Dataset of Fluorescence Spectra and Chemical Parameters of Olive Oils
This dataset encompasses fluorescence spectra and chemical parameters of 24 olive oil samples from the 2019–2020 harvest provided by the producer Conde de Benalúa, Granada, Spain. The oils are characterized by different qualities: 10 extra virgin olive oil (EVOO), 8 virgin olive oil (VOO), and 6 lampante olive oil (LOO) samples. For each sample, the dataset includes fluorescence spectra obtained with two excitation wavelengths and five chemical parameters necessary for the quality assessment of olive oil. The fluorescence spectra were obtained by exciting the samples at 395 nm and 365 nm and collecting the signal with a miniature spectrometer with a 1024-element CCD array with a resolution of 16 nm. Each olive oil sample was measured 20 times under identical conditions for excitation at 365 nm and 395 nm. Therefore, the dataset includes a total of 960 spectra (24 oil samples × 2 excitation wavelengths x 20 measurements). Each of the 960 spectra is an array of 1024 values whose elements are the intensity at the different pixel positions. For each olive oil sample, the dataset includes the values of the following chemical parameters: acidity, peroxide value, K_270, K_232, ethyl esters, and the quality of the samples (EVOO, VOO, or LOO). The chemical analysis of all the samples was performed by accredited laboratories according to the current European regulation. The dataset offers a unique possibility for researchers in food technology to develop machine learning models due to the availability of both spectroscopical and chemical data. The dataset can be used, for example, to predict one or multiple chemical parameters or to classify samples based on their quality from fluorescence spectra.
Steps to reproduce
The details about the dataset are contained in the data in Brief paper linked. The file format is Python pickle and the result is a pandas data frame.