您好,欢迎访问浙江省农业科学院 机构知识库!

Near-Infrared Spectroscopy and Machine Learning for Fast Quality Prediction of Bottle Gourd

文献类型: 外文期刊

作者: Guo, Xiao 1 ; Huang, Hongyu 3 ; Wang, Haiyan 2 ; Cai, Chang 3 ; Wang, Ying 2 ; Wu, Xiaohua 2 ; Wang, Jian 2 ; Wang, Baogen 2 ; Zhu, Biao 1 ; Xiang, Yun 3 ;

作者机构: 1.Zhejiang A&F Univ, Coll Hort Sci, Hangzhou 311300, Peoples R China

2.Zhejiang Acad Agr Sci, Inst Vegetables, Hangzhou 310021, Peoples R China

3.Zhejiang Univ Technol, Inst Cyberspace Secur, Hangzhou 310023, Peoples R China

4.Key Lab Vegetable Germplasm Innovat & Qual Breedin, Hangzhou 310021, Peoples R China

5.State Key Lab Qual & Safety Agroprod, Hangzhou 310021, Peoples R China

关键词: bottle gourd; protein and amino acid content; near-infrared spectroscopy; machine learning; quality prediction

期刊名称:FOODS ( 影响因子:5.1; 五年影响因子:5.6 )

ISSN:

年卷期: 2025 年 14 卷 14 期

页码:

收录情况: SCI

摘要: Protein and amino acid content are the crucial quality parameters in bottle gourd, and traditional measurement methods for detecting those parameters are complicated, time-consuming, and costly. In this study, we employed NIRS along with machine learning and neural network-based methods to model and predict protein and free amino acids (FAAs) of bottle gourd. Specifically, the content of protein and FAAs were measured through conventional methods. Then a near-infrared analyzer was utilized to obtain the spectral data, which were processed using multiple scattering correction (MSC) and standard normalized variate (SNV). The processed spectral data were further processed using feature importance selection to select the feature bands that had the highest correlation with protein and FAAs, respectively. The models for protein and FAAs estimation were developed using support vector regression (SVR), ridge regression (RR), random forest regression (RFR), and fully connected neural networks (FCNNs). Among them, ridge regression achieved the optimal performance, with determination coefficients (R2) of 0.96 and 0.77 on the protein and FAAs test sets, respectively, and root mean square error (RMSE) values of 0.23 and 0.5, respectively. Based on this, we developed a precise and rapid prediction model for the important quality indices of bottle gourd.

  • 相关文献
作者其他论文 更多>>