{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T17:42:12Z","timestamp":1793727732388,"version":"4.6.1"},"reference-count":26,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T00:00:00Z","timestamp":1787356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Foods"],"abstract":"<jats:p>Economically motivated adulteration of olive oil, coffee and fruit juice is a persistent food-fraud problem for which Fourier-transform infrared (FTIR) spectroscopy with chemometrics offers rapid screening. Linear partial least squares (PLS) is interpretable but cannot capture non-linear mixing; neural networks add flexibility at the cost of becoming black boxes. We evaluated a Kolmogorov\u2013Arnold network (KAN), which places learnable univariate functions on its edges and is therefore intrinsically interpretable, against PLS, support-vector regression, random forests, a multilayer perceptron and a one-dimensional convolutional network on three attenuated total reflectance (ATR)\u2013FTIR datasets (olive oil + sunflower oil, coffee + malt flour, orange juice + apple juice; approximately 350, 400 and 400 spectra). All models were compared under identical, leakage-free validation that splits spectra by physical sample. The compact KAN was consistently competitive (cross-validated coefficients of determination (R2) = 0.86, 0.93 and 0.69) and yielded closed-form equations whose variables map to recognised vibrational bands and whose importance ranking agrees with SHapley Additive exPlanations (SHAP; Spearman \u03c1 = 0.86\u20130.90); symbolic conversion costs no accuracy. We also report the following limits: PLS was strongest where the chemistry was linear (coffee) and the multilayer perceptron was strongest on fruit juice, whose equation is the weakest (R2 = 0.47\u20130.75 across seeds); a parameter-matched perceptron matched the KAN\u2019s accuracy; and leave-one-brand-out validation degraded every model. The KAN is therefore a promising, compact and genuinely transparent alternative under controlled multi-matrix conditions, not a deployment-ready method.<\/jats:p>","DOI":"10.3390\/foods15172949","type":"journal-article","created":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T09:20:02Z","timestamp":1787563202000},"page":"2949","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["An Interpretable Kolmogorov\u2013Arnold Network for FTIR Detection and Quantification of Adulteration Across Diverse Food Matrices"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0374-6755","authenticated-orcid":false,"given":"Abdulhamid","family":"Batayhi","sequence":"first","affiliation":[{"name":"Department of Mechatronics Engineering, Faculty of Mechanical Engineering, Yildiz Technical University, 34220 Istanbul, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5584-097X","authenticated-orcid":false,"given":"Muhammed","family":"\u00d6zg\u00f6let","sequence":"additional","affiliation":[{"name":"Department of Food Engineering, Faculty of Chemical and Metallurgical Engineering, Yildiz Technical University, 34220 Istanbul, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2063-1462","authenticated-orcid":false,"given":"Osman","family":"Sagdic","sequence":"additional","affiliation":[{"name":"Department of Food Engineering, Faculty of Chemical and Metallurgical Engineering, Yildiz Technical University, 34220 Istanbul, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1366\/0003702053945921","article-title":"Detection of apple juice adulteration using near-infrared transflectance spectroscopy","volume":"59","author":"Kelly","year":"2005","journal-title":"Appl. Spectrosc."},{"key":"ref_2","first-page":"1","article-title":"Infrared spectroscopy in the study of edible oils and fats","volume":"75","author":"Cabo","year":"1997","journal-title":"J. Sci. Food Agric."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.foodres.2013.08.041","article-title":"Vibrational spectroscopy and chemometrics to assess authenticity, adulteration and intrinsic quality parameters of edible oils and fats","volume":"60","author":"Nunes","year":"2014","journal-title":"Food Res. Int."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0169-7439(01)00155-1","article-title":"PLS-regression: A basic tool of chemometrics","volume":"58","author":"Wold","year":"2001","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1366\/0003702894202201","article-title":"Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra","volume":"43","author":"Barnes","year":"1989","journal-title":"Appl. Spectrosc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1021\/ac60214a047","article-title":"Smoothing and differentiation of data by simplified least squares procedures","volume":"36","author":"Savitzky","year":"1964","journal-title":"Anal. Chem."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.chemolab.2018.07.008","article-title":"Modern practical convolutional neural networks for multivariate regression: Applications to NIR calibration","volume":"182","author":"Cui","year":"2018","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_10","unstructured":"Lundberg, S.M., and Lee, S.-I. (2017). A unified approach to interpreting model predictions. arXiv."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Solja\u010di\u0107, M., Hou, T.Y., and Tegmark, M. (2024). KAN: Kolmogorov\u2013Arnold networks. arXiv.","DOI":"10.1103\/4t7t-v19l"},{"key":"ref_12","first-page":"041051","article-title":"Kolmogorov\u2013Arnold networks meet science","volume":"15","author":"Liu","year":"2025","journal-title":"Phys. Rev. X"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Zhang, J., Dou, Y., Zhang, P., Shu, X., and Lei, M. (2025). Radial basis function Kolmogorov\u2013Arnold network for coal calorific value prediction using portable near-infrared spectroscopy. Processes, 13.","DOI":"10.3390\/pr13113623"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1080\/00032719.2025.2555931","article-title":"Application of the frequency-domain Kolmogorov\u2013Arnold networks model in cancer screening and classification using serum surface-enhanced Raman scattering","volume":"59","author":"Li","year":"2025","journal-title":"Anal. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1002\/jrs.70085","article-title":"A multi-scale residual network based on Kolmogorov\u2013Arnold networks combined with Raman spectroscopy for rapid diagnosis of membranous glomerulonephritis","volume":"57","author":"Chang","year":"2026","journal-title":"J. Raman Spectrosc."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1039\/D5AN00834D","article-title":"Boosting living Bacillus spore identification: Kolmogorov\u2013Arnold network-guided convolutional neural network combined with laser tweezers Raman spectroscopy","volume":"151","author":"Sun","year":"2026","journal-title":"Analyst"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Dasenaki, M.E., and Thomaidis, N.S. (2019). Quality and authenticity control of fruit juices\u2014A review. Molecules, 24.","DOI":"10.3390\/molecules24061014"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1080\/10408347.2014.966185","article-title":"Coffee adulteration: More than two decades of research","volume":"46","author":"Toci","year":"2016","journal-title":"Crit. Rev. Anal. Chem."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Ordoudi, S.A., Strani, L., and Cocchi, M. (2023). Toward the non-targeted detection of adulterated virgin olive oil with edible oils via FTIR spectroscopy & chemometrics: Research methodology trends, gaps and future perspectives. Molecules, 28.","DOI":"10.3390\/molecules28010337"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"886","DOI":"10.1016\/j.foodres.2009.12.006","article-title":"Fourier transform infrared (FTIR) spectroscopy for analysis of extra virgin olive oil adulterated with palm oil","volume":"43","author":"Rohman","year":"2010","journal-title":"Food Res. Int."},{"key":"ref_21","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_22","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An imperative style, high-performance deep learning library. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"4974173","DOI":"10.1155\/2016\/4974173","article-title":"Concomitant use of Fourier transform infrared attenuated total reflectance spectroscopy and chemometrics for quantification of multiple adulterants in roasted and ground coffee","volume":"2016","author":"Reis","year":"2016","journal-title":"J. Spectrosc."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.chemolab.2011.05.006","article-title":"Model calibration and feature selection for orange juice authentication by 1H NMR spectroscopy","volume":"117","author":"Vigneau","year":"2012","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"109304","DOI":"10.1016\/j.microc.2023.109304","article-title":"An innovative screening approach for orange juice authentication using dual portable\/handheld NIR spectrometers and chemometrics","volume":"194","author":"Ehsani","year":"2023","journal-title":"Microchem. J."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"128647","DOI":"10.1016\/j.foodchem.2020.128647","article-title":"Comparison of near-infrared (NIR) and mid-infrared (MIR) spectroscopy based on chemometrics for saffron authentication and adulteration detection","volume":"344","author":"Amirvaresi","year":"2021","journal-title":"Food Chem."}],"container-title":["Foods"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2304-8158\/15\/17\/2949\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T09:53:34Z","timestamp":1787565214000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2304-8158\/15\/17\/2949"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,22]]},"references-count":26,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["foods15172949"],"URL":"https:\/\/doi.org\/10.3390\/foods15172949","relation":{},"ISSN":["2304-8158"],"issn-type":[{"value":"2304-8158","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,22]]}}}