Simultaneous Classification and Concentration Estimation for Electronic Nose

By virtue of the electronic nose (E-nose), detection and estimation of gases become feasible in many fields without resorting to complicated specific instruments. Detection is generally casted as a classification problem and concentration estimation is subsequently performed using conventional statistical techniques. In this paper, we develop a polynomial-based optimization method to perform classification and estimation simultaneously to improve the intelligence of an E-nose. The proposed method employs a parametric polynomial with user-defined order to describe sensor characteristics. Classification and concentration estimation can then be formulated as a standard convex optimization problem. The convex optimization is solved either by a typical gradient descent method for an unconstrained case or a NLS trust-region method for a constrained case. The main advantages of the proposed method are the flexibility and significant reduced computation cost as well as simple implementation. Moreover, the global minimum of the optimization is readily achieved. Experimental data analysis demonstrates the efficiency of the proposed method

[1]  J. Goschnick,et al.  Air quality monitoring and fire detection with the Karlsruhe electronic micronose KAMINA , 2002 .

[2]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.

[3]  Zhi-Quan Luo,et al.  Convex optimization approach to identify fusion for multisensor target tracking , 2001, IEEE Trans. Syst. Man Cybern. Part A.

[4]  Julian W. Gardner,et al.  A brief history of electronic noses , 1994 .

[5]  Takahiro Hayashi,et al.  Feature extraction of multi-gas sensor responses using Genetic Algorithm , 2000 .

[6]  Julian W. Gardner,et al.  Electronic noses: a review of signal processing techniques , 1999 .

[7]  M. Pardo,et al.  Learning from data: a tutorial with emphasis on modern pattern recognition methods , 2002 .

[8]  M.A. Ryan,et al.  Monitoring Space Shuttle air quality using the Jet Propulsion Laboratory electronic nose , 2004, IEEE Sensors Journal.

[9]  Thomas F. Coleman,et al.  An Interior Trust Region Approach for Nonlinear Minimization Subject to Bounds , 1993, SIAM J. Optim..

[10]  Wei Yu,et al.  An introduction to convex optimization for communications and signal processing , 2006, IEEE Journal on Selected Areas in Communications.

[11]  H. Troy Nagle,et al.  Performance of the Levenberg–Marquardt neural network training method in electronic nose applications , 2005 .

[12]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[13]  M. C. Horrillo,et al.  Identification of typical wine aromas by means of an electronic nose , 2004, Proceedings of IEEE Sensors, 2004..

[14]  M. Pardo,et al.  Classification of electronic nose data with support vector machines , 2005 .

[15]  Manuel A. Sánchez-Montañés,et al.  Chemical Sensor Array Optimization: Geometric and Information Theoretic Approaches , 2002 .

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

[17]  Rafael Castro,et al.  An electronic nose for multimedia applications , 2003, IEEE Trans. Consumer Electron..

[18]  Daqi Gao,et al.  Simultaneous estimation of classes and concentrations of odors by an electronic nose using combinative and modular multilayer perceptrons , 2005 .

[19]  Matteo Pardo,et al.  Coffee analysis with an electronic nose , 2002, IEEE Trans. Instrum. Meas..

[20]  M. Pardo,et al.  Remarks on the use of multilayer perceptrons for the analysis of chemical sensor array data , 2004, IEEE Sensors Journal.

[21]  Hanying Zhou,et al.  Nonlinear Least-Squares Based Method for Identifying and Quantifying Single and Mixed Contaminants in Air with an Electronic Nose , 2005, Sensors (Basel, Switzerland).

[22]  Antonella Macagnano,et al.  Multicomponent analysis on polluted waters by means of an electronic tongue , 1997 .

[23]  Hubert B. Keller,et al.  Source localization by spatially distributed electronic noses for advection and diffusion , 2005, IEEE Transactions on Signal Processing.

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

[25]  Ricardo Gutierrez-Osuna,et al.  Pattern analysis for machine olfaction: a review , 2002 .

[26]  M. Lampton.  Damping-undamping strategies for the Levenberg-Marquardt nonlinear least-squares method , 1997 .

[27]  Keith R. Godfrey,et al.  System identification of electronic nose data from cyanobacteria experiments , 2002 .

[28]  E. Llobet,et al.  Evaluation of an electronic nose to assess fruit ripeness , 2005, IEEE Sensors Journal.

[29]  H. T. Nagle,et al.  Using neural networks and genetic algorithms to enhance performance in an electronic nose , 1999, IEEE Transactions on Biomedical Engineering.