Online Sensor Drift Compensation for E-Nose Systems Using Domain Adaptation and Extreme Learning Machine

Sensor drift is a common issue in E-Nose systems and various drift compensation methods have received fruitful results in recent years. Although the accuracy for recognizing diverse gases under drift conditions has been largely enhanced, few of these methods considered online processing scenarios. In this paper, we focus on building online drift compensation model by transforming two domain adaptation based methods into their online learning versions, which allow the recognition models to adapt to the changes of sensor responses in a time-efficient manner without losing the high accuracy. Experimental results using three different settings confirm that the proposed methods save large processing time when compared with their offline versions, and outperform other drift compensation methods in recognition accuracy.

[1]  José Chilo,et al.  E-nose application to food industry production , 2016, IEEE Instrumentation & Measurement Magazine.

[2]  George Mois,et al.  A Low-Power Wireless Sensor for Online Ambient Monitoring , 2015, IEEE Sensors Journal.

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

[4]  P. T. Moseley,et al.  Materials selection for semiconductor gas sensors , 1992 .

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

[6]  Narasimhan Sundararajan,et al.  On-Line Sequential Extreme Learning Machine , 2005, Computational Intelligence.

[7]  Maarten Merkx,et al.  An Optical Sensor Based on a Photonic Polymer Film to Detect Calcium in Serum , 2016 .

[8]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[9]  Feng Lu,et al.  Sensor Fault Diagnosis for Aero Engine Based on Online Sequential Extreme Learning Machine with Memory Principle , 2017 .

[10]  M. Holmberg,et al.  Drift Compensation, Standards, and Calibration Methods , 2004 .

[11]  Shiliang Sun,et al.  A survey of multi-source domain adaptation , 2015, Inf. Fusion.

[12]  Xuegang Hu,et al.  Domain adaptation via Multi-Layer Transfer Learning , 2016, Neurocomputing.

[13]  Lijuan Wang,et al.  Online Sensor Fault Detection Based on an Improved Strong Tracking Filter , 2015, Sensors.

[14]  Patrick Thiran,et al.  Back To The Source: An Online Approach for Sensor Placement and Source Localization , 2017, WWW.

[15]  Qiong Luo,et al.  Online Mining in Sensor Networks , 2004, NPC.

[16]  Hang Liu,et al.  Metal Oxide Gas Sensor Drift Compensation Using a Dynamic Classifier Ensemble Based on Fitting , 2013, Sensors.

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

[18]  Jian-Wei Gong,et al.  Temperature feedback control for improving the stability of a semiconductor-metal-oxide (SMO) gas sensor , 2006, IEEE Sensors Journal.

[19]  William J. Welch,et al.  Computer-aided design of experiments , 1981 .

[20]  Jessica E Fitzgerald,et al.  Artificial Nose Technology: Status and Prospects in Diagnostics. , 2017, Trends in biotechnology.

[21]  Gabriela Csurka,et al.  Domain Adaptation for Visual Applications: A Comprehensive Survey , 2017, ArXiv.

[22]  Rama Chellappa,et al.  Visual Domain Adaptation: A survey of recent advances , 2015, IEEE Signal Processing Magazine.

[23]  V. Ghafarinia,et al.  Online Gas Diagnosis by a Capillary-attached Gas Sensor Coupled to a Pattern Recognition System , 2006, 2006 5th IEEE Conference on Sensors.

[24]  Octavian Buiu,et al.  Materials selection for gas sensing. An HSAB perspective , 2014, 2014 International Semiconductor Conference (CAS).

[25]  Lars Bungum,et al.  A Survey of Domain Adaptation in Machine Translation Towards a refinement of domain space , 2011 .

[26]  Moses O. Tadé,et al.  A Modified Kennard-Stone Algorithm for Optimal Division of Data for Developing Artificial Neural Network Models , 2012 .

[27]  Jordi Fonollosa,et al.  Chemical gas sensor array dataset , 2015, Data in brief.

[28]  Ann Gordon-Ross,et al.  Online algorithms for wireless sensor networks dynamic optimization , 2012, 2012 IEEE Consumer Communications and Networking Conference (CCNC).

[29]  Bartosz Szulczynski,et al.  Determination of Odour Interactions of Three-Component Gas Mixtures Using an Electronic Nose , 2017, Sensors.

[30]  Changjing Shang,et al.  USING MACHINE LEARNING TECHNIQUES , 2011 .

[31]  Matteo Falasconi,et al.  Metal Oxide Gas Sensors, a Survey of Selectivity Issues Addressed at the SENSOR Lab, Brescia (Italy) , 2017, Sensors.

[32]  Rajib Bandyopadhyay,et al.  Application of electronic nose for industrial odors and gaseous emissions measurement and monitoring--An overview. , 2015, Talanta.

[33]  C. D. Meyer,et al.  Generalized inverses of linear transformations , 1979 .

[34]  Alexander Vergara,et al.  On the calibration of sensor arrays for pattern recognition using the minimal number of experiments , 2014 .

[35]  A. Walmsley,et al.  Methodology for the selection of suitable sensors for incorporation into a gas sensor array , 1991 .

[36]  Nirvana Meratnia,et al.  Distributed online outlier detection in wireless sensor networks using ellipsoidal support vector machine , 2013, Ad Hoc Networks.

[37]  Marina Rumyantseva,et al.  Nanocrystalline BaSnO3 as an Alternative Gas Sensor Material: Surface Reactivity and High Sensitivity to SO2 , 2015, Materials.

[38]  Valérie Renaudin,et al.  Motion Mode Recognition and Step Detection Algorithms for Mobile Phone Users , 2013, Sensors.

[39]  A. Hierlemann,et al.  Higher-order Chemical Sensing , 2007 .

[40]  Karl Aberer,et al.  Online unsupervised state recognition in sensor data , 2015, 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[41]  Billur Barshan,et al.  Detecting Falls with Wearable Sensors Using Machine Learning Techniques , 2014, Sensors.

[42]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[43]  Guang-Bin Huang,et al.  Trends in extreme learning machines: A review , 2015, Neural Networks.

[44]  Subhasis Chaudhuri,et al.  Optimal selection of SAW sensors for E-Nose applications , 2015 .

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

[46]  David Zhang,et al.  Domain Adaptation Extreme Learning Machines for Drift Compensation in E-Nose Systems , 2015, IEEE Transactions on Instrumentation and Measurement.

[47]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[48]  Christian Haubelt,et al.  Sensor-based online hand gesture recognition on multi-core DSPs , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[49]  Alexandre Perera,et al.  Drift compensation of gas sensor array data by Orthogonal Signal Correction , 2010 .

[50]  Angelo M. Sabatini,et al.  A Machine Learning Framework for Gait Classification Using Inertial Sensors: Application to Elderly, Post-Stroke and Huntington’s Disease Patients , 2016, Sensors.

[51]  Yew-Soon Ong,et al.  A Fast Reduced Kernel Extreme Learning Machine , 2016, Neural Networks.

[52]  Eduard Llobet,et al.  On-line drift counteraction for metal oxide gas sensor arrays , 2003 .

[53]  S. Giannoukos,et al.  Advances in chemical sensing technologies for VOCs in breath for security/threat assessment, illicit drug detection, and human trafficking activity , 2018, Journal of breath research.

[54]  Nicolae Barsan,et al.  Influence of Conduction Mechanism Changes on the Sensor Performance of SMOX Based Gas Sensors , 2014 .