基于机器学习和可解释人工智能的杜仲皮不同炮制程度快速鉴别
Rapid identification of different processing degrees of Eucommiae cortex based on machine learning and explainable artificial intelligence.
摘要(中文译文)
本研究整合了机器学习与可解释人工智能（XAI），对杜仲（Eucommiae cortex，EC）的四种炮制程度进行分类：生品、炮制不足、炮制适中及炮制过度。分别通过分光光度计、高分辨率相机和材料试验机采集杜仲的粉末特征（L、a、b）和饮片特征（R、G、B、GRAY及断裂伸长率百分比（PBE））。在所评估的模型中，XGBoost表现出优越性能，训练准确率达到100%，测试准确率为94.74%。SHAP解释识别出PBE、a和h为关键特征。此外，基于饮片特征的模型优于基于粉末特征的模型。层次分析法（AHP）-熵权法（EWM）相结合的分析方法确认了外观与成分之间的关系。本研究成功建立了一种智能、快速、准确的杜仲饮片炮制程度识别方法，为工业生产中的在线取样质量控制提供了有价值的参考。
Abstract
This study integrated machine learning and explainable artificial intelligence (XAI) to classify four processing degrees of Eucommiae cortex (EC): raw, under-processed, moderately processed and over-processed. Powder characteristics (L, a, b), and decoction piece characteristics (R, G, B, GRAY, and the percentage of breaking elongation (PBE)) of EC were collected via spectrophotometer, high-resolution camera, and material testing machine, respectively. Among the evaluated models, XGBoost demonstrated superior performance, achieving perfect training accuracy (100%) and test accuracy (94.74%). SHAP explanation identified PBE, a and h as key features. Furthermore, models based on decoction pieces characteristics outperformed powder features. The integrated Analytic Hierarchy Process (AHP)-Entropy Weight Method (EWM) analytical approach was acknowledged the relationship of appearance and components. This study successfully established an intelligent, rapid, and accurate method for identifying the processing degrees of EC decoction pieces, offering a valuable reference for at-line sampling quality control in industrial production.
如何引用
AMA
Yatong Xin, Weihao Zhu, Dong Zhou, Huan Li, Fangyu Hao, Shuo Feng, et al. Rapid identification of different processing degrees of Eucommiae cortex based on machine learning and explainable artificial intelligence.. Food chemistry. 2026; doi:10.1016/j.foodchem.2026.149392.
APA
Yatong Xin, Weihao Zhu, Dong Zhou, Huan Li, Fangyu Hao, Shuo Feng, et al (2026). Rapid identification of different processing degrees of Eucommiae cortex based on machine learning and explainable artificial intelligence.. Food chemistry. https://doi.org/10.1016/j.foodchem.2026.149392
GB/T 7714
Yatong Xin, Weihao Zhu, Dong Zhou, Huan Li, Fangyu Hao, Shuo Feng, et al. Rapid identification of different processing degrees of Eucommiae cortex based on machine learning and explainable artificial intelligence.[J]. Food chemistry, 2026 doi:10.1016/j.foodchem.2026.149392.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出