Quantitative analysis of multiple kinds of volatile organic compounds using hierarchical models with an electronic nose

Abstract This paper studies hierarchical discrimination and quantification models in order to simultaneously quantify multiple kinds of odors with an improved electronic nose. Such tasks are first regard as multiple discrimination tasks and then as multiple quantification tasks, and implemented by the hierarchical models with the divide-and-conquer strategy. The discrimination models are the common classifiers, including nearest neighbor classifiers, local Euclidean distance templates, local Mahalanobis distance templates, multi-layer perceptrons (MLPs), support vector machines (SVMs) with Gaussian or polynomial kernels. Similarly, the quantification models are multivariate linear regressions, partial least squares regressions, multivariate quadratic regressions, MLPs, SVMs. We developed several types of hierarchical model and compared their capabilities for quantifying 12 kinds of volatile organic compounds with the improved electronic nose. The experimental results show that the hierarchical model composed of multiple single-output MLPs followed by multiple single-output MLPs with local decomposition, virtual balance and local generalization techniques, has advantages over the others in the aspects of time complexity, structure complexity and generalization performance.

[1]  Thomas G. Dietterich,et al.  Structured machine learning: the next ten years , 2008, Machine Learning.

[2]  Carles Cané,et al.  Chemical warfare agents simulants detection with an optimized SAW sensor array , 2011 .

[3]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[4]  Gao Daqi,et al.  Modular neural networks for estimating odor concentrations , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[5]  Danilo De Rossi,et al.  Characterisation of olive oil by an electronic nose based on conducting polymer sensors , 2000 .

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

[7]  Laszlo B. Kish,et al.  Fluctuation-enhanced sensing of bacterium odors , 2009 .

[8]  Suranjan Panigrahi,et al.  Neural-network-integrated electronic nose system for identification of spoiled beef , 2006 .

[9]  N. Ancona,et al.  Support vector machines for olfactory signals recognition , 2003 .

[10]  J. A. Ragazzo‐Sánchez,et al.  Identification of different alcoholic beverages by electronic nose coupled to GC , 2008 .

[11]  Naresh Magan,et al.  Potential of an electronic nose for the early detection and differentiation between Streptomyces in potable water , 2006 .

[12]  Bipan Tudu,et al.  Electronic nose for black tea quality evaluation by an incremental RBF network , 2009 .

[13]  Eduard Llobet,et al.  An electronic nose system based on a micro-machined gas sensor array to assess the freshness of sardines , 2009 .

[14]  G. Horner,et al.  Gas analysis by partial model building , 1990 .

[15]  Li Chunxia,et al.  Task decomposition and modular single-hidden-layer perceptron classifiers for multi-class learning problems , 2007, Pattern Recognit..

[16]  M. Santonico,et al.  Olfactory systems for medical applications , 2008 .

[17]  Gao Daqi,et al.  Simultaneous estimation of odor classes and concentrations using an electronic nose with function approximation model ensembles , 2007 .

[18]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[19]  Taher Alizadeh,et al.  Electronic nose based on the polymer coated SAW sensors array for the warfare agent simulants classification , 2008 .

[20]  Manuel A. Duarte-Mermoud,et al.  Chilean Wine Classification Using Volatile Organic Compounds Data Obtained With a Fast GC Analyzer , 2008, IEEE Transactions on Instrumentation and Measurement.

[21]  T. Nakamoto,et al.  Perfume and flavor identification by odor sensing system using quartz-resonator sensor array and neural-network pattern recognition , 1991, TRANSDUCERS '91: 1991 International Conference on Solid-State Sensors and Actuators. Digest of Technical Papers.

[22]  Przemyslaw M. Szecowka,et al.  Application of sensor array and neural networks for quantification of organic solvent vapours in air , 1999 .

[23]  O. Lind,et al.  Detection of mastitic milk using a gas-sensor array system (electronic nose) , 2005 .

[24]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[25]  T. Sundic,et al.  Fuzzy inference system for sensor array calibration: prediction of CO and CH4 levels in variable humidity conditions , 2002 .

[26]  J. Brezmes,et al.  Qualitative and quantitative analysis of volatile organic compounds using transient and steady-state responses of a thick-film tin oxide gas sensor array , 1997 .

[27]  Robert G. Dambergs,et al.  Two-dimensional correlation analysis of the effect of temperature on the fingerprint of wines analysed by mass spectrometry electronic nose , 2010 .

[28]  Naresh Magan,et al.  Table olives volatile fingerprints: Potential of an electronic nose for quality discrimination. , 2008 .

[29]  Udo Weimar,et al.  Odours and flavours identified with hybrid modular sensor systems1 , 1997 .

[30]  Eduard Llobet,et al.  Selective methane detection under varying moisture conditions using static and dynamic sensor signals , 1999 .

[31]  Selena Sironi,et al.  Electronic noses for the continuous monitoring of odours from a wastewater treatment plant at specific receptors: Focus on training methods , 2008 .

[32]  David G. Stork,et al.  Pattern Classification , 1973 .

[33]  Martin Sommer,et al.  Assessment of meat freshness with metal oxide sensor microarray electronic nose: A practical approach , 2010 .

[34]  B. Kowalski,et al.  Partial least-squares regression: a tutorial , 1986 .

[35]  K. Persaud,et al.  Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose , 1982, Nature.

[36]  Petra Reinhold,et al.  Electronic nose responses and acute phase proteins correlate in blood using a bovine model of respiratory infection , 2010 .

[37]  T. Nakamoto,et al.  Perfume and flavour identification by odour-sensing system using quartz-resonator sensor array and neural-network pattern recognition☆ , 1993 .

[38]  J W Gardner and P N Bartlett,et al.  Electronic Noses: Principles and Applications , 1999 .

[39]  Daniel Rodriguez,et al.  Performance of an e-nose in hops classification , 2004 .

[40]  Changying Li,et al.  Neural network and Bayesian network fusion models to fuse electronic nose and surface acoustic wave sensor data for apple defect detection , 2007 .