Comparison of different classification methods for analyzing fluorescence spectra to characterize type and freshness of olive oils

Anna Dankowska , Wojciech Kowalewski


The potential of synchronous fluorescence spectroscopic measurements for the classification of olive oil samples with respect to type (extra virgin/refined) and shelf-life condition (expired/non-expired) was examined. Data multidimensionality was reduced by application of the PCA method. Six classification methods, namely, LDA, QDA, RDA, KNN, SVM, and RF, were used to analyze fluorescence data. Classification accuracy was employed to evaluate the performance of these methods for the classification of olive oil samples. The results indicate that fresh and expired olive oils produced with different methods, extra virgin (cold pressed) and refined, are characterized by different fluorescence spectra. KNN and SVM outperform the other classification methods in distinguishing olive oils. The lowest classification error rates were obtained with these two classification methods for measurements at the wavelength interval of 30 nm, and equaled 5.4, 5.7 and 2.9, 3.5% for the four and three classes’ models, respectively.
Author Anna Dankowska (WT / KTAS)
Anna Dankowska,,
- Department of Food Commodity Science
, Wojciech Kowalewski - Adam Mickiewicz University (UAM)
Wojciech Kowalewski,,
Journal seriesEuropean Food Research and Technology, ISSN 1438-2377, e-ISSN 1438-2385, (N/A 70 pkt)
Issue year2019
Publication size in sheets0.5
Keywords in Polishzafałszowania, oliwa z oliwek, fluorymetria, chemometria, metody kasyfikacji
Keywords in Englishadulteration, olive ois, fluorimetry, chemoemtic methods, classifcation methods
ASJC Classification1106 Food Science; 1303 Biochemistry; 1305 Biotechnology; 1600 General Chemistry; 2209 Industrial and Manufacturing Engineering
Languageen angielski
Score (nominal)70
Score sourcejournalList
ScoreMinisterial score = 70.0, 07-04-2020, ArticleFromJournal
Publication indicators WoS Citations = 2; Scopus SNIP (Source Normalised Impact per Paper): 2018 = 0.943; WoS Impact Factor: 2018 = 2.056 (2) - 2018=2.093 (5)
Citation count*
Share Share

Get link to the record

* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.
Are you sure?