Advancing Loquat Total Soluble Solids Content Determination by Near-Infrared Spectroscopy and Explainable AI

Agriculture, Год журнала: 2025, Номер 15(3), С. 281 - 281

Опубликована: Янв. 28, 2025

TSSC is one of the most important factors affecting loquat flavor, consumer satisfaction, and market competitiveness. To improve ability to assess loquats, a method leveraging near-infrared spectroscopy explainable artificial intelligence was proposed. The 900–1700 nm 156 fresh samples collected preprocessed using seven preprocessing techniques, significant wavelength extraction utilizing six feature methods eliminate data redundancy. Linear nonlinear models were employed establish relationship between spectrum TSSC, with focus on comparing analyzing prediction performance. findings reveal that combination 26 spectral bands selected by SPA PLSR model yielded best outcomes (R = 0.9031, RMSEP 0.6171, RPD 2.2803). contribution key wavelengths can be obtained SHAP, which explains differences in accuracy provides reference for application determination.

Язык: Английский

A systematic review of explainable artificial intelligence for spectroscopic agricultural quality assessment

Computers and Electronics in Agriculture, Год журнала: 2025, Номер 235, С. 110354 - 110354

Опубликована: Апрель 4, 2025

Язык: Английский