A Novel Semi-Supervised Electronic Nose Learning Technique: M-Training

When an electronic nose (E-nose) is used to distinguish different kinds of gases, the label information of the target gas could be lost due to some fault of the operators or some other reason, although this is not expected. Another fact is that the cost of getting the labeled samples is usually higher than for unlabeled ones. In most cases, the classification accuracy of an E-nose trained using labeled samples is higher than that of the E-nose trained by unlabeled ones, so gases without label information should not be used to train an E-nose, however, this wastes resources and can even delay the progress of research. In this work a novel multi-class semi-supervised learning technique called M-training is proposed to train E-noses with both labeled and unlabeled samples. We employ M-training to train the E-nose which is used to distinguish three indoor pollutant gases (benzene, toluene and formaldehyde). Data processing results prove that the classification accuracy of E-nose trained by semi-supervised techniques (tri-training and M-training) is higher than that of an E-nose trained only with labeled samples, and the performance of M-training is better than that of tri-training because more base classifiers can be employed by M-training.

[1]  Rajeshuni Ramesham,et al.  Electronic nose for space program applications. , 2003, Sensors and actuators. B, Chemical.

[2]  Patrycja Ciosek,et al.  The analysis of sensor array data with various pattern recognition techniques , 2006 .

[3]  L. Zeller,et al.  Implementation of an electronic nose for continuous odour monitoring in a poultry shed , 2008 .

[4]  Ganesh Kumar Mani,et al.  Electronic noses for food quality : a review , 2015 .

[5]  Sihao Zheng,et al.  Geoherbalism evaluation of Radix Angelica sinensis based on electronic nose. , 2015, Journal of pharmaceutical and biomedical analysis.

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

[7]  Yan Zhou,et al.  Enhancing Supervised Learning with Unlabeled Data , 2000, ICML.

[8]  Michael R. Lyu,et al.  Multi-task Learning for one-class classification , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[9]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[10]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[11]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[12]  S. De Vito,et al.  Semi-Supervised Learning Techniques in Artificial Olfaction: A Novel Approach to Classification Problems and Drift Counteraction , 2012, IEEE Sensors Journal.

[13]  Matthias Seeger,et al.  Learning from Labeled and Unlabeled Data , 2010, Encyclopedia of Machine Learning.

[14]  Shukai Duan,et al.  An Enhanced Quantum-Behaved Particle Swarm Optimization Based on a Novel Computing Way of Local Attractor , 2015, Inf..

[15]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[16]  M. Tenenhaus,et al.  Prediction of clinical outcome with microarray data: a partial least squares discriminant analysis (PLS-DA) approach , 2003, Human Genetics.

[17]  M. Santonico,et al.  Detection and identification of cancers by the electronic nose. , 2012, Expert opinion on medical diagnostics.

[18]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[19]  E. Gobbi,et al.  Rapid diagnosis of Enterobacteriaceae in vegetable soups by a metal oxide sensor based electronic nose , 2015 .

[20]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[21]  Xiaojin Zhu,et al.  --1 CONTENTS , 2006 .

[22]  Jing Zhang,et al.  Impedance sensing and molecular modeling of an olfactory biosensor based on chemosensory proteins of honeybee. , 2013, Biosensors & bioelectronics.

[23]  Xin Yin,et al.  A novel classifier ensemble for recognition of multiple indoor air contaminants by an electronic nose , 2014 .

[24]  S. Adeloju,et al.  Polypyrrole-based electronic noses for environmental and industrial analysis , 2005 .

[25]  Xiaojin Zhu,et al.  Semi-Supervised Learning , 2010, Encyclopedia of Machine Learning.

[26]  Lei Zhang,et al.  Standardization of metal oxide sensor array using artificial neural networks through experimental design , 2013 .

[27]  Hui Guohua,et al.  Study of grass carp (Ctenopharyngodon idellus) quality predictive model based on electronic nose , 2012 .

[28]  Deborah H Yates,et al.  A breath test for malignant mesothelioma using an electronic nose , 2011, European Respiratory Journal.

[29]  Alexander Zien,et al.  Semi-Supervised Learning , 2006 .

[30]  Frank Stam,et al.  Packaging effects of a novel explosion-proof gas sensor , 2003 .

[31]  Michael R. Lyu,et al.  Efficient online learning for multitask feature selection , 2013, TKDD.

[32]  Shu Fan,et al.  Feature extraction of wound infection data for electronic nose based on a novel weighted KPCA , 2014 .

[33]  Greg Schohn,et al.  Less is More: Active Learning with Support Vector Machines , 2000, ICML.

[34]  Chee Kheong Siew,et al.  Extreme learning machine: RBF network case , 2004, ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004..

[35]  Jun Wang,et al.  Quality grade identification of green tea using the eigenvalues of PCA based on the E-nose signals , 2009 .

[36]  Daniel Cicerone,et al.  The use of an electronic nose to characterize emissions from a highly polluted river , 2008 .

[37]  Shukai Duan,et al.  A Novel Feature Extraction Approach Using Window Function Capturing and QPSO-SVM for Enhancing Electronic Nose Performance , 2015, Sensors.

[38]  Zhi-Hua Zhou,et al.  Semi-supervised learning by disagreement , 2010, Knowledge and Information Systems.

[39]  Zhi-Hua Zhou,et al.  Tri-training: exploiting unlabeled data using three classifiers , 2005, IEEE Transactions on Knowledge and Data Engineering.