Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy
The addition of incorrect agri-food powders to a production line due to human error is a large safety concern in food and drink manufacturing, owing to incorporation of allergens in the final product. This work combines near-infrared spectroscopy with machine-learning models for early detection of t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/19/7239 |
| _version_ | 1797476947715948544 |
|---|---|
| author | Alexander Lewis Bowler Samet Ozturk Ahmed Rady Nicholas Watson |
| author_facet | Alexander Lewis Bowler Samet Ozturk Ahmed Rady Nicholas Watson |
| author_sort | Alexander Lewis Bowler |
| collection | DOAJ |
| description | The addition of incorrect agri-food powders to a production line due to human error is a large safety concern in food and drink manufacturing, owing to incorporation of allergens in the final product. This work combines near-infrared spectroscopy with machine-learning models for early detection of this problem. Specifically, domain adaptation is used to transfer models from spectra acquired under stationary conditions to moving samples, thereby minimizing the volume of labelled data required to collect on a production line. Two deep-learning domain-adaptation methodologies are used: domain-adversarial neural networks and semisupervised generative adversarial neural networks. Overall, accuracy of up to 96.0% was achieved using no labelled data from the target domain moving spectra, and up to 99.68% was achieved when incorporating a single labelled data instance for each material into model training. Using both domain-adaptation methodologies together achieved the highest prediction accuracies on average, as did combining measurements from two near-infrared spectroscopy sensors with different wavelength ranges. Ensemble methods were used to further increase model accuracy and provide quantification of model uncertainty, and a feature-permutation method was used for global interpretability of the models. |
| first_indexed | 2024-03-09T21:11:00Z |
| format | Article |
| id | doaj.art-50f906265cfb49a8b5f19156cdb73b20 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:11:00Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-50f906265cfb49a8b5f19156cdb73b202023-11-23T21:45:51ZengMDPI AGSensors1424-82202022-09-012219723910.3390/s22197239Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared SpectroscopyAlexander Lewis Bowler0Samet Ozturk1Ahmed Rady2Nicholas Watson3Food, Water, Waste Research Group, Faculty of Engineering, University Park, University of Nottingham, Nottingham NG7 2RD, UKFood, Water, Waste Research Group, Faculty of Engineering, University Park, University of Nottingham, Nottingham NG7 2RD, UKFood, Water, Waste Research Group, Faculty of Engineering, University Park, University of Nottingham, Nottingham NG7 2RD, UKFood, Water, Waste Research Group, Faculty of Engineering, University Park, University of Nottingham, Nottingham NG7 2RD, UKThe addition of incorrect agri-food powders to a production line due to human error is a large safety concern in food and drink manufacturing, owing to incorporation of allergens in the final product. This work combines near-infrared spectroscopy with machine-learning models for early detection of this problem. Specifically, domain adaptation is used to transfer models from spectra acquired under stationary conditions to moving samples, thereby minimizing the volume of labelled data required to collect on a production line. Two deep-learning domain-adaptation methodologies are used: domain-adversarial neural networks and semisupervised generative adversarial neural networks. Overall, accuracy of up to 96.0% was achieved using no labelled data from the target domain moving spectra, and up to 99.68% was achieved when incorporating a single labelled data instance for each material into model training. Using both domain-adaptation methodologies together achieved the highest prediction accuracies on average, as did combining measurements from two near-infrared spectroscopy sensors with different wavelength ranges. Ensemble methods were used to further increase model accuracy and provide quantification of model uncertainty, and a feature-permutation method was used for global interpretability of the models.https://www.mdpi.com/1424-8220/22/19/7239near-infrared spectroscopydomain adaptationtransfer learningmachine learningprocess monitoringfood and drink |
| spellingShingle | Alexander Lewis Bowler Samet Ozturk Ahmed Rady Nicholas Watson Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy Sensors near-infrared spectroscopy domain adaptation transfer learning machine learning process monitoring food and drink |
| title | Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy |
| title_full | Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy |
| title_fullStr | Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy |
| title_full_unstemmed | Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy |
| title_short | Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy |
| title_sort | domain adaptation for in line allergen classification of agri food powders using near infrared spectroscopy |
| topic | near-infrared spectroscopy domain adaptation transfer learning machine learning process monitoring food and drink |
| url | https://www.mdpi.com/1424-8220/22/19/7239 |
| work_keys_str_mv | AT alexanderlewisbowler domainadaptationforinlineallergenclassificationofagrifoodpowdersusingnearinfraredspectroscopy AT sametozturk domainadaptationforinlineallergenclassificationofagrifoodpowdersusingnearinfraredspectroscopy AT ahmedrady domainadaptationforinlineallergenclassificationofagrifoodpowdersusingnearinfraredspectroscopy AT nicholaswatson domainadaptationforinlineallergenclassificationofagrifoodpowdersusingnearinfraredspectroscopy |