Continuous chemical classification in uncontrolled environments with sliding windows

Abstract Electronic noses are sensing devices that are able to classify chemical volatiles according to the readings of an array of non-selective gas sensors and some pattern recognition algorithm. Given their high versatility to host multiple sensors while still being compact and lightweight, e-noses have demonstrated to be a promising technology to real-world chemical recognition, which is our main concern in this work. Under these scenarios, classification is usually carried out on sub-sequences of the main e-nose data stream after a segmentation phase which objective is to exploit the temporal correlation of the e-nose's data. In this work we analyze to which extent considering segments of delayed samples by means of fixed-length sliding windows improves the classification accuracy. Extensive experimentation over a variety of experimental scenarios and gas sensor types, together with the analysis of the classification accuracy of three state-of-the-art classifiers, support our conclusions and findings. In particular, it has been found that fixed-length sliding windows attain better results than instantaneous sensor values for several classifier models, with a high statistical significance.

[1]  Tak-Chung Fu,et al.  A review on time series data mining , 2011, Eng. Appl. Artif. Intell..

[2]  Vittorio Dell'Orto,et al.  Potential Application of Electronic Olfaction Systems in Feedstuffs Analysis and Animal Nutrition , 2013, Sensors.

[3]  M. Salvato,et al.  Dynamic multivariate regression for on-field calibration of high speed air quality chemical multi-sensor systems , 2015, 2015 XVIII AISEM Annual Conference.

[4]  A Gelperin,et al.  Nanotube-based sensor arrays for clinical breath analysis , 2008, Journal of breath research.

[5]  John E. Hummel.  Object Recognition , 2014, Computer Vision, A Reference Guide.

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

[7]  David Zhang,et al.  A Novel Breath Analysis System Based on Electronic Olfaction , 2010, IEEE Transactions on Biomedical Engineering.

[8]  Nikolai F. Rulkov,et al.  On the performance of gas sensor arrays in open sampling systems using Inhibitory Support Vector Machines , 2013 .

[9]  Eamonn J. Keogh,et al.  Time Series Classification under More Realistic Assumptions , 2013, SDM.

[10]  Silvia Coradeschi,et al.  Odour classification system for continuous monitoring applications , 2009 .

[11]  Sadique Sheik,et al.  Reservoir computing compensates slow response of chemosensor arrays exposed to fast varying gas concentrations in continuous monitoring , 2015 .

[12]  Javier Gonzalez-Jimenez,et al.  Probabilistic gas quantification with MOX sensors in Open Sampling Systems—A Gaussian Process approach , 2013 .

[13]  E. Schaller,et al.  ‘Electronic Noses’ and Their Application to Food , 1998 .

[14]  Bartosz Krawczyk,et al.  VOCs classification based on the committee of classifiers coupled with single sensor signals , 2013 .

[15]  Doron Lancet,et al.  A feature extraction method for chemical sensors in electronic noses , 2003 .

[16]  Eros Comunello,et al.  Classification of Images Acquired with Colposcopy Using Artificial Neural Networks , 2014, Cancer Informatics.

[17]  Vit Niennattrakul,et al.  Shape-based template matching for time series data , 2012, Knowl. Based Syst..

[18]  Javier Gonzalez-Jimenez,et al.  Real-Time odor classification through sequential bayesian filtering , 2015 .

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

[20]  Jonathan R. M. Hosking,et al.  Partitioning Nominal Attributes in Decision Trees , 1999, Data Mining and Knowledge Discovery.

[21]  Juan Miguel Ortiz-de-Lazcano-Lobato,et al.  Automatic Model Selection by Cross-Validation for Probabilistic PCA , 2009, Neural Processing Letters.

[22]  Javier Gonzalez Monroy,et al.  Odor recognition in robotics applications by discriminative time-series modeling , 2015, Pattern Analysis and Applications.

[23]  Shukai Duan,et al.  Electronic Nose Feature Extraction Methods: A Review , 2015, Sensors.

[24]  Eduard Llobet,et al.  Wavelet transform and fuzzy ARTMAP-based pattern recognition for fast gas identification using a micro-hotplate gas sensor , 2002 .

[25]  Nir Friedman,et al.  Bayesian Network Classifiers , 1997, Machine Learning.

[26]  Byeong Ho Kang,et al.  Investigation and improvement of multi-layer perception neural networks for credit scoring , 2015, Expert Syst. Appl..

[27]  Annette M. Molinaro,et al.  Prediction error estimation: a comparison of resampling methods , 2005, Bioinform..

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

[29]  Silvia Coradeschi,et al.  Object recognition: A new application for smelling robots , 2005, Robotics Auton. Syst..

[30]  Matteo Della Torre,et al.  Development of an Electronic Nose for Environmental Odour Monitoring , 2012, Sensors.

[31]  M MolinaroAnnette,et al.  Prediction error estimation , 2005 .

[32]  Qinyu. Zhu.  Extreme Learning Machine , 2013 .

[33]  Jiongqi Wang,et al.  An Improved Detection Statistic for Monitoring the Nonstationary and Nonlinear Processes , 2015 .

[34]  Ramón Huerta,et al.  Chemical Discrimination in Turbulent Gas Mixtures with MOX Sensors Validated by Gas Chromatography-Mass Spectrometry , 2014, Sensors.

[35]  J. Friedman,et al.  Classification and Regression Trees (Wadsworth Statistics/Probability) , 1984 .

[36]  Camelia Chira,et al.  Classifiers with a reject option for early time-series classification , 2013, 2013 IEEE Symposium on Computational Intelligence and Ensemble Learning (CIEL).

[37]  S. D. Vito,et al.  CO, NO2 and NOx urban pollution monitoring with on-field calibrated electronic nose by automatic bayesian regularization , 2009 .