What question did this study set out to answer?

This research aims to develop interpretable models for predicting fat and protein content in foxtail millet using near-infrared spectroscopy.

February 12, 2026Foods0 citationsOpen Access

Development and Interpretability Analysis of Near-Infrared Spectroscopy Models for Fat and Protein Prediction in Foxtail Millet Setaria italica (L.) Beauv.

AGAnqi Gao EGErhu Guo BWBin Wang

Key Points

This research aims to develop interpretable models for predicting fat and protein content in foxtail millet using near-infrared spectroscopy.
214 foxtail millet samples were analyzed using near-infrared spectroscopy.
Sparrow Search Algorithm was utilized to select key wavelengths.
Quantitative models were constructed using Partial Least Squares Regression, Random Forest, and Support Vector Machine.
SHapley Additive exPlanations was used to interpret model contributions.
13 key wavelengths were identified for fat prediction, while 15 were for protein.
Random Forest model predicted fat content best (RP2 = 0.797).
Partial Least Squares model was most effective for protein content (RP2 = 0.695).
Models, established for millet, can be extended to other grains for nutritional analysis.

Abstract

Foxtail millet is a nutritionally important cereal whose fat and protein content directly influence its nutritional quality and processing properties. To overcome the limitations of traditional detection methods, developing rapid, non-destructive, and interpretable models is essential. A total of 214 samples of the foxtail millet cultivar “Changnong No. 47” were used in this study. The Sparrow Search Algorithm was introduced to screen stable key wavelengths by statistically analyzing their selection frequency. Based on the selected wavelengths, quantitative models were constructed using Partial Least Squares Regression (PLS), Random Forest (RF), and Support Vector Machine. The SHapley Additive exPlanations method was employed to quantify the direction and magnitude of contribution of the key wavelengths within the model. Results show the selection of 13 key wavelengths for fat and 15 for protein. The RF model delivered the best prediction for fat content (RP2 = 0.797, RMSEP = 0.218%, RPDP = 2.219), while the PLS model performed best for protein content (RP2 = 0.695, RMSEP = 0.268%, RPDP = 1.811). The methodology established in this study can be applied not only to the rapid quality assessment of millet but can also be extended to analyze the nutritional components of other grains.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper