{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T09:21:50Z","timestamp":1777713710586,"version":"3.51.4"},"reference-count":43,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,9,24]],"date-time":"2022-09-24T00:00:00Z","timestamp":1663977600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"University of Nottingham STFC Impact Acceleration Account"},{"name":"University of Nottingham Smart Products Beacon of Excellence"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s22197239","type":"journal-article","created":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T03:34:17Z","timestamp":1664163257000},"page":"7239","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Domain Adaptation for In-Line Allergen Classification of Agri-Food Powders Using Near-Infrared Spectroscopy"],"prefix":"10.3390","volume":"22","author":[{"given":"Alexander Lewis","family":"Bowler","sequence":"first","affiliation":[{"name":"Food, Water, Waste Research Group, Faculty of Engineering, University Park, University of Nottingham, Nottingham NG7 2RD, UK"}]},{"given":"Samet","family":"Ozturk","sequence":"additional","affiliation":[{"name":"Food, Water, Waste Research Group, Faculty of Engineering, University Park, University of Nottingham, Nottingham NG7 2RD, UK"}]},{"given":"Ahmed","family":"Rady","sequence":"additional","affiliation":[{"name":"Food, Water, Waste Research Group, Faculty of Engineering, University Park, University of Nottingham, Nottingham NG7 2RD, UK"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5216-4873","authenticated-orcid":false,"given":"Nicholas","family":"Watson","sequence":"additional","affiliation":[{"name":"Food, Water, Waste Research Group, Faculty of Engineering, University Park, University of Nottingham, Nottingham NG7 2RD, UK"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2222","DOI":"10.1111\/1541-4337.12580","article-title":"Recent advances in processing food powders by using superfine grinding techniques: A review","volume":"19","author":"Gao","year":"2020","journal-title":"Compr. Rev. Food Sci. Food"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Okere, E.E., Arendse, E., Nieuwoudt, H., Fawole, O.A., Perold, W.J., and Opara, U.L. (2021). Non-invasive methods for predicting the quality of processed horticultural food products, with emphasis on dried powders, juices and oils: A review. Foods, 10.","DOI":"10.3390\/foods10123061"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e14031","DOI":"10.1111\/jfpe.14031","article-title":"A review on the influence of water on food powder flowability","volume":"45","author":"Olivas","year":"2022","journal-title":"J. Food Process. Eng."},{"key":"ref_4","unstructured":"Food Standard Agency (2022, April 07). Business Committee Meeting\u2014September 2020, Available online: https:\/\/www.food.gov.uk\/sites\/default\/files\/media\/document\/fsa-20-09-12-incidents-resilience-annual-report.pdf."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Loh, W., and Tang, M.L.K. (2018). The epidemiology of food allergy in the global context. Int. J. Environ. Res. Public Health, 15.","DOI":"10.3390\/ijerph15092043"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1939","DOI":"10.1080\/10408398.2013.871693","article-title":"Applications of Near-infrared Spectroscopy in Food Safety Evaluation and Control: A Review of Recent Research Advances","volume":"55","author":"Qu","year":"2015","journal-title":"Crit. Rev. Food Sci. Nutr."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1524","DOI":"10.1080\/10408398.2015.1115954","article-title":"Quality analysis, classification, and authentication of liquid foods by near-infrared spectroscopy: A review of recent research developments","volume":"57","author":"Wang","year":"2017","journal-title":"Crit. Rev. Food Sci. Nutr."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.tifs.2015.10.002","article-title":"On-line application of near infrared (NIR) spectroscopy in food production","volume":"46","author":"Porep","year":"2015","journal-title":"Trends Food Sci. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.foodchem.2016.07.156","article-title":"Rapid authentication of starch adulterations in ultrafine granular powder of Shanyao by near-infrared spectroscopy coupled with chemometric methods","volume":"215","author":"Ma","year":"2017","journal-title":"Food Chem."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"360","DOI":"10.5740\/jaoacint.15-0115","article-title":"Determination of protein content by NIR spectroscopy in protein powder mix products","volume":"99","author":"Ingle","year":"2016","journal-title":"J. AOAC Int."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.biosystemseng.2016.04.018","article-title":"Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy","volume":"152","author":"Morellos","year":"2016","journal-title":"Biosyst. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/j.geoderma.2019.06.016","article-title":"Convolutional neural network for simultaneous prediction of several soil properties using visible\/near-infrared, mid-infrared, and their combined spectra","volume":"352","author":"Ng","year":"2019","journal-title":"Geoderma"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106303","DOI":"10.1016\/j.agwat.2020.106303","article-title":"A deep learning CNN architecture applied in smart near-infrared analysis of water pollution for agricultural irrigation resources","volume":"240","author":"Chen","year":"2020","journal-title":"Agric. Water Manag."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1255\/jnirs.445","article-title":"In-line analysis of ground beef using a diode array near infrared instrument on a conveyor belt","volume":"12","author":"Hildrum","year":"2004","journal-title":"J. Near Infrared Spectrosc."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1255\/jnirs.1221","article-title":"Prediction of beef fat content simultaneously under static and motion conditions using near infrared spectroscopy","volume":"24","author":"Dixit","year":"2016","journal-title":"J. Near Infrared Spectrosc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1121","DOI":"10.1016\/j.foodchem.2013.01.002","article-title":"Near infrared spectroscopy (NIRS) for on-line determination of quality parameters in intact olives","volume":"139","author":"Baeten","year":"2013","journal-title":"Food Chem."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1016\/j.talanta.2016.03.084","article-title":"Multipoint NIR spectroscopy for gross composition analysis of powdered infant formula under various motion conditions","volume":"154","author":"Dixit","year":"2016","journal-title":"Talanta"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/S0003-2670(00)01313-1","article-title":"Characterization of diffuse reflectance fiber probe sampling on moving solids using a Fourier transform near-infrared spectrometer","volume":"431","author":"Berntsson","year":"2001","journal-title":"Anal. Chim. Acta"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1016\/j.ejpb.2013.01.016","article-title":"Use of near-infrared spectroscopy to quantify drug content on a continuous blending process: Influence of mass flow and rotation speed variations","volume":"84","author":"Peinado","year":"2013","journal-title":"Eur. J. Pharm. Biopharm."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"106776","DOI":"10.1016\/j.ultras.2022.106776","article-title":"A review of ultrasonic sensing and machine learning methods to monitor industrial processes","volume":"124","author":"Bowler","year":"2022","journal-title":"Ultrasonics"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"e3080","DOI":"10.1002\/cem.3080","article-title":"Sample and feature augmentation strategies for calibration updating","volume":"33","author":"Andries","year":"2019","journal-title":"J. Chemom."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Lin, J., Zhang, L., Li, J., and Zhou, W. (2019, January 9\u201311). A feature domain space transfer method for improving identification of maize haploid seed based on near-infrared spectroscopy. Proceedings of the 2019 International Conference on High Performance Big Data and Intelligent Systems (HPBD&IS), Shenzhen, China.","DOI":"10.1109\/HPBDIS.2019.8735481"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"103986","DOI":"10.1016\/j.chemolab.2020.103986","article-title":"Domain adaptive partial least squares regression","volume":"201","author":"Huang","year":"2020","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"122461","DOI":"10.1016\/j.talanta.2021.122461","article-title":"A brief note on application of domain-invariant PLS for adapting near-infrared spectroscopy calibrations between different physical forms of samples","volume":"232","author":"Mishra","year":"2021","journal-title":"Talanta"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1061","DOI":"10.1007\/s11676-019-01052-2","article-title":"Compression strength prediction of Xylosma racemosum using a transfer learning system based on near-infrared spectral data","volume":"31","author":"Shi","year":"2020","journal-title":"J. For. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"104499","DOI":"10.1016\/j.chemolab.2022.104499","article-title":"Domain invariant covariate selection (Di-CovSel) for selecting generalized features across domains","volume":"222","author":"Diaz","year":"2022","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"2220","DOI":"10.1021\/acs.jcim.0c01493","article-title":"Reliable Model Selection without Reference Values by Utilizing Model Diversity with Prediction Similarity","volume":"61","author":"Spiers","year":"2021","journal-title":"J. Chem Inf Model."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A Comprehensive Survey on Transfer Learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc. IEEE"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"107781","DOI":"10.1016\/j.compeleceng.2022.107781","article-title":"An infrared pedestrian detection method based on segmentation and domain adaptation learning","volume":"99","author":"Zhang","year":"2022","journal-title":"Comput. Electr. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Nikisins, O., George, A., and Marcel, S. (2019, January 4\u20137). Domain Adaptation in Multi-Channel Autoencoder based Features for Robust Face Anti-Spoofing. Proceedings of the 2019 International Conference on Biometrics (ICB), Crete, Greece.","DOI":"10.1109\/ICB45273.2019.8987247"},{"key":"ref_31","first-page":"12023","article-title":"Multi-spectral salient object detection by adversarial domain adaptation","volume":"34","author":"Song","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1109\/TMM.2020.3046868","article-title":"Deep Domain Adaptation Based Multi-Spectral Salient Object Detection","volume":"24","author":"Song","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"ref_33","first-page":"1","article-title":"Domain-adversarial training of neural networks","volume":"17","author":"Ganin","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref_34","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., and Chen, X. (2016, January 5\u201310). Improved techniques for training GANs. Proceedings of the Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, Barcelona, Spain."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","article-title":"A review of uncertainty quantification in deep learning: Techniques, applications and challenges","volume":"76","author":"Abdar","year":"2021","journal-title":"Inf. Fusion"},{"key":"ref_36","unstructured":"Molnar, C. (2022, August 18). Interpretable Machine Learning: A Guide for Making Black Box Models Explainable (2nd ed.). Available online: Christophm.github.io\/interpretable-ml-book\/."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"620","DOI":"10.1016\/j.powtec.2020.12.030","article-title":"Rapid and non-destructive determination of protein and starch content in agricultural powders using near-infrared and fluorescence spectroscopy, and data fusion","volume":"381","author":"Vitelli","year":"2021","journal-title":"Powder Technol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1016\/j.tifs.2020.05.002","article-title":"Review of NIR spectroscopy methods for nondestructive quality analysis of oilseeds and edible oils","volume":"101","author":"Li","year":"2020","journal-title":"Trends Food Sci. Technol."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Rady, A., Fischer, J., Reeves, S., Logan, B., and Watson, N.J. (2020). The effect of light intensity, sensor height, and spectral pre-processing methods when using nir spectroscopy to identify different allergen- containing powdered foods. Sensors, 20.","DOI":"10.3390\/s20010230"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Pu, Y., P\u00e9rez-Mar\u00edn, D., O\u2019Shea, N., and Garrido-Varo, A. (2021). Recent advances in portable and handheld NIR spectrometers and applications in milk, cheese and dairy powders. Foods, 10.","DOI":"10.3390\/foods10102377"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"104287","DOI":"10.1016\/j.chemolab.2021.104287","article-title":"A synergistic use of chemometrics and deep learning improved the predictive performance of near-infrared spectroscopy models for dry matter prediction in mango fruit","volume":"212","author":"Mishra","year":"2021","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"103547","DOI":"10.1016\/j.infrared.2020.103547","article-title":"Partial least square regression versus domain invariant partial least square regression with application to near-infrared spectroscopy of fresh fruit","volume":"111","author":"Mishra","year":"2020","journal-title":"Infrared Phys. Technol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"111326","DOI":"10.1016\/j.postharvbio.2020.111326","article-title":"Two standard-free approaches to correct for external influences on near-infrared spectra to make models widely applicable","volume":"170","author":"Mishra","year":"2020","journal-title":"Postharvest Biol. Technol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7239\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:38:38Z","timestamp":1760143118000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,24]]},"references-count":43,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22197239"],"URL":"https:\/\/doi.org\/10.3390\/s22197239","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,24]]}}}