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

• Published in: Food chemistry 2024-07, Vol.447, p.138895-138895, Article 138895
• Main Authors: Zhang, Shaoliang, Duan, Xin, Yan, Xinglong, Yuan, Xiaoxue, Zhang, Dongfang, Liu, Yuanming, Wang, Yanhua, Shen, Shuxing, Xuan, Shuxin, Zhao, Jianjun, Chen, Xueping, Luo, Shuangxia, Gu, Aixia
• Format: Article
• Language: English
• Subjects: Chinese cabbage; Dietary fiber; Multispectral imaging; Predictive model; Random forest
• ISSN: 0308-8146; 1873-7072
• DOI: 10.1016/j.foodchem.2024.138895

•MSI was used for the 1st time to predict the DF content of Chinese cabbage leaves.•RF model was obtained by comparing with BP neural network, RBF, and MLR models.•The RF model is suitable for predicting DF content throughout the plant growth period. 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 R2 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.