A sensor array optimization method for electronic noses with sub-arrays

Sensor array configuration needs to be optimized in developing an application-specific instrument of electronic noses. Currently, sensor array optimization is commonly done by feature selection techniques. These methods could solve how to optimize a sensor array. However, they could not figure out what are the unique functions that each sensor plays in the optimized sensor array. The method proposed in this paper could solve this problem by sensor clustering and dividing the whole sample classification mission into several small recognition tasks. A measurement with a six Taguchi Gas Sensors (TGS sensor hereinafter) sensors array to classify 11 gas sorts was used in the data validation. The sensor array was optimized to three sensors with the proposed method. Each sensor in the optimized array had unique functions to solve different recognition tasks. TGS2600 had the unique functions to discriminate butanone and acetaldehyde. TGS2602 had the unique functions to discriminate benzene and cyclohexane, methanol and ethanol. TGS813 had the unique functions to discriminate cyclohexane and pentane. The combination of TGS2600 and TGS2602 had the unique functions to discriminate acetone and butanone, acetone and acetaldehyde. The proposed method might be a new generation of sensor array optimization methods.

[1]  C. Xie,et al.  An entire feature extraction method of metal oxide gas sensors , 2008 .

[2]  J. Brezmes,et al.  Coupling fast variable selection methods to neural network-based classifiers: Application to multisensor systems , 2006 .

[3]  Ralf Riedel,et al.  In situ and operando spectroscopy for assessing mechanisms of gas sensing. , 2007, Angewandte Chemie.

[4]  M. Ashby,et al.  The selection of sensors , 2001 .

[5]  J. Brezmes,et al.  Variable selection for support vector machine based multisensor systems , 2007 .

[6]  Evor L. Hines,et al.  Enhancing electronic nose performance by sensor selection using a new integer-based genetic algorithm approach , 2005 .

[7]  P. Travers,et al.  A method for selecting an optimum sensor array , 2000 .

[8]  G. Sberveglieri,et al.  Comparing the performance of different features in sensor arrays , 2007 .

[9]  R. Todeschini,et al.  A chemometric approach based on a novel similarity/diversity measure for the characterisation and selection of electronic nose sensors. , 2006, Analytica chimica acta.

[10]  Changsheng Xie,et al.  A Method of Feature Extraction From the Desorption Part of MOX's Response Curves to Gases , 2008, IEEE Sensors Journal.

[11]  Changsheng Xie,et al.  A reaction model of metal oxide gas sensors and a recognition method by pattern matching , 2009 .

[12]  Jens Scheidtmann,et al.  A combinatorial technique for the search of solid state gas sensor materials , 2004 .

[13]  Lalita Udpa,et al.  Artificial intelligence methods for selection of an optimized sensor array for identification of volatile organic compounds , 2001 .

[14]  J. Brezmes,et al.  Building parsimonious fuzzy ARTMAP models by variable selection with a cascaded genetic algorithm: application to multisensor systems for gas analysis , 2004 .