NIR spectroscopy with multivariate calibration and lock-in amplification to detect chemicals concealed behind fabrics

The detection of specific chemicals when concealed behind a layer of clothing is reported using near infrared (NIR) spectroscopy. Concealment modifies the spectrum of a particular chemical when recorded at stand-off ranges of three meters in a diffuse reflection experiment. The subsequent analysis to identify a particular chemical has involved employing calibration models such as principal component regression (PCR) and partial least squares regression (PLSR). Additionally, detection has been attempted with good results using neural networks. The latter technique serves to overcome nonlinearities in the calibration/training dataset, affording more robust modelling. Finally, lock-in amplification of spectral data collected in through-transmission arrangement has been shown to allow detection at SNR as low as -60dB. The work has been shown to both allow detection of specific chemicals concealed behind a single intervening layer of fabric material, and to estimate the concentration of certain liquids.

[1]  Paul J. Gemperline,et al.  Nonlinear multivariate calibration using principal components regression and artificial neural networks , 1991 .

[2]  Martin T. Hagan,et al.  Gauss-Newton approximation to Bayesian learning , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[3]  Art Springsteen.  Standards for the measurement of diffuse reflectance – an overview of available materials and measurement laboratories , 1999 .

[4]  Steven D. Brown,et al.  Nonlinear multivariate mapping of chemical data using feed-forward neural networks , 1993 .

[5]  A. Savitzky,et al.  Smoothing and Differentiation of Data by Simplified Least Squares Procedures. , 1964 .

[6]  Gerrit Kateman,et al.  Using artificial neural networks for solving chemical problems Part I. Multi-layer feed-forward networks , 1994 .

[7]  Lowell J. Burnett.  Liquid explosives detection , 1994, Other Conferences.

[8]  Albert Bos,et al.  Tutorial review—Data processing by neural networks in quantitative chemical analysis , 1993 .

[9]  Desire L. Massart,et al.  Variable selection for neural networks in multivariate calibration , 1998 .

[10]  Bruce Slutsky,et al.  Chemometrics: A Practical Guide By Kenneth R. Beebe, Randy J. Pell, and Mary Beth Seasholtz. Wiley-Interscience Series on Laboratory Automation. John Wiley & Sons: New York, 1998, xi + 348 pp, ISBN 0-471-12451-6 , 1998, Journal of chemical information and computer sciences.

[11]  Gerrit Kateman,et al.  Interpretation of infrared spectra with modular neural-network systems , 1993 .

[12]  Christophe Croux,et al.  TOMCAT: A MATLAB toolbox for multivariate calibration techniques , 2007 .

[13]  P. Gemperline,et al.  Spectroscopic calibration and quantitation using artificial neural networks , 1990 .

[14]  Maneesha Singh,et al.  Explosives detection systems (EDS) for aviation security , 2003, Signal Process..

[15]  Peter V. Czipott,et al.  Screening sealed bottles for liquid explosives , 1997, Defense + Security Symposium.

[16]  W. Fred McClure,et al.  Near infrared spectroscopy : the giant is running strong , 1994 .

[17]  Gerrit Kateman,et al.  Pattern classification with artificial neural networks : classification of algae, based upon flow cytometer data , 1992 .

[18]  Yuji Yamauchi,et al.  Liquid explosive detection from outside of the bottle by IR , 2009, Defense + Commercial Sensing.

[19]  Hilko van der Voet,et al.  Comparing the predictive accuracy of models using a simple randomization test , 1994 .

[20]  Mia Hubert,et al.  LIBRA: a MATLAB library for robust analysis , 2005 .

[21]  David J. C. MacKay,et al.  Bayesian Interpolation , 1992, Neural Computation.

[22]  L. A. Stone,et al.  Computer Aided Design of Experiments , 1969 .

[23]  D. Massart.  Chemometrics: A Textbook , 1988 .

[24]  Roger J. Green,et al.  Remote identification of chemicals concealed behind clothing using near infrared spectroscopy. , 2011, Analytical methods : advancing methods and applications.

[25]  G. M. Stone.  Application and limitations of advanced technologies in explosives detection , 1990, IEEE International Carnahan Conference on Security Technology, Crime Countermeasures.

[26]  H. H. Thodberg,et al.  Optimal minimal neural interpretation of spectra , 1992 .

[27]  Beata Walczak,et al.  Comparison of Multivariate Calibration Techniques Applied to Experimental NIR Data Sets , 2000 .

[28]  Desire L. Massart,et al.  The optimal brain surgeon for pruning neural network architecture applied to multivariate calibration , 1998 .

[29]  Desire L. Massart,et al.  A comparison of multivariate calibration techniques applied to experimental NIR data sets: Part II. Predictive ability under extrapolation conditions , 2001 .

[30]  Ronald D. Snee,et al.  Validation of Regression Models: Methods and Examples , 1977 .

[31]  H. Martens,et al.  Physics-Based Multiplicative Scatter Correction Approaches for Improving the Performance of Calibration Models , 2006, Applied spectroscopy.

[32]  H. Martens,et al.  Near-Infrared Absorption and Scattering Separated by Extended Inverted Signal Correction (EISC): Analysis of Near-Infrared Transmittance Spectra of Single Wheat Seeds , 2002 .