sensors Journal.

[22]  Sabina Licen,et al.  Odor control map: Self organizing map built from electronic nose signals and integrated by different instrumental and sensorial data to obtain an assessment tool for real environmental scenarios , 2018, Sensors and Actuators B: Chemical.

[23]  B. Kremer,et al.  Training and Validating a Portable Electronic Nose for Lung Cancer Screening , 2018, Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer.

[24]  Eduard Llobet,et al.  Fuzzy ARTMAP based electronic nose data analysis , 1999 .

[25]  Bin Deng,et al.  A novel electronic nose learning technique based on active learning: EQBC-RBFNN , 2017 .

[26]  Cosimo Distante,et al.  Drift counteraction with multiple self-organising maps for an electronic nose , 2004 .

[27]  Andrew McCallum,et al.  Employing EM and Pool-Based Active Learning for Text Classification , 1998, ICML.

[28]  Luca Francioso,et al.  Influence of electrodes ageing on the properties of the gas sensors based on SnO2 , 2006 .

[29]  Raffaele Di Fuccio,et al.  An adaptive classification model based on the Artificial Immune System for chemical sensor drift mitigation , 2013 .

[30]  Manuel Pineda-Sánchez,et al.  SENose: An under U$50 electronic nose for the monitoring of soil gas emissions , 2017, Comput. Electron. Agric..