Portable NIR Spectroscopy Combined with Machine Learning for Kiwi Ripeness Classification: An Approach to Precision Farming DOI Creative Commons
Giuseppe Altieri, Sabina Laveglia, Mahdi Rashvand

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(11), С. 6233 - 6233

Опубликована: Июнь 1, 2025

This study aims to evaluate and classify the ripening stages of yellow-fleshed kiwifruit by integrating spectral physicochemical data collected from pre-harvest phase through 60 days storage. A portable near-infrared (NIR) spectrometer (900–1700 nm) was used develop predictive models for soluble solids content (SSC) firmness (FF), testing multiple preprocessing methods within a Partial Least Squares Regression (PLSR) framework. SNV achieved best predictions FF (R2P = 0.74, RMSEP 12.342 ± 0.274 N), while Raw-PLS model showed optimal performance SSC 0.93, 1.142 0.022°Brix). more robustly predicted than FF, as reflected RPD values 2.6 1.7, respectively. For stage classification, an Artificial Neural Network (ANN) outperformed other models, correctly classifying 97.8% samples (R2 0.95, RMSE 0.08, MAE 0.03). These results demonstrate potential combining NIR spectroscopy with AI techniques non-destructive quality assessment accurate ripeness discrimination. The integration regression classification further supports development intelligent decision-support systems optimize harvest timing postharvest handling.

Язык: Английский

Development and Transfer of a Non-Destructive Detection Model based on Visible/Near-Infrared Full Transmission Spectroscopy for Soluble Solid Content in Pomelo under Different Integration Times DOI Creative Commons
Sai Xu,

Zhenhui He,

Xin Liang

и другие.

LWT, Год журнала: 2025, Номер unknown, С. 117796 - 117796

Опубликована: Апрель 1, 2025

Язык: Английский

Процитировано

0
A data-driven study on viscosity estimation of hydrogen-containing gas mixtures using machine learning DOI
Mohammad Rasool Dehghani,

Moein Kafi,

Mehdi Maleki

и другие.

International Journal of Hydrogen Energy, Год журнала: 2025, Номер 138, С. 331 - 343

Опубликована: Май 17, 2025

Язык: Английский

Процитировано

0
Portable NIR Spectroscopy Combined with Machine Learning for Kiwi Ripeness Classification: An Approach to Precision Farming DOI Creative Commons
Giuseppe Altieri, Sabina Laveglia, Mahdi Rashvand

и другие.

Applied Sciences, Год журнала: 2025, Номер 15(11), С. 6233 - 6233

Опубликована: Июнь 1, 2025

This study aims to evaluate and classify the ripening stages of yellow-fleshed kiwifruit by integrating spectral physicochemical data collected from pre-harvest phase through 60 days storage. A portable near-infrared (NIR) spectrometer (900–1700 nm) was used develop predictive models for soluble solids content (SSC) firmness (FF), testing multiple preprocessing methods within a Partial Least Squares Regression (PLSR) framework. SNV achieved best predictions FF (R2P = 0.74, RMSEP 12.342 ± 0.274 N), while Raw-PLS model showed optimal performance SSC 0.93, 1.142 0.022°Brix). more robustly predicted than FF, as reflected RPD values 2.6 1.7, respectively. For stage classification, an Artificial Neural Network (ANN) outperformed other models, correctly classifying 97.8% samples (R2 0.95, RMSE 0.08, MAE 0.03). These results demonstrate potential combining NIR spectroscopy with AI techniques non-destructive quality assessment accurate ripeness discrimination. The integration regression classification further supports development intelligent decision-support systems optimize harvest timing postharvest handling.

Язык: Английский

Процитировано

0