GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction
Food flavor quality evaluation is attracting continuous attention, but a suitable evaluation system is severely lacking. Gas chromatography-mass spectrometry/olfactometry (GC-MS/O) is widely used to solve the food flavor evaluation problem, but the olfactometry evaluation is unfeasible to be carried...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-12-01
|
Series: | Processes |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9717/8/1/23 |
id |
doaj-777f0b9735134212853dda529001e52a |
---|---|
record_format |
Article |
spelling |
doaj-777f0b9735134212853dda529001e52a2020-11-25T02:25:58ZengMDPI AGProcesses2227-97172019-12-01812310.3390/pr8010023pr8010023GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor PredictionKexin Bi0Dong Zhang1Tong Qiu2Yizhen Huang3Department of Chemical Engineering, Tsinghua University, Beijing 100084, ChinaCOFCO Nutrition Health Research Institute, Beijing 102209, ChinaDepartment of Chemical Engineering, Tsinghua University, Beijing 100084, ChinaCOFCO Nutrition Health Research Institute, Beijing 102209, ChinaFood flavor quality evaluation is attracting continuous attention, but a suitable evaluation system is severely lacking. Gas chromatography-mass spectrometry/olfactometry (GC-MS/O) is widely used to solve the food flavor evaluation problem, but the olfactometry evaluation is unfeasible to be carried out in large batches and is unreliable due to potential issue of an operator or systematic laboratory effect. Thus, a novel fingerprint modeling and profiling process was proposed based on several machine learning models including convolutional neural network (CNN). The fingerprint template was created by the data analysis of existing GC-MS spectrum dataset. Then the fingerprint image generation program was applied for structuring the complex instrumental data. Food olfactometry result was obtained by a machine learning method based on CNN using fingerprint image as the input. The case study on peanut oil samples demonstrated the model accuracy of around 93%. By structure optimization and further dataset expansion, the whole process has the potential to be utilized by sensory laboratories for aroma analysis instead of humans.https://www.mdpi.com/2227-9717/8/1/23gc-ms/o profilingmachine learningconvolutional neural networkfingerprint modelingodor compounds |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Kexin Bi Dong Zhang Tong Qiu Yizhen Huang |
spellingShingle |
Kexin Bi Dong Zhang Tong Qiu Yizhen Huang GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction Processes gc-ms/o profiling machine learning convolutional neural network fingerprint modeling odor compounds |
author_facet |
Kexin Bi Dong Zhang Tong Qiu Yizhen Huang |
author_sort |
Kexin Bi |
title |
GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction |
title_short |
GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction |
title_full |
GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction |
title_fullStr |
GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction |
title_full_unstemmed |
GC-MS Fingerprints Profiling Using Machine Learning Models for Food Flavor Prediction |
title_sort |
gc-ms fingerprints profiling using machine learning models for food flavor prediction |
publisher |
MDPI AG |
series |
Processes |
issn |
2227-9717 |
publishDate |
2019-12-01 |
description |
Food flavor quality evaluation is attracting continuous attention, but a suitable evaluation system is severely lacking. Gas chromatography-mass spectrometry/olfactometry (GC-MS/O) is widely used to solve the food flavor evaluation problem, but the olfactometry evaluation is unfeasible to be carried out in large batches and is unreliable due to potential issue of an operator or systematic laboratory effect. Thus, a novel fingerprint modeling and profiling process was proposed based on several machine learning models including convolutional neural network (CNN). The fingerprint template was created by the data analysis of existing GC-MS spectrum dataset. Then the fingerprint image generation program was applied for structuring the complex instrumental data. Food olfactometry result was obtained by a machine learning method based on CNN using fingerprint image as the input. The case study on peanut oil samples demonstrated the model accuracy of around 93%. By structure optimization and further dataset expansion, the whole process has the potential to be utilized by sensory laboratories for aroma analysis instead of humans. |
topic |
gc-ms/o profiling machine learning convolutional neural network fingerprint modeling odor compounds |
url |
https://www.mdpi.com/2227-9717/8/1/23 |
work_keys_str_mv |
AT kexinbi gcmsfingerprintsprofilingusingmachinelearningmodelsforfoodflavorprediction AT dongzhang gcmsfingerprintsprofilingusingmachinelearningmodelsforfoodflavorprediction AT tongqiu gcmsfingerprintsprofilingusingmachinelearningmodelsforfoodflavorprediction AT yizhenhuang gcmsfingerprintsprofilingusingmachinelearningmodelsforfoodflavorprediction |
_version_ |
1724849174333095936 |