{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T05:08:53Z","timestamp":1787029733566,"version":"build-2736575974"},"reference-count":41,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T00:00:00Z","timestamp":1769731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0199500"],"award-info":[{"award-number":["2024YFE0199500"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Ethanol stability is an important indicator for evaluating the quality and heat-processing suitability of raw milk. Traditional ethanol stability testing relies on destructive laboratory procedures, which are not suitable for large-scale industrial use. In contrast, parameters such as protein, fat, lactose and other basic compositional indicators are already measured routinely in dairy plants through sensor-based or spectroscopic systems. This provides the basis for developing a non-destructive soft sensing approach for ethanol stability. In this study, a soft sensing model was developed to predict ethanol stability from commonly monitored raw-milk intake indicators. An autoencoder was used to examine feature correlations and select variables with stronger relevance to ethanol stability. TabNet was then applied to build the classification model, and a TabDDPM-based data generation method was introduced to address class imbalance in the dataset. The proposed model was trained and tested using three years of industrial raw-milk intake data from a dairy company. It achieved an accuracy of 92.57% and a recall of 90.26% for identifying ethanol-unstable samples. These results demonstrate the model\u2019s strong potential for practical engineering applications in real-world dairy quality monitoring.<\/jats:p>","DOI":"10.3390\/s26030903","type":"journal-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T13:04:46Z","timestamp":1769778286000},"page":"903","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Data-Driven Soft Sensing for Raw Milk Ethanol Stability Prediction"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0522-169X","authenticated-orcid":false,"given":"Song","family":"Shen","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Song","sequence":"additional","affiliation":[{"name":"Key Laboratory of Dairy Quality Digital Intelligence Monitoring Technology, Hohhot 011517, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7921-6629","authenticated-orcid":false,"given":"Haohan","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China"},{"name":"Science Center for Future Foods, Jiangnan University, Wuxi 214122, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China"},{"name":"Science Center for Future Foods, Jiangnan University, Wuxi 214122, China"},{"name":"School of Cyber Science and Engineering, Wuhan University, Wuhan 430079, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenqi","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Chemical & Materials Engineering, University of Auckland, Auckland 1010, New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huadi","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanjun","family":"Dong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Dairy Quality Digital Intelligence Monitoring Technology, Hohhot 011517, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"15","DOI":"10.3738\/21751463.3734","article-title":"Factors that affect the thermal stability of bovine milk and the use of alcohol test in the milk industry\u2014A review","volume":"12","author":"Angelo","year":"2020","journal-title":"Nucl. Anim."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2787","DOI":"10.1002\/jsfa.8775","article-title":"Field findings about milk ethanol stability: A first report of interrelationship between \u03b1-lactalbumin and lactose","volume":"98","author":"Fagnani","year":"2018","journal-title":"J. Sci. Food Agric."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1080\/10942912.2016.1152480","article-title":"Effects of milk pH alteration on casein micelle size and gelation properties of milk","volume":"20","author":"Sinaga","year":"2017","journal-title":"Int. J. Food Prop."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Alhaj, O.A., Lajnaf, R., Jrad, Z., Alshuniaber, M.A., Jahrami, H.A., and Serag El-Din, M.F. (2022). Comparison of ethanol stability and chemical composition of camel milk from five samples. Animals, 12.","DOI":"10.3390\/ani12050615"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1017\/S0022029900021695","article-title":"Factors affecting the ethanol stability of bovine milk.: I. Effect of serum phase components","volume":"48","author":"Horne","year":"1981","journal-title":"J. Dairy Res."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"11413","DOI":"10.3168\/jds.2021-20201","article-title":"Type A and B bovine milks: Heat stability is driven by different physicochemical parameters","volume":"104","author":"Loveday","year":"2021","journal-title":"J. Dairy Sci."},{"key":"ref_7","unstructured":"(2013). Milk and Liquid Milk Products\u2014Guidelines for the Application of Mid-Infrared Spectrometry (Standard No. ISO 9622:2013|IDF 141:2013)."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"7585","DOI":"10.1007\/s11694-024-02750-0","article-title":"The impedance-based detection of total bacterial content in raw milk samples","volume":"18","author":"Rajabzadeh","year":"2024","journal-title":"J. Food Meas. Charact."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"7438","DOI":"10.3168\/jds.2020-19576","article-title":"Predicting cow milk quality traits from routinely available milk spectra using statistical machine learning methods","volume":"104","author":"Frizzarin","year":"2021","journal-title":"J. Dairy Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1007\/s11831-021-09600-y","article-title":"Food adulteration detection using artificial intelligence: A systematic review","volume":"29","author":"Goyal","year":"2022","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1017\/S0022029904000172","article-title":"Bovine milk composition parameters affecting the ethanol stability","volume":"71","author":"Chavez","year":"2004","journal-title":"J. Dairy Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1007\/s11483-016-9430-y","article-title":"Alcohol stability of milk from the perspective of X-ray diffractometry","volume":"11","author":"Fagnani","year":"2016","journal-title":"Food Biophys."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Horne, D.S. (2016). Ethanol stability and milk composition. Advanced Dairy Chemistry: Volume 1B: Proteins: Applied Aspects, Springer Nature.","DOI":"10.1007\/978-1-4939-2800-2_9"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Arik, S.\u00d6., and Pfister, T. (2021, January 2\u20139). Tabnet: Attentive interpretable tabular learning. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v35i8.16826"},{"key":"ref_15","unstructured":"Kotelnikov, A., Baranchuk, D., Rubachev, I., and Babenko, A. (2023, January 23\u201329). Tabddpm: Modelling tabular data with diffusion models. Proceedings of the International Conference on Machine Learning, Honolulu, HI, USA."},{"key":"ref_16","unstructured":"(1986). Milk\u2014Determination of Stability (Standard No. GB\/T 6914-1986)."},{"key":"ref_17","unstructured":"(2013). Microbiology of the Food Chain\u2014Horizontal Method for the Enumeration of Microorganisms\u2014Part 1: Colony Count at 30 \u00b0C by the Pour Plate Technique (Standard No. ISO 4833-1:2013)."},{"key":"ref_18","unstructured":"(2010). Milk, Cream and Evaporated Milk\u2014Determination of Total Solids Content (Reference Method) (Standard No. ISO 6731:2010|IDF 21:2010)."},{"key":"ref_19","unstructured":"(2010). Dried Milk\u2014Determination of Titratable Acidity (Reference Method) (Standard No. ISO 6091:2010|IDF 86:2010)."},{"key":"ref_20","unstructured":"(2009). Milk\u2014Determination of Freezing Point\u2014Thermistor Cryoscope Method (Reference Method) (Standard No. ISO 5764:2009|IDF 108:2009)."},{"key":"ref_21","unstructured":"(2008). Milk\u2014Enumeration of Somatic Cells\u2014Part 1: Microscopic Method (Reference Method) (Standard No. ISO 13366-1:2008|IDF 148-1:2008)."},{"key":"ref_22","unstructured":"(2019). Microbiology of the Food Chain\u2014Horizontal Method for the Enumeration of Psychrotrophic Microorganisms (Standard No. ISO 17410:2019)."},{"key":"ref_23","unstructured":"(2024). Crude Petroleum, Petroleum Products and Related Products\u2014Determination of Density\u2014Laboratory Density Meter with an Oscillating U-Tube Sensor (Standard No. ISO 12185:2024)."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"163","DOI":"10.55730\/1300-0632.3977","article-title":"Variational autoencoder-based anomaly detection in time series data for inventory record inaccuracy","volume":"31","author":"Alptekin","year":"2023","journal-title":"Turk. J. Electr. Eng. Comput. Sci."},{"key":"ref_25","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"369","DOI":"10.2298\/CICEQ180606015L","article-title":"Modeling of milk lactose removal by column adsorption using artificial neural networks: Mlp and Rbf","volume":"25","author":"Leite","year":"2019","journal-title":"Chem. Ind. Chem. Eng. Q."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"111913","DOI":"10.1016\/j.fct.2020.111913","article-title":"Occurrence, exposure evaluation and risk assessment in child population for aflatoxin M1 in dairy products in Brazil","volume":"148","author":"Pante","year":"2021","journal-title":"Food Chem. Toxicol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Ayyadevara, V.K. (2018). Gradient boosting machine. Pro Machine Learning Algorithms: A Hands-On Approach to Implementing Algorithms in Python and R, Springer.","DOI":"10.1007\/978-1-4842-3564-5"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1139","DOI":"10.1016\/j.idairyj.2006.12.012","article-title":"An international ring trial for the sensory evaluation of raw ewes\u2019 milk cheese texture","volume":"17","author":"Elortondo","year":"2007","journal-title":"Int. Dairy J."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kornbrot, D. (2014). Point biserial correlation. Wiley StatsRef: Statistics Reference Online, Wiley Online Library.","DOI":"10.1002\/9781118445112.stat06227"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Menze, B.H., Kelm, B.M., Masuch, R., Himmelreich, U., Bachert, P., Petrich, W., and Hamprecht, F.A. (2009). A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinform., 10.","DOI":"10.1186\/1471-2105-10-213"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1409","DOI":"10.1093\/sf\/89.4.1409","article-title":"Standards for standardized logistic regression coefficients","volume":"89","author":"Menard","year":"2011","journal-title":"Soc. Forces"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Mu, F., Gu, Y., Zhang, J., and Zhang, L. (2020). Milk source identification and milk quality estimation using an electronic nose and machine learning techniques. Sensors, 20.","DOI":"10.3390\/s20154238"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Fizza, K., Banerjee, A., Georgakopoulos, D., Jayaraman, P.P., Yavari, A., and Dawod, A. (2025). An Inexpensive AI-Powered IoT Sensor for Continuous Farm-to-Factory Milk Quality Monitoring. Sensors, 25.","DOI":"10.3390\/s25144439"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"9647","DOI":"10.1007\/s11947-025-03971-x","article-title":"Predicting spoilage intensity level in sausage products using explainable machine learning and GAN-Based data augmentation","volume":"18","author":"Ince","year":"2025","journal-title":"Food Bioprocess Technol."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Koh, G., Oh, H.-J., Noh, J., and Jeong, W.-K. (2025, January 11\u201315). Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPRW67362.2025.00043"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ding, H., Xie, Z., Wang, C., Yu, W., Cui, X., and Wang, Z. (2024). Applications of big data and blockchain technology in food testing and their exploration on educational reform. Foods, 13.","DOI":"10.3390\/foods13213391"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1016\/j.foodcont.2016.09.048","article-title":"Food safety pre-warning system based on data mining for a sustainable food supply chain","volume":"73","author":"Wang","year":"2017","journal-title":"Food Control"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"110136","DOI":"10.1016\/j.foodcont.2023.110136","article-title":"A new data analysis approach for an AgNPs-modified impedimetric bioelectronic tongue for dairy analysis","volume":"156","year":"2024","journal-title":"Food Control"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Fern\u00e1ndez Gonz\u00e1lez, A., Bad\u00eda La\u00ed\u00f1o, R., Costa-Fern\u00e1ndez, J.M., and Soldado, A. (2024). Progress and challenge of sensors for dairy food safety monitoring. Sensors, 24.","DOI":"10.3390\/s24051383"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Song, X., Shen, S., Dong, G., Ding, H., Xie, Z., Wang, L., and Cheng, W. (2025). A comprehensive review of direct, indirect, and AI-based detection methods for milk powder. Front. Sustain. Food Syst., 9.","DOI":"10.3389\/fsufs.2025.1571317"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/903\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T13:06:20Z","timestamp":1769778380000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/903"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,30]]},"references-count":41,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["s26030903"],"URL":"https:\/\/doi.org\/10.3390\/s26030903","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,30]]}}}