Hyperspectral Classification of Kiwiberry Ripeness for Postharvest Sorting Using PLS-DA and SVM: From Baseline Models to Meta-Inspired Stacked SVM

Abstract

The accurate and non-destructive assessment of fruit ripeness is essential for post-harvest sorting and quality management. This study evaluated a meta-inspired classification framework integrating partial least squares discriminant analysis (PLS-DA) with support vector machines (SVMs) trained on latent variables (sSVM) or on class probabilities (pSVM) derived from multiple PLS-DA components. Two kiwi-berry varieties, ‘Geneva’ and ‘Weiki’, were analyzed using variety-specific and combined datasets. Performance was assessed in calibration and prediction using accuracy, F05, Cohen’s kappa, precision, sensitivity, specificity, and likelihood ratios. Conventional PLS-DA provided reasonably good classification, but pSVM models, particularly those with an RBF kernel (pSVM_R), consistently outperformed other approaches and ensured higher stability across all datasets. Unlike sSVMs, which were prone to over-fitting, pSVM_R models achieved the highest accuracy of 92.4–96.9%, Cohen’s kappa of 84.8–93.9%, and precision of 89.1–94.2%, clearly surpassing both score-based SVM and PLS-DA. Contrasting tendencies were observed between cultivars: ‘Geneva’ models improved during prediction, while ‘Weiki’ models declined, especially in specificity. Combined datasets provided greater stability but slightly reduced peak performance than single-variety models. These findings highlight the value of probability-enriched stacking models for non-invasive ripeness discrimination, suggesting that adaptive or hybrid strategies may further enhance generalization across diverse cultivars.

Plant phenotyping relevance

ハイパースペクトル画像からキウイベリー果実の成熟度を非破壊推定する分類手法を開発・比較しており、果実状態の取得・抽出が研究の中心である。

Code and data availability

The supplied blocks describe hyperspectral imaging of kiwiberry fruits and PLS-DA/SVM modeling, but contain no data availability statement, no public dataset or image deposit, no author code repository or URL, and no trained model release. The only URLs present are the preprint DOI and Preprints.org boilerplate, which指

No evidence-backed public reproduction asset is currently recorded.