Title :
Data fusion approach for human body odor discrimination using GC-MS spectra
Author :
Jha, Sumit Kumar ; Imahashi, Masahiro ; Hayashi, K. ; Takamizawa, Tadashi
Author_Institution :
Dept. of Electron. Grad., Kyushu Univ., Fukuoka, Japan
Abstract :
This study deals with data fusion approach to search discriminating biomarker volatile organic chemicals (VOCs) in body odor for individual differentiation. Particularly we have employed kernel principal component analysis (KPCA) combined with majority voting method to build up novel data fusion strategy. Gas chromatography-mass spectrometry (GC-MS) characterizes human body odor samples to find out the VOCs composition (alcohols, acids, aldehydes, esters, ketones, carbonyl compounds, sulfides and hydrocarbons etc.). Peak number and related area value of VOCs from the GC-MS spectra of body odor extract is used for analysis. GC-MS data from three experiments, based on body odor samples of four persons (different age groups) in dissimilar conditions are collected. Optimal set of peak numbers are selected with fusion approach. Linear PCA is used in validation of elected peak numbers for discrimination of individual´s body odor. The opted peaks result satisfactory differentiation of individual´s body odor in feature space. Thereafter biomarker VOCs are affirmed by matching corresponding peak number in GC-MS spectra. Analysis outcomes conclude particular set of biomarker VOCs for each experiment.
Keywords :
biochemistry; biomedical measurement; chromatography; data analysis; feature extraction; mass spectroscopic chemical analysis; medical signal processing; operating system kernels; organic compounds; principal component analysis; sensor fusion; signal classification; GC-MS data analysis; GC-MS spectra; KPCA; VOC biomarker; VOC composition; VOC peak number; VOC related area value; acid content; alcohol content; aldehyde content; carbonyl compound content; corresponding peak number matching; data fusion approach; discriminating biomarker search; elected peak number validation; ester content; feature space; gas chromatography-mass spectrometry; human body odor discrimination; human body odor sample characterization; hydrocarbon content; individual body odor discrimination; kernel principal component analysis; ketone content; linear PCA; majority voting method; optimal peak number set selection; sulfide content; volatile organic chemicals; Analysis of variance; Data integration; Data mining; Kernel; Loading; Principal component analysis; Skin; Body Odor; Data Fusion; GC-MS Analysis; KPCA;
Conference_Titel :
Intelligent Sensors, Sensor Networks and Information Processing (ISSNIP), 2014 IEEE Ninth International Conference on
Conference_Location :
Singapore
Print_ISBN :
978-1-4799-2842-2
DOI :
10.1109/ISSNIP.2014.6827592
