Machine learning feature extraction for predicting the ageing of olive oil

被引:0
|
作者
Gucciardi, Arnaud [1 ,2 ]
El Ghazouali, Safouane [1 ]
Michelucci, Umberto [1 ,3 ]
Venturini, Francesca [1 ,4 ]
机构
[1] TOELT llc, Machine Learning Res & Dev, Birchlenstr 25, CH-8600 Dubendorf, Switzerland
[2] Univ Ljubljana, Artificial Intelligence Lab, Ljubljana, Slovenia
[3] Lucerne Univ Appl Sci & Arts, Comp Sci Dept, Luzern, Switzerland
[4] Zurich Univ Appl Sci, Inst Appl Math & Phys, Technikumstr 9, CH-8401 Winterthur, Switzerland
来源
DATA SCIENCE FOR PHOTONICS AND BIOPHOTONICS | 2024年 / 13011卷
关键词
Fluorescence spectroscopy; olive oil; machine learning; artificial neural networks; quality control; explainability; convolutional neural networks; SPECTROSCOPY;
D O I
10.1117/12.3017680
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Monitoring the quality of extra virgin olive oil (EVOO) during its life cycle is of particular importance due to its influence on health-related characteristics and its significance for the oil industry. For this reason it is critical to find an easy-to-perform, non-destructive and affordable method to monitor the quality of EVOO and detect its degradation due to ageing. The following study explores a machine learning approach based on fluorescence measurements for predicting oil changes arising from the ageing process. The proposed method specifically predicts the quality parameters that are required for an olive oil to qualify as extra virgin. In particular, the two properties considered in this analysis are the UV absorbance at 232 and 268 nm (K-232 and K-268), both critical markers of the quality of extra virgin oil. To achieve this goal, a large dataset of fluorescence measurements was analysed, comprising 720 excitation-emission matrices of twenty-four different oils initially labeled as extra virgin. The samples were aged under accelerated conditions at 60 degrees C in the dark for nine weeks and their properties were measured at ten different time steps during the process. Two different machine learning pipelines were implemented for the prediction of K-232 and K-268. In a first approach, the model was trained on all the ten ageing steps of each oil and learned to predict all the ten steps of an unseen oil. In a second approach, the model was trained on one single ageing on multiple oils and step for all the oils and learned to predicta single ageing step. The results demonstrate the potential of the proposed approach.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] Machine Learning-Enhanced Fluorescence Spectroscopy for the Quality Assessment of Extra Virgin Olive Oil during Ageing
    Venturini, Francesca
    Fluri, Silvan
    Mejari, Manas
    Baumgartner, Michael
    Piga, Dario
    Michelucci, Umberto
    OPTICAL SENSING AND DETECTION VIII, 2024, 12999
  • [2] Exploration of Spanish Olive Oil Quality with a Miniaturized Low-Cost Fluorescence Sensor and Machine Learning Techniques
    Venturini, Francesca
    Sperti, Michela
    Michelucci, Umberto
    Herzig, Ivo
    Baumgartner, Michael
    Caballero, Josep Palau
    Jimenez, Arturo
    Deriu, Marco Agostino
    FOODS, 2021, 10 (05)
  • [3] Shedding light on the ageing of extra virgin olive oil: Probing the impact of temperature with fluorescence spectroscopy and machine learning techniques
    Venturini, Francesca
    Fluri, Silvan
    Mejari, Manas
    Baumgartner, Michael
    Piga, Dario
    Michelucci, Umberto
    LWT-FOOD SCIENCE AND TECHNOLOGY, 2024, 191
  • [4] IDENTIFYING OLIVE OIL FRAUD AND ADULTERATION USING MACHINE LEARNING ALGORITHMS
    Yakar, Yasin
    Karada, Kerim
    QUIMICA NOVA, 2022, 45 (10): : 1245 - 1250
  • [5] Classification of olive cultivars by machine learning based on olive oil chemical composition
    Skiada, Vasiliki
    Katsaris, Panagiotis
    Kambouris, Manousos E.
    Gkisakis, Vasileios
    Manoussopoulos, Yiannis
    FOOD CHEMISTRY, 2023, 429
  • [6] Comparative Analysis of Feature Extraction Methods and Machine Learning Models for Predicting Osteoporosis Prevalence
    Danni Zhang
    Xingyu Yang
    Fangying Wang
    Cifang Qiu
    Yanfu Chai
    Danruo Fang
    Journal of Medical Systems, 49 (1)
  • [7] Integrating near-infrared hyperspectral imaging with machine learning and feature selection: Detecting adulteration of extra-virgin olive oil with lower-grade olive oils and hazelnut oil
    Malavi, Derick
    Raes, Katleen
    van Haute, Sam
    CURRENT RESEARCH IN FOOD SCIENCE, 2024, 9
  • [8] Machine Learning Framework for Classifying and Predicting Depressive Behavior Based on PPG and ECG Feature Extraction
    Alzate, Mateo
    Torres, Robinson
    De la Roca, Jose
    Quintero-Zea, Andres
    Hernandez, Martha
    APPLIED SCIENCES-BASEL, 2024, 14 (18):
  • [9] OLIVE AND OLIVE OIL EXTRACTION IN PORTUGAL
    Carvalho Lima De Jesus, M. A.
    Gucci, R.
    RIVISTA ITALIANA DELLE SOSTANZE GRASSE, 2011, 88 (01): : 56 - 63
  • [10] What olive oil for healthy ageing?
    Aiello, Anna
    Guccione, Giovanni Dara
    Accardi, Giulia
    Caruso, Calogero
    MATURITAS, 2015, 80 (02) : 117 - 118