College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China; Key Laboratory of on Site Processing Equipment for Agricultural Products, Ministry of Agriculture and Rural Affairs, Hangzhou 310058, China; Key Laboratory of Intelligent Equipment and Robotics for Agriculture of Zhejiang Province, Hangzhou 310058, China.
College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China.
Food Res Int. 2023 Aug;170:112988. doi: 10.1016/j.foodres.2023.112988. Epub 2023 May 19.
Soluble solids content (SSC) is particularly important for kiwifruit, as it not only determines its flavor, but also helps assess its maturity. Visible/near-infrared (Vis/NIR) spectroscopy has been widely used to evaluate the SSC of kiwifruit. Still, the local calibration models may be ineffective for new batches of samples with biological variability, which limits the commercial application of this technology. Thus, a calibration model was developed using one batch of fruit and the prediction performance was tested with a different batch, which differs in origin and harvest time. Four calibration models were established with Batch 1 kiwifruit to predict SSC, which were based on full spectra (i.e., partial least squares regression (PLSR) model based on full spectra), continuous effective wavelengths (i.e., changeable size moving window-PLSR (CSMW-PLSR) model), and discrete effective wavelengths (i.e., competitive adaptive reweighted sampling-PLSR (CARS-PLSR) model and PLSR-variable importance in projection (PLSR-VIP) model) respectively. The R values of these four models in the internal validation set were 0.83, 0.92, 0.96, and 0.89, with corresponding RMSEV values of 1.08 %, 0.75 %, 0.56 %, and 0.89 %, and RPD values of 2.49, 3.61, 4.80, and 3.02, respectively. Clearly, all four PLSR models performed acceptably in the validation set. However, these models performed very poorly in predicting the Batch 2 samples, with their RMSEP values all exceeding 1.5 %. Although the models could not be used to predict exact SSC, they could still interpret the SSC values of Batch 2 kiwifruit to some extent because the predicted SSC values could fit a specific line. To enable the CSMW-PLSR calibration model to predict the SSC of Batch 2 kiwifruit, the robustness of this model was improved by calibration updating and slope/bias correction (SBC). Different numbers of new samples were randomly selected for updating and SBC, and the minimum number of samples for updating and SBC was finally determined to be 30 and 20, respectively. After calibration updating and SBC, the new models had average R, average RMSEP, and average RPD values of 0.83 and 0.89, 0.69 % and 0.57 %, and 2.45 and 2.97, respectively, in the prediction set. Overall, the methods proposed in this study can effectively address the issue of poor performance of calibration models in predicting new samples with biological variability and make the models more robust, thus providing important guidance for the maintenance of SSC online detection models in practical applications.
可溶性固形物含量（SSC）对猕猴桃尤为重要，因为它不仅决定了猕猴桃的风味，还有助于评估其成熟度。可见/近红外（Vis/NIR）光谱技术已广泛应用于评估猕猴桃的 SSC。然而，对于具有生物变异性的新批次样本，本地校准模型可能效果不佳，这限制了该技术的商业应用。因此，我们使用一批水果建立了一个校准模型，并使用不同批次的水果（起源和收获时间不同）对预测性能进行了测试。使用 Batch1 猕猴桃建立了四个 SSC 预测的校准模型，分别基于全谱（即基于全谱的偏最小二乘回归（PLSR）模型）、连续有效波长（即可变大小移动窗口-PLSR（CSMW-PLSR）模型）和离散有效波长（即竞争性自适应重加权采样-PLSR（CARS-PLSR）模型和 PLSR-变量重要性投影（PLSR-VIP）模型）。这四个模型在内部验证集的 R 值分别为 0.83、0.92、0.96 和 0.89，相应的 RMSEV 值分别为 1.08%、0.75%、0.56%和 0.89%，RPD 值分别为 2.49、3.61、4.80 和 3.02。显然，这四个 PLSR 模型在验证集的表现都可接受。然而，这些模型在预测 Batch2 样本时表现非常差，其 RMSEP 值均超过 1.5%。尽管这些模型不能用于准确预测 SSC，但它们仍然可以在一定程度上解释 Batch2 猕猴桃的 SSC 值，因为预测的 SSC 值可以拟合特定的直线。为了使 CSMW-PLSR 校准模型能够预测 Batch2 猕猴桃的 SSC，通过校准更新和斜率/偏差校正（SBC）提高了该模型的稳健性。对不同数量的新样本进行随机选择进行更新和 SBC，最终确定更新和 SBC 的最小样本数分别为 30 和 20。经过校准更新和 SBC 后，新模型在预测集中的平均 R、平均 RMSEP 和平均 RPD 值分别为 0.83 和 0.89、0.69%和 0.57%以及 2.45 和 2.97。总的来说，本研究提出的方法可以有效解决校准模型在预测具有生物变异性的新样本时性能不佳的问题，使模型更加稳健，从而为实际应用中 SSC 在线检测模型的维护提供重要指导。
