基于红外光谱结合机器学习方法的牛膝不同炮制品及炮制程度的判别分析  

Discrimination analysis of different processed products and processing degree of Achyranthis Bidentatae Radix based on infrared spectroscopy combined with machine learning methods

作　　者：田瀚举 杨颜溶 贾豪 李莹莹 段浩瀚 赵新梅 张春亚 雷敬卫[1,2] 谢彩侠 杨春静[1,2,3] 龚海燕 TIAN Han-ju;YANG Yan-rong;JIA Hao;LI Ying-ying;DUAN Hao-han;ZHAO Xin-mei;ZHANG Chun-ya;LEI Jing-wei;XIE Cai-xia;YANG Chun-jing;GONG Hai-yan(School of Pharmacy,Henan University of Chinese Medicine,Zhengzhou 450046,China;Henan Engineering Technology Research Center for TCM Quality Control and Evaluation,Zhengzhou 450046,China;Third Affiliated Hospital of Henan University of Chinese Medicine,Zhengzhou 450046,China)

机构地区：[1]河南中医药大学药学院,河南郑州450046 [2]河南省中药质量控制与评价工程技术研究中心,河南郑州450046 [3]河南中医药大学第三附属医院,河南郑州450046

出　　处：《中草药》2023年第22期7387-7401,共15页Chinese Traditional and Herbal Drugs

基　　金：国家重点研发计划“中医药现代化研究”重点专项项目(2018YFC1707000);河南省中医药科学研究专项课题(2022ZY1156)。

摘　　要：目的采用红外光谱技术结合机器学习算法建立牛膝Achyranthes bidentata炮制品类别与炮制程度的定性判别模型。方法采集不同炮制品与不同炮制程度牛膝的中红外光谱(midinfraredspectroscopy,MIRS),运用BP神经网络(back propagation neural network,BPNN)、遗传算法优化BP神经网络(GA-BP)、随机森林(random forest,RF)、径向基神经网络(radial basis function network,RBFN)、卷积神经网络(convolutional neural networks,CNN)等机器学习算法建立牛膝炮制品类别与炮制程度的定性判别模型;采集不同炮制品与不同炮制程度牛膝的近红外光谱(near infrared spectroscopy,NIRS),使用TQAnalyst软件中的判别分析法建立牛膝炮制品类别与炮制程度的定性分析模型。结果机器学习算法模型结果显示CNN判别模型较优秀,BPNN、RF及RBFN性能相近,GA-BP模型性能相对较差。3个NIRS定性模型结果显示验证集准确率均为100%,可准确预测炮制品类别与炮制程度。结论通过红外光谱技术建立的定性分析模型可作为牛膝炮制品类别与炮制程度的鉴别手段。同时提供了快速、无损的检测手段及可靠的数据分析方法,为中药材炮制品类别与炮制程度精准识别提供新的方法参考。Objective To establish a qualitative discrimination model for the type and degree of processing of Niuxi(Achyranthesbidentata,AB)using infrared spectroscopy and machine learning algorithms.Methods The infrared spectra of AB with different processing types and degreewas collected,and various machine learning algorithms,including back propagation neural network(BPNN),genetic algorithm-optimized BP neural network(GA-BP),random forest(RF),radial basis function network(RBFN),and convolutional neural networks(CNN)were used to establish a qualitative discrimination model for the type and degree of processed products of AB.The near-infrared spectra(NIRS)of AB with different processing types and degreewas collected,and TQ Analyst software was used to establish a qualitative analysis model for the type and degree ofprocessedproducts ofAB.Results The results of the machine learning algorithm models showed that the CNN discriminative model was superior,the BPNN,RF and RBFN had similar performance,and the GA-BP model had relatively poor performance.The three NIRS qualitative models had validation accuracies of 100%,indicating that they could accurately predict the type and degree of processed productsof AB.Conclusion The qualitative analysis model developed in this study by infrared spectroscopy can be used as a means to identify the type and degree of processed productsof AB.It also provides a rapid and non-destructive means of testing and a reliable method for data analysis,with view to providing a new method of reference for the accurate identification of the type and degree of preparation of Chinese herbal processedproducts.

关 键 词：牛膝 炮制品 炮制程度 红外光谱 正交偏最小二乘法-判别分析 机器学习算法 

分 类 号：R283.6[医药卫生—中药学]