A Bayesian Approach to Binary Classification of Mid-Infrared Spectral Data With Noisy Sensors

The problem of classifying substances using MIR laser and sensors with low signal-to-noise ratio remains challenging. The existing methods rely largely on using lasers at multiple wavelengths and expensive high quality sensors. We propose and demonstrate a statistical method that classifies spectral data generated from MIR imaging spectroscopy experiments using few wavelengths and inexpensive detector arrays while still achieving high accuracy. Results with quantifiable analytic performance are obtained by attributing probability distribution functions to the images obtained and implementing a binary decision process. Our method can provide a solution with as few as a single measurement and allows the use of low SNR sensors. This can increase throughput and lower costs on security checkpoints, pharmaceutical production monitoring, industrial quality control, and similar applications.

[1]  J. Kiefer,et al.  Asymptotic Minimax Character of the Sample Distribution Function and of the Classical Multinomial Estimator , 1956 .

[2]  T. Antal,et al.  1/f noise and extreme value statistics. , 2001, Physical review letters.

[3]  Boris Mizaikoff,et al.  Current applications and new trends in mid-infrared sensor technology and integrated scanning probe sensors , 2001, SIcon/01. Sensors for Industry Conference. Proceedings of the First ISA/IEEE. Sensors for Industry Conference (Cat. No.01EX459).

[4]  J. Hammond Chapter 11 – The Use of Spectrophotometry in the Pharmaceutical Industry , 2014 .

[5]  S. Lanteri,et al.  Detection of minced beef adulteration with turkey meat by UV-vis, NIR and MIR spectroscopy , 2013 .

[6]  F. Massey The Kolmogorov-Smirnov Test for Goodness of Fit , 1951 .

[7]  L. Pacheco-Londoño,et al.  Vibrational spectroscopy standoff detection of explosives , 2009, Analytical and bioanalytical chemistry.

[8]  Joachim Wagner,et al.  Recent Advances and Applications of External Cavity-QCLs towards Hyperspectral Imaging for Standoff Detection and Real-Time Spectroscopic Sensing of Chemicals , 2016 .

[9]  Jordi-Roger Riba,et al.  Recovered Paperboard Samples Identification by Means of Mid-Infrared Sensors , 2013, IEEE Sensors Journal.

[10]  R. Walters,et al.  Laser-induced breakdown spectroscopy (LIBS): a promising versatile chemical sensor technology for hazardous material detection , 2005, IEEE Sensors Journal.

[11]  David Benirschke,et al.  Characterization of a low-cost, commercially available, vanadium oxide microbolometer array for spectroscopic imaging , 2017 .

[12]  Rolf Aidam,et al.  Imaging standoff detection of explosives using widely tunable midinfrared quantum cascade lasers , 2010 .

[13]  B. Mizaikoff,et al.  Potential and Challenges for Mid-Infrared Sensors in Breath Diagnostics , 2010, IEEE Sensors Journal.

[14]  E. S. Pearson,et al.  On the Problem of the Most Efficient Tests of Statistical Hypotheses , 1933 .

[15]  J. Faist,et al.  Trace Sensing with Miniaturized Mid-Infrared Sensors , 2006, 2006 5th IEEE Conference on Sensors.

[16]  Amanda M. Figueroa-Navedo,et al.  Mid-Infrared Laser Spectroscopy Applications I: Detection of Traces of High Explosives on Reflective and Matte Substrates , 2018, Infrared Spectroscopy - Principles, Advances, and Applications.