Search prefilters for mid‐infrared absorbance spectra of clear coat automotive paint smears using stacked and linear classifiers

By using stacked partial least squares classifiers and genetic algorithms for feature selection and classification, it is demonstrated that search prefilters can be developed to extract investigative lead information from clear coat paint smears. The results obtained in this study also show that identifying specific wavelengths or wavelet coefficients in IR spectral data is superior to identifying informative wavelength windows when applying pattern recognition techniques to IR spectra from the paint data query (PDQ) database when differentiating paint samples by assembly plant. Search prefilters developed using specific wavelengths or wavelet coefficients outperformed search prefilters that utilized spectral regions. Clear coat paint spectra from the PDQ database may not be well suited for stacking as there are few spectral intervals that can reliably distinguish the different sample groups (i.e., assembly plants) in the data. The information contained in the IR spectra about assembly plant may not be highly compartmentalized in an interval, which also works against stacking. The similarity of the IR spectra within a plant group and the noise present in the IR spectra may also be obscuring information present in spectral intervals. Copyright © 2014 John Wiley & Sons, Ltd.

[1]  Steven D. Brown,et al.  Decision pathway modeling , 2004 .

[2]  Barry K. Lavine,et al.  One stop shopping: feature selection, classification and prediction in a single step , 2011 .

[3]  Barry K. Lavine,et al.  Genetic algorithms for pattern recognition analysis and fusion of sensor data , 1999, Optics East.

[4]  Nikhil Mirjankar,et al.  Wavelets and genetic algorithms applied to search prefilters for spectral library matching in forensics. , 2011, Talanta.

[5]  J. L. Buckle,et al.  PDQ—Paint Data Queries: The History and Technology Behind the Development of the Royal Canadian Mounted Police Forensic Laboratory Services Automotive Paint Database , 1997 .

[6]  B. K. Lavine,et al.  Multivariate Approaches to Classification using Genetic Algorithms , 2009 .

[7]  Steven D. Brown,et al.  Data fusion in multivariate calibration transfer. , 2010, Analytica chimica acta.

[8]  B. Lavine,et al.  Ion mobility-mass spectrometry analysis of serum N-linked glycans from esophageal adenocarcinoma phenotypes. , 2012, Journal of proteome research.

[9]  Barry K. Lavine,et al.  Raman Spectroscopy and Genetic Algorithms for the Classification of Wood Types , 2001 .

[10]  Jerome J. Workman,et al.  Pattern Recognition Assisted Infrared Library Searching , 2012, Applied spectroscopy.

[11]  Nikhil Mirjankar,et al.  Pattern recognition analysis of differential mobility spectra with classification by chemical family. , 2006, Analytica chimica acta.

[12]  A. Beveridge,et al.  Use of infrared spectroscopy for the characterisation of paint fragments , 2001 .

[13]  Gregory A. Bishea,et al.  International forensic automotive paint database , 1999, Other Conferences.

[14]  L. Breiman.  Stacked Regressions , 1996, Machine Learning.

[15]  Nikhil Mirjankar,et al.  Odor-structure relationship studies of tetralin and indan musks. , 2012, Chemical senses.

[16]  John H. Kalivas,et al.  Wavelength Selection Characterization for NIR Spectra , 1997 .

[17]  B. Lavine,et al.  Development of carboxylic acid search prefilters for spectral library matching , 2012 .

[18]  Silvana Andreescu,et al.  Multiarray sensors with pattern recognition for the detection, classification, and differentiation of bacteria at subspecies and strain levels. , 2005, Analytical chemistry.

[19]  W. H. Clark,et al.  A Computerized System for the Identification of Suspect Vehicles Involved in Hit and Run Accidents , 1982 .

[20]  John M. Chalmers.  Spectroscopy in process analysis , 2000 .

[21]  Barry K Lavine,et al.  Machine learning based pattern recognition applied to microarray data. , 2004, Combinatorial chemistry & high throughput screening.