WSEAS Transactions on Environment and Development
Print ISSN: 1790-5079, E-ISSN: 2224-3496
Volume 21, 2025
Prediction of PDO Kalamata Olive Oil Tasting Quality based on Statistical Machine Learning Techniques Utilizing Real Data from Synchronous Emission-Excitation Fluorescence Spectra and Tasting Analyses
Authors: , ,
Search Articles
Abstract: Combining domain knowledge provided by analyses of Protected Designation of Origin (PDO) Kalamata olive oil data sources could input multiclass classification statistical machine learning models to output accurate predictions of certain olive oil quality classes. Concretely, machine learning models are trained with both synchronous emission-excitation fluorescence spectra provided by certain spectroscopic techniques with tasting analyses of domain tasting panelists to infer the quality class of the input sample. Such a process enhances tasting panelists specific tasting knowledge by supporting their prediction accuracy with chemical data of certain real olive oil data samples. In this research effort, real PDO Kalamata olive oil data is used from fluorescence spectra and tasting processes to train multiclass classification statistical machine learning models to provide accurate predictions of the examined olive oil samples’ quality classes.
Keywords:
PDO Kalamata olive oil, statistical machine learning, multiclass classification, synchronous
emission-excitation fluorescence spectra, spectroscopic techniques, tasting analyses, domain
tasting panelists, prediction accuracy and Chi-Square significance test, real data
Pages: 775-785
DOI: 10.37394/232015.2025.21.64