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

W. N. S. Mat-Desa, D. Ismail, N. NicDaeid

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

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of SOFM were further tested and validated for their predictive abilities where one set of weather data in each case was withdrawn from the sample set and used as a test set of the retrained network This revealed SOFM to be an outstanding mechanism for sample discrimination and linkage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.
LanguageEnglish
Pages7745-7754
Number of pages10
JournalAnalytical Chemistry
Volume83
Issue number20
DOIs
Publication statusPublished - 15 Oct 2011

Fingerprint

Petroleum distillates
Self organizing maps
Neural networks
Cluster analysis
Principal component analysis
Petroleum products
Boiling point
Brushes
Hydrocarbons
Electric lamps
Paint
Gas chromatography
Mass spectrometry
Oils

Keywords

  • scheme
  • samples
  • GC-MS
  • chromatography mass-spectrometry
  • accelerants
  • fire debris
  • classification
  • source determination
  • medium petroleum distillates
  • artificial neural networks
  • chemometric
  • self organizing
  • feature approach

Cite this

@article{0f6ed3fd68cd4daa97c4329c11ca4932,
title = "Classification and source determination of medium petroleum distillates by chemometric and artificial neural networks: a self organizing feature approach",
abstract = "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.",
keywords = "scheme, samples, GC-MS, chromatography mass-spectrometry, accelerants, fire debris, classification, source determination , medium petroleum distillates , artificial neural networks, chemometric , self organizing, feature approach",
author = "Mat-Desa, {W. N. S.} and D. Ismail and N. NicDaeid",
year = "2011",
month = "10",
day = "15",
doi = "10.1021/ac202315y",
language = "English",
volume = "83",
pages = "7745--7754",
journal = "Analytical Chemistry",
issn = "0003-2700",
publisher = "American Chemical Society",
number = "20",

}

Classification and source determination of medium petroleum distillates by chemometric and artificial neural networks : a self organizing feature approach. / Mat-Desa, W. N. S.; Ismail, D.; NicDaeid, N.

In: Analytical Chemistry, Vol. 83, No. 20, 15.10.2011, p. 7745-7754.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Classification and source determination of medium petroleum distillates by chemometric and artificial neural networks

T2 - Analytical Chemistry

AU - Mat-Desa, W. N. S.

AU - Ismail, D.

AU - NicDaeid, N.

PY - 2011/10/15

Y1 - 2011/10/15

N2 - 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.

AB - 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.

KW - scheme

KW - samples

KW - GC-MS

KW - chromatography mass-spectrometry

KW - accelerants

KW - fire debris

KW - classification

KW - source determination

KW - medium petroleum distillates

KW - artificial neural networks

KW - chemometric

KW - self organizing

KW - feature approach

UR - http://www.scopus.com/inward/record.url?scp=80054682878&partnerID=8YFLogxK

U2 - 10.1021/ac202315y

DO - 10.1021/ac202315y

M3 - Article

VL - 83

SP - 7745

EP - 7754

JO - Analytical Chemistry

JF - Analytical Chemistry

SN - 0003-2700

IS - 20

ER -