Szczegóły publikacji
Opis bibliograficzny
Computer vision analysis of sample colors versus quadruple-disk iridium-platinum voltammetric e-tongue for recognition of natural honey adulteration / Szymon WÓJCIK, Filip CIEPIELA, Małgorzata JAKUBOWSKA // Measurement ; ISSN 0263-2241. — 2023 — vol. 209 art. no. 112514, s. 1-15. — Bibliogr. s. 13-15, Abstr. — Publikacja dostępna online od: 2023-01-24
Autorzy (3)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 145014 |
|---|---|
| Data dodania do BaDAP | 2023-01-31 |
| Tekst źródłowy | URL |
| DOI | 10.1016/j.measurement.2023.112514 |
| Rok publikacji | 2023 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Czasopismo/seria | Measurement |
Abstract
This work presents a deep learning approach for computer vision-based recognition of natural honey adulteration. The results are compared with the machine learning models using chemical data obtained with an innovative bimetallic voltammetric electrode that acts as an e-tongue. Computer vision is based on the recognition of the color of the sample, which changes with the addition of undesirable synthetic substances. The pictures were taken with a smartphone under controlled conditions using seven different background illumination colors for samples that contained 0 – 50 % foreign additives. In the best case root mean square error (RMSE) in the regression approach was 0.46 % for the external test set at R2 = 0.9993, calculated as a compatibility evaluation between the true values and the prediction result. The minimum RMSE for the voltammetric measurements on the quadruple-disk iridium-platinum electrode and the regression algorithms PCR, PLSR, and SVR was 0.25 % with R2 = 0.9998. It has been shown that when food adulteration affects its color, it is possible to successfully replace the classical e-tongue with computer vision. The convenient, rapid, and nondestructive approach does not require the use of equipment, reagents, or solvents and laboratory work techniques typical for analytical chemistry.
