Prediction of Total Soluble Solids in Apricot Using Adaptive Boosting Ensemble Model Combined with NIR and High-Frequency UVE-Selected Variables

Molecules, Год журнала: 2025, Номер 30(7), С. 1543 - 1543

Опубликована: Март 30, 2025

Total soluble solids (TSSs) serve as a crucial maturity indicator and quality determinant in apricots, influencing harvest timing postharvest management decisions. This study develops an advanced framework integrating adaptive boosting (Adaboost) ensemble learning with high-frequency spectral variables selected by uninformative variable elimination (UVE) for the rapid non-destructive detection of fruit quality. Near-infrared (NIR) spectra (1000~2500 nm) were acquired then preprocessed through robust principal component analysis (ROBPCA) outlier combined z-score normalization pretreatment. Subsequent data processes included three steps: (1) 100 continuous runs UVE identified characteristic wavelengths, which classified into levels—high-frequency (≥90 times), medium-frequency (30–90 low-frequency (≤30 times) subsets; (2) development base optimal partial least squares regression (PLSR) models each wavelength subset; (3) execution weight optimization Adaboost algorithm. The experimental findings revealed following: model established based on wavelengths outperformed both full-spectrum full-characteristic model. optimized UVE-PLS-Adaboost achieved peak performance (R = 0.889, RMSEP 1.267, MAE 0.994). research shows that UVE-Adaboost fusion method enhances prediction accuracy generalization ability multi-dimensional feature allocation. proposed enables rapid, apricot TSSs provides reference evaluation other fruits agricultural applications.

Язык: Английский

Insights of Freshness Phenotype Detection for Postharvest Fruit and Vegetables

Plant Phenomics, Год журнала: 2025, Номер unknown, С. 100042 - 100042

Опубликована: Апрель 1, 2025

Язык: Английский