Active instance selection for drift calibration of an electronic nose

Abstract An electronic nose (E-nose) system is regularly composed of a gas sensor array and certain pattern-recognition algorithms. With the use of E-nose, the gas sensors inevitably undergo physical changes, which causes gas-sensor drift to invalid algorithm models of E-noses. In this study, we intend to explore a suitable approach for online E-nose drift calibration. Considering drift calibration samples cannot be obtained directly during continuous odor detection, we have adopted Active Learning (AL) paradigm to select calibration samples from previous tested samples and provide their categories by querying. Further, we deal with the class imbalance problem of drift calibration set caused by traditional AL instance-selection strategy. We propose a new strategy named Dual-Rule Sampling (DRS) to simultaneously measure sample uncertainty and minority-class similarity. The high uncertain instances being close to minority-class are selected for drift calibration when class imbalance occurs. We have used two datasets to evaluate the performance of DRS. The experimental results show that DRS reaches the highest recognition score among all the tested methodologies by emphasizing the minority-class recognition improvement. We can conclude that DRS successfully implements online E-nose drift calibration in continuous odor detection.

[1]  Lei Zhang,et al.  On-line sensor calibration transfer among electronic nose instruments for monitoring volatile organic chemicals in indoor air quality , 2011 .

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

[3]  Tao Liu,et al.  Gas-Sensor Drift Counteraction with Adaptive Active Learning for an Electronic Nose , 2018, Sensors.

[4]  David Zhang,et al.  Calibration transfer and drift compensation of e-noses via coupled task learning , 2016 .

[5]  Qin Wang,et al.  A high precise E-nose for daily indoor air quality monitoring in living environment , 2017, Integr..

[6]  Udo Weimar,et al.  On-line novelty detection by recursive dynamic principal component analysis and gas sensor arrays under drift conditions , 2006 .

[7]  M. Sjöström,et al.  Drift correction for gas sensors using multivariate methods , 2000 .

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

[9]  Jianhua Cao,et al.  Active Learning on Dynamic Clustering for Drift Compensation in an Electronic Nose System , 2019, Sensors.

[10]  J. Gardner,et al.  An electronic nose system to diagnose illness , 2000 .

[11]  Lei Zhang,et al.  Anti-drift in E-nose: A subspace projection approach with drift reduction , 2017 .

[12]  Tomasz Dymerski,et al.  Electronic noses in classification and quality control of edible oils: A review. , 2018, Food chemistry.

[13]  Ingemar Lundström,et al.  Classification of complex gas mixtures from automotive leather using an electronic nose , 2000 .

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

[15]  Xizhao Wang,et al.  Impact of fuzziness categorization on divide and conquer strategy for instance selection , 2017, J. Intell. Fuzzy Syst..

[16]  Tomasz Dymerski,et al.  Electronic Noses in Medical Diagnostics. , 2019, Current medicinal chemistry.

[17]  Alexander Vergara,et al.  Cooperative classifiers for reconfigurable sensor arrays , 2014 .

[18]  Miguel Peris,et al.  Electronic noses and tongues to assess food authenticity and adulteration , 2016 .

[19]  Wenhua Xu,et al.  Active learning over evolving data streams using paired ensemble framework , 2016, 2016 Eighth International Conference on Advanced Computational Intelligence (ICACI).

[20]  Alexander Vergara,et al.  Algorithmic mitigation of sensor failure: is sensor replacement really necessary? , 2013 .

[21]  David Zhang,et al.  Correcting Instrumental Variation and Time-Varying Drift: A Transfer Learning Approach With Autoencoders , 2016, IEEE Transactions on Instrumentation and Measurement.

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

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

[24]  Oliver Tomic,et al.  Independent component analysis applied on gas sensor array measurement data , 2003 .

[25]  Wenyong Wang,et al.  An efficient instance selection algorithm to reconstruct training set for support vector machine , 2017, Knowl. Based Syst..

[26]  Xizhao Wang,et al.  Voting-based instance selection from large data sets with MapReduce and random weight networks , 2016, Inf. Sci..

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

[28]  Giulia Sedda,et al.  The Electronic Nose’s Emerging Role in Respiratory Medicine , 2018, Sensors.

[29]  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.

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