Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational Spectroscopy
One of the significant challenges in the food industry is the determination of the geographical origin, since products from different regions can lead to great variance in raw milk. Therefore, monitoring the origin of raw milk has become very relevant for producers and consumers worldwide. In this e...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-01-01
|
| Series: | Journal of Spectroscopy |
| Online Access: | http://dx.doi.org/10.1155/2021/5845422 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832557119042224128 |
|---|---|
| author | Aimen El Orche Amine Mamad Omar Elhamdaoui Amine Cheikh Miloud El Karbane Mustapha Bouatia |
| author_facet | Aimen El Orche Amine Mamad Omar Elhamdaoui Amine Cheikh Miloud El Karbane Mustapha Bouatia |
| author_sort | Aimen El Orche |
| collection | DOAJ |
| description | One of the significant challenges in the food industry is the determination of the geographical origin, since products from different regions can lead to great variance in raw milk. Therefore, monitoring the origin of raw milk has become very relevant for producers and consumers worldwide. In this exploratory study, midinfrared spectroscopy combined with machine learning classification methods was investigated as a rapid and nondestructive method for the classification of milk according to its geographical origin. The curse of dimensionality makes some classification methods struggle to train efficient models. Thus, principal component analysis (PCA) has been applied to create a smaller set of features. The application of machine learning methods such as PLS-DA, PCA-LDA, SVM, and PCA-SVM demonstrates that the best results are obtained using PLS-DA, PCA-LDA, and PCA-SVM methods which show a correct classification rate (CCR) of 100% for PLS-DA and PCA-LDA and 94.95% for PCA-SVM, whereas the application of SVM without feature extraction gives a low CCR of 66.67%. These findings demonstrate that FT-MIR spectroscopy, combined with machine learning methods, is an efficient and suitable approach to classify the geographical origins of raw milk. |
| format | Article |
| id | doaj-art-a328ff2dfdd74d7a8edd7d18fb946fc2 |
| institution | Kabale University |
| issn | 2314-4939 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Spectroscopy |
| spelling | doaj-art-a328ff2dfdd74d7a8edd7d18fb946fc22025-02-03T05:43:34ZengWileyJournal of Spectroscopy2314-49392021-01-01202110.1155/2021/5845422Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational SpectroscopyAimen El Orche0Amine Mamad1Omar Elhamdaoui2Amine Cheikh3Miloud El Karbane4Mustapha Bouatia5Team of Analytical and Computational Chemistry,Nanotechnology and EnvironmentLaboratory of Analytical ChemistryLaboratory of Analytical ChemistryFaculty of MedicineLaboratory of Analytical ChemistryLaboratory of Analytical ChemistryOne of the significant challenges in the food industry is the determination of the geographical origin, since products from different regions can lead to great variance in raw milk. Therefore, monitoring the origin of raw milk has become very relevant for producers and consumers worldwide. In this exploratory study, midinfrared spectroscopy combined with machine learning classification methods was investigated as a rapid and nondestructive method for the classification of milk according to its geographical origin. The curse of dimensionality makes some classification methods struggle to train efficient models. Thus, principal component analysis (PCA) has been applied to create a smaller set of features. The application of machine learning methods such as PLS-DA, PCA-LDA, SVM, and PCA-SVM demonstrates that the best results are obtained using PLS-DA, PCA-LDA, and PCA-SVM methods which show a correct classification rate (CCR) of 100% for PLS-DA and PCA-LDA and 94.95% for PCA-SVM, whereas the application of SVM without feature extraction gives a low CCR of 66.67%. These findings demonstrate that FT-MIR spectroscopy, combined with machine learning methods, is an efficient and suitable approach to classify the geographical origins of raw milk.http://dx.doi.org/10.1155/2021/5845422 |
| spellingShingle | Aimen El Orche Amine Mamad Omar Elhamdaoui Amine Cheikh Miloud El Karbane Mustapha Bouatia Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational Spectroscopy Journal of Spectroscopy |
| title | Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational Spectroscopy |
| title_full | Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational Spectroscopy |
| title_fullStr | Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational Spectroscopy |
| title_full_unstemmed | Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational Spectroscopy |
| title_short | Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational Spectroscopy |
| title_sort | comparison of machine learning classification methods for determining the geographical origin of raw milk using vibrational spectroscopy |
| url | http://dx.doi.org/10.1155/2021/5845422 |
| work_keys_str_mv | AT aimenelorche comparisonofmachinelearningclassificationmethodsfordeterminingthegeographicaloriginofrawmilkusingvibrationalspectroscopy AT aminemamad comparisonofmachinelearningclassificationmethodsfordeterminingthegeographicaloriginofrawmilkusingvibrationalspectroscopy AT omarelhamdaoui comparisonofmachinelearningclassificationmethodsfordeterminingthegeographicaloriginofrawmilkusingvibrationalspectroscopy AT aminecheikh comparisonofmachinelearningclassificationmethodsfordeterminingthegeographicaloriginofrawmilkusingvibrationalspectroscopy AT miloudelkarbane comparisonofmachinelearningclassificationmethodsfordeterminingthegeographicaloriginofrawmilkusingvibrationalspectroscopy AT mustaphabouatia comparisonofmachinelearningclassificationmethodsfordeterminingthegeographicaloriginofrawmilkusingvibrationalspectroscopy |