Vis/NIR Spectroscopy and Vis/NIR Hyperspectral Imaging for Non-Destructive Monitoring of Apricot Fruit Internal Quality with Machine Learning
The fruit supply chain requires simple, non-destructive, and fast tools for quality evaluation both in the field and during the post-harvest phase. In this study, a portable visible and near-infrared (Vis/NIR) spectrophotometer and a portable Vis/NIR hyperspectral imaging (HSI) device were tested to...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Foods |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2304-8158/14/2/196 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588473121374208 |
|---|---|
| author | Tiziana Amoriello Roberto Ciorba Gaia Ruggiero Francesca Masciola Daniela Scutaru Roberto Ciccoritti |
| author_facet | Tiziana Amoriello Roberto Ciorba Gaia Ruggiero Francesca Masciola Daniela Scutaru Roberto Ciccoritti |
| author_sort | Tiziana Amoriello |
| collection | DOAJ |
| description | The fruit supply chain requires simple, non-destructive, and fast tools for quality evaluation both in the field and during the post-harvest phase. In this study, a portable visible and near-infrared (Vis/NIR) spectrophotometer and a portable Vis/NIR hyperspectral imaging (HSI) device were tested to highlight genetic differences among apricot cultivars, and to develop multi-cultivar and multi-year models for the most important marketable attributes (total soluble solids, TSS; titratable acidity, TA; dry matter, DM). To do this, the fruits of seventeen cultivars from a single experimental orchard harvested at the commercial maturity stage were considered. Spectral data emphasized genetic similarities and differences among the cultivars, capturing changes in the pigment content and macro components of the apricot samples. In recent years, machine learning techniques, such as artificial neural networks (ANNs), have been successfully applied to more efficiently extract valuable information from spectral data and to accurately predict quality traits. In this study, prediction models were developed based on a multilayer perceptron artificial neural network (ANN-MLP) combined with the Levenberg–Marquardt learning algorithm. Regarding the Vis/NIR spectrophotometer dataset, good predictive performances were achieved for TSS (R<sup>2</sup> = 0.855) and DM (R<sup>2</sup> = 0.857), while the performance for TA was unsatisfactory (R<sup>2</sup> = 0.681). In contrast, the optimal predictive ability was found for models of the HSI dataset (TSS: R<sup>2</sup> = 0.904; DM: R<sup>2</sup> = 0.918, TA: R<sup>2</sup> = 0.811), as confirmed by external validation. Moreover, the ANN allowed us to identify the most predictive input spectral regions for each model. The results showed the potential of Vis/NIR spectroscopy as an alternative to traditional destructive methods to monitor the qualitative traits of apricot fruits, reducing the time and costs of analyses. |
| format | Article |
| id | doaj-art-381b0d0e2a9e41f3ba797ca80b1b3ce8 |
| institution | Kabale University |
| issn | 2304-8158 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Foods |
| spelling | doaj-art-381b0d0e2a9e41f3ba797ca80b1b3ce82025-01-24T13:32:50ZengMDPI AGFoods2304-81582025-01-0114219610.3390/foods14020196Vis/NIR Spectroscopy and Vis/NIR Hyperspectral Imaging for Non-Destructive Monitoring of Apricot Fruit Internal Quality with Machine LearningTiziana Amoriello0Roberto Ciorba1Gaia Ruggiero2Francesca Masciola3Daniela Scutaru4Roberto Ciccoritti5CREA—Research Centre for Food and Nutrition, Via Ardeatina 546, 00178 Rome, ItalyCREA—Research Centre for Olive, Fruit and Citrus Crops, Via di Fioranello 52, 00134 Rome, ItalyCREA—Research Centre for Olive, Fruit and Citrus Crops, Via di Fioranello 52, 00134 Rome, ItalyCREA—Research Centre for Olive, Fruit and Citrus Crops, Via di Fioranello 52, 00134 Rome, ItalyCREA—Research Centre for Olive, Fruit and Citrus Crops, Via di Fioranello 52, 00134 Rome, ItalyCREA—Research Centre for Olive, Fruit and Citrus Crops, Via di Fioranello 52, 00134 Rome, ItalyThe fruit supply chain requires simple, non-destructive, and fast tools for quality evaluation both in the field and during the post-harvest phase. In this study, a portable visible and near-infrared (Vis/NIR) spectrophotometer and a portable Vis/NIR hyperspectral imaging (HSI) device were tested to highlight genetic differences among apricot cultivars, and to develop multi-cultivar and multi-year models for the most important marketable attributes (total soluble solids, TSS; titratable acidity, TA; dry matter, DM). To do this, the fruits of seventeen cultivars from a single experimental orchard harvested at the commercial maturity stage were considered. Spectral data emphasized genetic similarities and differences among the cultivars, capturing changes in the pigment content and macro components of the apricot samples. In recent years, machine learning techniques, such as artificial neural networks (ANNs), have been successfully applied to more efficiently extract valuable information from spectral data and to accurately predict quality traits. In this study, prediction models were developed based on a multilayer perceptron artificial neural network (ANN-MLP) combined with the Levenberg–Marquardt learning algorithm. Regarding the Vis/NIR spectrophotometer dataset, good predictive performances were achieved for TSS (R<sup>2</sup> = 0.855) and DM (R<sup>2</sup> = 0.857), while the performance for TA was unsatisfactory (R<sup>2</sup> = 0.681). In contrast, the optimal predictive ability was found for models of the HSI dataset (TSS: R<sup>2</sup> = 0.904; DM: R<sup>2</sup> = 0.918, TA: R<sup>2</sup> = 0.811), as confirmed by external validation. Moreover, the ANN allowed us to identify the most predictive input spectral regions for each model. The results showed the potential of Vis/NIR spectroscopy as an alternative to traditional destructive methods to monitor the qualitative traits of apricot fruits, reducing the time and costs of analyses.https://www.mdpi.com/2304-8158/14/2/196total soluble solidstitratable aciditydry matterVis/NIR hyperspectral imagingVis/NIR spectrophotometerartificial neural networks |
| spellingShingle | Tiziana Amoriello Roberto Ciorba Gaia Ruggiero Francesca Masciola Daniela Scutaru Roberto Ciccoritti Vis/NIR Spectroscopy and Vis/NIR Hyperspectral Imaging for Non-Destructive Monitoring of Apricot Fruit Internal Quality with Machine Learning Foods total soluble solids titratable acidity dry matter Vis/NIR hyperspectral imaging Vis/NIR spectrophotometer artificial neural networks |
| title | Vis/NIR Spectroscopy and Vis/NIR Hyperspectral Imaging for Non-Destructive Monitoring of Apricot Fruit Internal Quality with Machine Learning |
| title_full | Vis/NIR Spectroscopy and Vis/NIR Hyperspectral Imaging for Non-Destructive Monitoring of Apricot Fruit Internal Quality with Machine Learning |
| title_fullStr | Vis/NIR Spectroscopy and Vis/NIR Hyperspectral Imaging for Non-Destructive Monitoring of Apricot Fruit Internal Quality with Machine Learning |
| title_full_unstemmed | Vis/NIR Spectroscopy and Vis/NIR Hyperspectral Imaging for Non-Destructive Monitoring of Apricot Fruit Internal Quality with Machine Learning |
| title_short | Vis/NIR Spectroscopy and Vis/NIR Hyperspectral Imaging for Non-Destructive Monitoring of Apricot Fruit Internal Quality with Machine Learning |
| title_sort | vis nir spectroscopy and vis nir hyperspectral imaging for non destructive monitoring of apricot fruit internal quality with machine learning |
| topic | total soluble solids titratable acidity dry matter Vis/NIR hyperspectral imaging Vis/NIR spectrophotometer artificial neural networks |
| url | https://www.mdpi.com/2304-8158/14/2/196 |
| work_keys_str_mv | AT tizianaamoriello visnirspectroscopyandvisnirhyperspectralimagingfornondestructivemonitoringofapricotfruitinternalqualitywithmachinelearning AT robertociorba visnirspectroscopyandvisnirhyperspectralimagingfornondestructivemonitoringofapricotfruitinternalqualitywithmachinelearning AT gaiaruggiero visnirspectroscopyandvisnirhyperspectralimagingfornondestructivemonitoringofapricotfruitinternalqualitywithmachinelearning AT francescamasciola visnirspectroscopyandvisnirhyperspectralimagingfornondestructivemonitoringofapricotfruitinternalqualitywithmachinelearning AT danielascutaru visnirspectroscopyandvisnirhyperspectralimagingfornondestructivemonitoringofapricotfruitinternalqualitywithmachinelearning AT robertociccoritti visnirspectroscopyandvisnirhyperspectralimagingfornondestructivemonitoringofapricotfruitinternalqualitywithmachinelearning |