Classification and source determination of medium petroleum distillates by chemometric and artificial neural networks: a self organizing feature approach.

Three different medium petroleum distillate (MPD) products (white spirit, paint brush cleaner, and lamp oil) were purchased from commercial stores in Glasgow, Scotland. Samples of 10, 25, 50, 75, 90, and 95% evaporated product were prepared, resulting in 56 samples in total which were analyzed using gas chromatography-mass spectrometry. Data sets from the chromatographic patterns were examined and preprocessed for unsupervised multivariate analyses using principal component analysis (PCA), hierarchical cluster analysis (HCA), and a self organizing feature map (SOFM) artificial neural network. It was revealed that data sets comprised of higher boiling point hydrocarbon compounds provided a good means for the classification of the samples and successfully linked highly weathered samples back to their unevaporated counterpart in every case. The classification abilities of SOFM were further tested and validated for their predictive abilities where one set of weather data in each case was withdrawn from the sample set and used as a test set of the retrained network. This revealed SOFM to be an outstanding mechanism for sample discrimination and linkage over the more conventional PCA and HCA methods often suggested for such data analysis. SOFM also has the advantage of providing additional information through the evaluation of component planes facilitating the investigation of underlying variables that account for the classification.

[1]  H. A. Frank,et al.  Lead alkyl components as discriminating factors in the comparison of gasolines. , 1980, Journal - Forensic Science Society.

[2]  J. Nowicki.  Analysis of Fire Debris Samples by Gas Chromatography/Mass Spectrometry (GC-MS): Case Studies , 1991 .

[3]  M S Olivier,et al.  The use of self-organising maps for anomalous behaviour detection in a digital investigation. , 2006, Forensic science international.

[4]  C. Lennard,et al.  A GC–MS database of target compound chromatograms for the identification of arson accelerants , 1995 .

[5]  John P. Jackowski.  The Incidence of Ignitable Liquid Residues in Fire Debris as Determined by a Sensitive and Comprehensive Analytical Scheme , 1997 .

[6]  E. du Pasquier,et al.  Chemical fingerprinting of unevaporated automotive gasoline samples. , 2003, Forensic science international.

[7]  P. L. Wineman,et al.  Detection of petroleum-based accelerants in fire debris by target compound gas chromatography/mass spectrometry , 1991 .

[8]  D. J. Tranthim-Fryer.  The Application of a Simple and Inexpensive Modified Carbon Wire Adsorption/Solvent Extraction Technique to the Analysis of Accelerants and Volatile Organic Compounds in Arson Debris , 1990 .

[9]  Martin Grootveld,et al.  Self Organising Maps for variable selection: Application to human saliva analysed by nuclear magnetic resonance spectroscopy to investigate the effect of an oral healthcare product , 2009 .

[10]  J. Nowicki.  An Accelerant Classification Scheme Based on Analysis by Gas Chromatography/Mass Spectrometry (GC-MS) , 1990 .

[11]  Juha Vesanto,et al.  SOM-based data visualization methods , 1999, Intell. Data Anal..

[12]  K. Savage,et al.  Application of unsupervised chemometric analysis and self-organizing feature map (SOFM) for the classification of lighter fuels. , 2010, Analytical chemistry.

[13]  A. Vella.  Arson investigation using the ion trap detector , 1992 .