{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T11:21:36Z","timestamp":1777375296017,"version":"3.51.4"},"reference-count":21,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ayd\u0131n Adnan Menderes University Scientific Research Projects Coordination Unit","award":["MF-24012"],"award-info":[{"award-number":["MF-24012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biosensors"],"abstract":"<jats:p>In this study, a low-cost AS7265x-based multispectral electronic tongue system was developed for estimating milk composition and adulteration indicators and supported with an explainable artificial intelligence (XAI) framework. Experimental analyses were conducted on 190 augmented commercial milk samples, where fat, protein, solids-not-fat (SNF), density, freezing point, and added water ratio were treated as target variables. Sensor data were modeled as RAW, DERIVED, and FUSION feature sets, and regression performance was compared using Random Forest, Gradient Boosting, AdaBoost, KNN, and XGBoost. Model validation was carried out with both five-fold cross-validation and Leave-One-Out (LOO) strategies to assess field-level generalizability. Results showed that a narrow-band, low-cost optical sensor platform can estimate not only fat and protein but also SNF, density, and freezing point with high accuracy. Within the XAI framework, permutation-based importance analysis and SHAP were used to identify critical spectral bands for each target parameter, enabling data-driven recommendations for band-oriented sensor design optimization. The study presents a scalable methodology that integrates low-cost sensor design, multi-parameter quality estimation, and explainable modeling beyond traditional fat\u2013protein-focused approaches. Across all six targets, the XAI analysis consistently identified the near-infrared channel at 860 nm (asIR_3) as the most informative band, reflecting the combined effect of water absorption and Mie scattering by fat globules; the visible channel at 680 nm (asVIS_4) emerged as a secondary band, reflecting dissolved-matter scattering. These bands are therefore the natural starting point for cost-reduced versions of the sensor. Among the compared feature sets (RAW, DERIVED, FUSION), the 18-band RAW configuration provided the most balanced performance across all six targets.<\/jats:p>","DOI":"10.3390\/bios16050245","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T08:12:31Z","timestamp":1777363951000},"page":"245","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["XAI-Supported Electronic Tongue for Estimating Milk Composition and Adulteration Indicators"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9849-3338","authenticated-orcid":false,"given":"Ahmet \u00c7a\u011fda\u015f","family":"Se\u00e7kin","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Ayd\u0131n Adnan Menderes University, 09010 Aydin, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8875-0775","authenticated-orcid":false,"given":"Murat","family":"Ekici","sequence":"additional","affiliation":[{"name":"Civil Air Transportation Management Program, Efes Vocational School, Dokuz Eyl\u00fcl University, 35920 Izmir, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2488-5769","authenticated-orcid":false,"given":"Tolga","family":"Akcan","sequence":"additional","affiliation":[{"name":"Food Processing Department, Efes Vocational School, Dokuz Eyl\u00fcl University, 35920 Izmir, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8426-2283","authenticated-orcid":false,"given":"Fatih","family":"Soygazi","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Ayd\u0131n Adnan Menderes University, 09010 Aydin, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Habibe","family":"G\u00fcrsoy Demir","sequence":"additional","affiliation":[{"name":"Department of Aerospace Engineering, Faculty of Aeronautics and Astronautics, Iskenderun Technical University, 31200 Hatay, T\u00fcrkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Vanaraj, R., IP, B., Mayakrishnan, G., Kim, I.S., and Kim, S.-C. (2025). A Systematic Review of the Applications of Electronic Nose and Electronic Tongue in Food Quality Assessment and Safety. Chemosensors, 13.","DOI":"10.3390\/chemosensors13050161"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Gil, M., Rudy, M., Duma-Kocan, P., and Stanis\u0142awczyk, R. (2025). Electronic Sensing Technologies in Food Quality Assessment: A Comprehensive Literature Review. Appl. Sci., 15.","DOI":"10.3390\/app15031530"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"0713","DOI":"10.34133\/research.0713","article-title":"Advancements in Intelligent Sensing Technologies for Food Safety Detection","volume":"8","author":"Jiang","year":"2025","journal-title":"Research"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"105823","DOI":"10.1016\/j.compag.2020.105823","article-title":"A Cost-Effective on-Site Milk Analyzer Based on Multispectral Sensor","volume":"179","author":"Yang","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1080\/10408398.2020.1731417","article-title":"Recent Developments on Rapid Detection of Main Constituents in Milk: A Review","volume":"61","author":"Zhu","year":"2021","journal-title":"Crit. Rev. Food Sci. Nutr."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"107746","DOI":"10.1016\/j.microc.2022.107746","article-title":"Low-Cost Spectroscopic Devices with Multivariate Analysis Applied to Milk Authenticity","volume":"181","author":"Galvan","year":"2022","journal-title":"Microchem. J."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Hayes, E., Greene, D., O\u2019Donnell, C., O\u2019Shea, N., and Fenelon, M.A. (2023). Spectroscopic Technologies and Data Fusion: Applications for the Dairy Industry. Front. Nutr., 9.","DOI":"10.3389\/fnut.2022.1074688"},{"key":"ref_8","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_9","doi-asserted-by":"crossref","unstructured":"Agiomavriti, A.-A., Nikolopoulou, M.P., Bartzanas, T., Chorianopoulos, N., Demestichas, K., and Gelasakis, A.I. (2024). Spectroscopy-Based Methods and Supervised Machine Learning Applications for Milk Chemical Analysis in Dairy Ruminants. Chemosensors, 12.","DOI":"10.20944\/preprints202411.0204.v1"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gast\u00e9lum-Barrios, A., Soto-Zaraz\u00faa, G.M., Escamilla-Garc\u00eda, A., Toledano-Ayala, M., Mac\u00edas-Bobadilla, G., and Jauregui-Vazquez, D. (2020). Optical Methods Based on Ultraviolet, Visible, and Near-Infrared Spectra to Estimate Fat and Protein in Raw Milk: A Review. Sensors, 20.","DOI":"10.3390\/s20123356"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"103388","DOI":"10.1016\/j.jfca.2019.103388","article-title":"Milk Quality Control Requirement Evaluation Using a Handheld near Infrared Reflectance Spectrophotometer and a Bespoke Mobile Application","volume":"86","year":"2020","journal-title":"J. Food Compos. Anal."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Riu, J., Gorla, G., Chakif, D., Boqu\u00e9, R., and Giussani, B. (2020). Rapid Analysis of Milk Using Low-Cost Pocket-Size NIR Spectrometers and Multivariate Analysis. Foods, 9.","DOI":"10.3390\/foods9081090"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"105734","DOI":"10.1016\/j.compag.2020.105734","article-title":"Online Milk Composition Analysis with an On-Farm near-Infrared Sensor","volume":"178","author":"Adriaens","year":"2020","journal-title":"Comput. Electron. Agric."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Durgun, M. (2024). Real-Time Milk Quality Control Using Multi-Spectral Sensing and Edge Computing: Advancing On-Site Detection of Milk Components with XGBoost. Appl. Sci., 14.","DOI":"10.3390\/app142310916"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wang, Y., Zhang, K., Shi, S., Wang, Q., and Liu, S. (2023). Portable Protein and Fat Detector in Milk Based on Multi-Spectral Sensor and Machine Learning. Appl. Sci., 13.","DOI":"10.2139\/ssrn.4519655"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"110495","DOI":"10.1016\/j.foodcont.2024.110495","article-title":"XAI-Empowered IoT Multi-Sensor System for Real-Time Milk Adulteration Detection","volume":"164","author":"Goyal","year":"2024","journal-title":"Food Control"},{"key":"ref_17","unstructured":"(2008). Milk\u2014Determination of Fat Content (Standard No. ISO 2446:2008|IDF 226:2008)."},{"key":"ref_18","unstructured":"(2014). Milk and Milk Products\u2014Determination of Nitrogen Content\u2014Part 1: Kjeldahl Principle and Crude Protein Calculation (Standard No. ISO 8968-1:2014)."},{"key":"ref_19","unstructured":"(2010). Milk, Cream and Evaporated Milk\u2014Determination of Total Solids Content (Standard No. ISO 6731:2010)."},{"key":"ref_20","unstructured":"(2009). Milk\u2014Determination of Freezing Point\u2014Thermistor Cryoscope Method (Standard No. ISO 5764:2009)."},{"key":"ref_21","unstructured":"(2026, February 24). AS7265x-Triad Spectroscopy Sensor. Available online: https:\/\/cdn.sparkfun.com\/assets\/c\/2\/9\/0\/a\/AS7265x_Datasheet.pdf."}],"container-title":["Biosensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-6374\/16\/5\/245\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:01:20Z","timestamp":1777366880000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-6374\/16\/5\/245"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":21,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["bios16050245"],"URL":"https:\/\/doi.org\/10.3390\/bios16050245","relation":{},"ISSN":["2079-6374"],"issn-type":[{"value":"2079-6374","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,27]]}}}