来自中国的科学家，最近在知名期刊Food Chemistry ( IF 8.8 ， Pub Date : 2024-02-28 , DOI: 10.1016/j.foodchem.2024.138895）利用VideometerLab 4多光谱成像系统发表了题为“Multispectral detection of dietary fiber content in Chinese cabbage leaves across different growth periods”的文章。

采用多光谱成像技术，结合化学计量值，构建了不同生育期大白菜叶片膳食纤维含量变化的预测模型。基于所有光谱波段（365–970 nm）和特征光谱波段（430、880、590、490、690 nm），利用随机森林（RF）、反向传播神经网络、径向基函数和多元线性回归4种机器学习算法建立了8个定量预测模型。最后，构建了基于全谱段的RF学习算法定量预测模型，该模型具有较好的预测精度和模型鲁棒性，预测性能R为0.9023，均方根误差（RMSE）为2.7182 g/100 g，残差预测偏差（RPD）为3.1220>3.0。综上所述，该模型能够有效检测大白菜不同生育期膳食纤维（DF）含量的变化，为田间蔬菜分选分级提供技术支持。

Multispectral detection of dietary fiber content in Chinese cabbage leaves across different growth periods

Food Chemistry ( IF 8.8 ) Pub Date : 2024-02-28 , DOI: 10.1016/j.foodchem.2024.138895  

Multispectral imaging, combined with stoichiometric values, was used to construct a prediction model to measure changes in dietary fiber (DF) content in Chinese cabbage leaves across different growth periods. Based on all the spectral bands (365–970 nm) and characteristic spectral bands (430, 880, 590, 490, 690 nm), eight quantitative prediction models were established using four machine learning algorithms, namely random forest (RF), backpropagation neural network, radial basis function, and multiple linear regression. Finally, a quantitative prediction model of RF learning algorithm is constructed based on all spectral bands, which has good prediction accuracy and model robustness, prediction performance with R of 0.9023, root mean square error (RMSE) of 2.7182 g/100 g, residual predictive deviation (RPD) of 3.1220 > 3.0. In summary, this model efficiently detects changes in DF content across different growth periods of Chinese cabbage, which offers technical support for vegetable sorting and grading in the field.