Human body odor discrimination by GC-MS spectra data mining

Sunil Kr Jha, Ninoslav Marina, Chuanjun Liu, Kenshi Hayashi

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

The present study explores individual identity perception by analyzing the chemical peak information in the gas chromatography-mass spectrometry (GC-MS) spectra of body odor samples with standard data mining approaches. Mainly, the principal component analysis (PCA) method is chosen for the visual discrimination of the body odor samples in feature space. PCA in combination with the support vector machine (SVM) method is used for quantitative recognition. GC-MS characterization confirms the composition of numerous chemical species (aldehydes, acids, ketones, esters, sulfides etc.) in the body odor samples. The GC-MS spectra of body odor samples from the armpit and neck of three people (from dissimilar age groups) at two different sampling times (0 h and 4 h) were recorded in the experiment. A few blank (non-body odor) samples were also characterized with GC-MS and included as references in further analysis by the data mining methods. The discrimination efficiency (both qualitative and quantitative) for the individual body odors was evaluated for (i) three variables of chemical information in the GC-MS spectra (the peak area, peak height and ratio of peak area to height); (ii) two sampling times (0 h and 4 h); and (iii) two sampling parts of the body (the neck and armpit). The best visual discrimination of the individual body odors has been achieved using the peak height as a variable for the neck odor with a sampling time of 4 h. This result has been established with class separability measures calculated with principal component (PC) scores and SVM classification outcomes (86%).

Original languageEnglish
Pages (from-to)9549-9561
Number of pages13
JournalAnalytical Methods
Volume7
Issue number22
DOIs
Publication statusPublished - Jan 1 2015

Fingerprint

Odors
Gas chromatography
Mass spectrometry
Data mining
Sampling
Principal component analysis
Support vector machines
Sulfides
Ketones
Aldehydes
Esters
Acids
Chemical analysis

All Science Journal Classification (ASJC) codes

  • Analytical Chemistry
  • Chemical Engineering(all)
  • Engineering(all)

Cite this

Human body odor discrimination by GC-MS spectra data mining. / Jha, Sunil Kr; Marina, Ninoslav; Liu, Chuanjun; Hayashi, Kenshi.

In: Analytical Methods, Vol. 7, No. 22, 01.01.2015, p. 9549-9561.

Research output: Contribution to journalArticle

Jha, Sunil Kr ; Marina, Ninoslav ; Liu, Chuanjun ; Hayashi, Kenshi. / Human body odor discrimination by GC-MS spectra data mining. In: Analytical Methods. 2015 ; Vol. 7, No. 22. pp. 9549-9561.
@article{f02254b058ea497686515f6ef89fb8f5,
title = "Human body odor discrimination by GC-MS spectra data mining",
abstract = "The present study explores individual identity perception by analyzing the chemical peak information in the gas chromatography-mass spectrometry (GC-MS) spectra of body odor samples with standard data mining approaches. Mainly, the principal component analysis (PCA) method is chosen for the visual discrimination of the body odor samples in feature space. PCA in combination with the support vector machine (SVM) method is used for quantitative recognition. GC-MS characterization confirms the composition of numerous chemical species (aldehydes, acids, ketones, esters, sulfides etc.) in the body odor samples. The GC-MS spectra of body odor samples from the armpit and neck of three people (from dissimilar age groups) at two different sampling times (0 h and 4 h) were recorded in the experiment. A few blank (non-body odor) samples were also characterized with GC-MS and included as references in further analysis by the data mining methods. The discrimination efficiency (both qualitative and quantitative) for the individual body odors was evaluated for (i) three variables of chemical information in the GC-MS spectra (the peak area, peak height and ratio of peak area to height); (ii) two sampling times (0 h and 4 h); and (iii) two sampling parts of the body (the neck and armpit). The best visual discrimination of the individual body odors has been achieved using the peak height as a variable for the neck odor with a sampling time of 4 h. This result has been established with class separability measures calculated with principal component (PC) scores and SVM classification outcomes (86{\%}).",
author = "Jha, {Sunil Kr} and Ninoslav Marina and Chuanjun Liu and Kenshi Hayashi",
year = "2015",
month = "1",
day = "1",
doi = "10.1039/c5ay02457a",
language = "English",
volume = "7",
pages = "9549--9561",
journal = "Analytical Methods",
issn = "1759-9660",
publisher = "Royal Society of Chemistry",
number = "22",

}

TY - JOUR

T1 - Human body odor discrimination by GC-MS spectra data mining

AU - Jha, Sunil Kr

AU - Marina, Ninoslav

AU - Liu, Chuanjun

AU - Hayashi, Kenshi

PY - 2015/1/1

Y1 - 2015/1/1

N2 - The present study explores individual identity perception by analyzing the chemical peak information in the gas chromatography-mass spectrometry (GC-MS) spectra of body odor samples with standard data mining approaches. Mainly, the principal component analysis (PCA) method is chosen for the visual discrimination of the body odor samples in feature space. PCA in combination with the support vector machine (SVM) method is used for quantitative recognition. GC-MS characterization confirms the composition of numerous chemical species (aldehydes, acids, ketones, esters, sulfides etc.) in the body odor samples. The GC-MS spectra of body odor samples from the armpit and neck of three people (from dissimilar age groups) at two different sampling times (0 h and 4 h) were recorded in the experiment. A few blank (non-body odor) samples were also characterized with GC-MS and included as references in further analysis by the data mining methods. The discrimination efficiency (both qualitative and quantitative) for the individual body odors was evaluated for (i) three variables of chemical information in the GC-MS spectra (the peak area, peak height and ratio of peak area to height); (ii) two sampling times (0 h and 4 h); and (iii) two sampling parts of the body (the neck and armpit). The best visual discrimination of the individual body odors has been achieved using the peak height as a variable for the neck odor with a sampling time of 4 h. This result has been established with class separability measures calculated with principal component (PC) scores and SVM classification outcomes (86%).

AB - The present study explores individual identity perception by analyzing the chemical peak information in the gas chromatography-mass spectrometry (GC-MS) spectra of body odor samples with standard data mining approaches. Mainly, the principal component analysis (PCA) method is chosen for the visual discrimination of the body odor samples in feature space. PCA in combination with the support vector machine (SVM) method is used for quantitative recognition. GC-MS characterization confirms the composition of numerous chemical species (aldehydes, acids, ketones, esters, sulfides etc.) in the body odor samples. The GC-MS spectra of body odor samples from the armpit and neck of three people (from dissimilar age groups) at two different sampling times (0 h and 4 h) were recorded in the experiment. A few blank (non-body odor) samples were also characterized with GC-MS and included as references in further analysis by the data mining methods. The discrimination efficiency (both qualitative and quantitative) for the individual body odors was evaluated for (i) three variables of chemical information in the GC-MS spectra (the peak area, peak height and ratio of peak area to height); (ii) two sampling times (0 h and 4 h); and (iii) two sampling parts of the body (the neck and armpit). The best visual discrimination of the individual body odors has been achieved using the peak height as a variable for the neck odor with a sampling time of 4 h. This result has been established with class separability measures calculated with principal component (PC) scores and SVM classification outcomes (86%).

UR - http://www.scopus.com/inward/record.url?scp=84946893588&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946893588&partnerID=8YFLogxK

U2 - 10.1039/c5ay02457a

DO - 10.1039/c5ay02457a

M3 - Article

VL - 7

SP - 9549

EP - 9561

JO - Analytical Methods

JF - Analytical Methods

SN - 1759-9660

IS - 22

ER -