浏览全部资源
扫码关注微信
甘肃中医药大学 医学信息工程学院,甘肃 兰州 730000
李四海,教授,研究方向:机器学习、深度学习、光谱分析,E-mail:lshroom@163.com
收稿:2025-04-14,
修回:2025-07-03,
录用:2025-07-04,
纸质出版:2025-10-15
移动端阅览
刘明奇,李四海,宋航.基于近红外光谱技术和编码器-解码器的黄芪产地鉴别[J].分析测试学报,2025,44(10):2063-2070.
LIU Ming-qi,LI Si-hai,SONG Hang.Astragalus Origin Identification Based on Near-infrared Spectroscopy Technology and Encoder-Decoder[J].Journal of Instrumental Analysis,2025,44(10):2063-2070.
刘明奇,李四海,宋航.基于近红外光谱技术和编码器-解码器的黄芪产地鉴别[J].分析测试学报,2025,44(10):2063-2070. DOI: 10.12452/j.fxcsxb.250414291.
LIU Ming-qi,LI Si-hai,SONG Hang.Astragalus Origin Identification Based on Near-infrared Spectroscopy Technology and Encoder-Decoder[J].Journal of Instrumental Analysis,2025,44(10):2063-2070. DOI: 10.12452/j.fxcsxb.250414291.
为进行黄芪产地溯源,提出了CTGAN+1D-CNN+Encoder-Decoder(CCEN)网络模型,首先通过条件表格生成对抗网络(CTGAN)增强黄芪近红外光谱数据,解决数据较少的问题,再通过在一维卷积神经网络(1D-CNN)上加入编码器-解码器(Encoder-Decoder)结构,使网络可以同时捕获特征之间的全局关系和局部关系。实验结果表明,CTGAN和Savitzky-Golay增强后,偏最小二乘法判别分析(PLS-DA)、随机森林(RF)、K近邻算法(KNN)和1D-CNN的准确率分别提升至0.973 3、0.953 3、0.960 0和0.973 3。加入编码器-解码器后,1D-CNN准确率提升至0.977 8。最终CCEN模型在黄芪数据集上的准确率、召回率和F1值分别达到0.986 7、0.987 2和0.986 8,均优于对比模型。结果证明CCEN模型适用于近红外光谱这类结构复杂、样本有限的一维信号数据,为黄芪中药材道地性产地识别研究提供了新方法。
To trace the origin of
Astragalus
,a CTGAN+1D-CNN+encoder-decoder(CCEN) network model was proposed. First,conditional generative adversarial networks(CTGAN) enhance
Astragalus
near-infrared spectral data to address limited data. Then,integrating an encoder-decoder structure into a 1D-CNN enables the network to capture both global and local relationships among features simultaneously. Experimental results demonstrate that after CTGAN and Savitzky-Golay enhancement,the accuracy rates of partial least squares discriminant analysis(PLS-DA),random forest(RF),K-nearest neighbors(KNN),and 1D-CNN improved to 0.973 3,0.953 3,0.960 0,and 0.973 3,respectively. The incorporation of the encoder-decoder architecture further elevated the 1D-CNN accuracy to 0.977 8. Ultimately,the CCEN model achieved accuracy,recall,and F1 scores of 0.986 7,0.987 2,and 0.986 8,respectively,on the
Astragalus
dataset,outperforming all comparison models. The results demonstrate that the CCEN model is suitable for one-dimensional signal data with complex structures and limited samples,such as near-infrared spectra,providing a novel approach for identifying the origin of
Astragalus
.
Shahrivari-Baviloliaei S , Orhan I E , Kaplan N A , Konopacka A , Waleron K , Plenis A , Viapiana A . Antioxidants , 2024 , 13 ( 8 ): 993 .
Durazzo A , Nazhand A , Lucarini M , Silva A M , Souto S B , Guerra F , Severino P , Zaccardelli M , Souto E B , Santini A . Rend . Lincei , 2021 , 32 : 625 - 642 .
Wang X , Cui L J . J. Basic Chin. Med. (王兮,崔立俊. 中国中医基础医学杂志), 2025 , 31 ( 2 ): 329 - 331 .
Li N X , Zhang J J , Zhang Y , Ma Z G , Liao J H , Cao H , Wu M H . Chin. Med. , 2020 , 15 : 1 - 12 .
Liu X Y , Jiang W W , Su M , Sun Y , Liu H M , Nie L , Zang H C . J. Sep. Sci. , 2020 , 43 ( 1 ): 6 - 17 .
Noviana E , Indrayanto G , Rohman A . Front. Pharmacol. , 2022 , 13 : 853023 .
Beć K B , Grabska J , Huck C W . J. Pharm. Biomed. Anal. , 2021 , 193 : 113686 .
Gao L L , Zhong L , Zhang J , Zhang M Q , Zeng Y Z , Li L , Zang H C . Spectrochim . Acta A , 2021 , 244 : 118854 .
Amirvaresi A , Nikounezhad N , Amirahmadi M , Daraei B , Parastar H . Food Chem. , 2021 , 344 : 128647 .
Raypah M E , Zhi L J , Loon L Z , Omar A F . Chemom. Intell. Lab. Syst. , 2022 , 224 : 104540 .
Zhang Z Y , Wang Y J , Yan H , Chang X W , Zhou G S , Zhu L , Liu P , Guo S , Dong T T X , Duan J A . J. Anal. Methods Chem. , 2021 , 1 : 8875876 .
Sun F , Chen Y , Wang K Y , Wang S M , Liang S W . Anal. Lett. , 2020 , 53 ( 6 ): 937 - 959 .
Li Q Q , Zeng J Q , Lin L , Zhang J , Zhu J Y , Yao L , Wang S Y , Du J , Wu Z S . LWT , 2021 , 140 : 110856 .
Li X , Wu J M , Bai T C , Wu C Y , He Y F , Huang J X , Li X C , Shi Z Y , Hou K Y . Comput. Electron. Agric. , 2024 , 223 : 109122 .
Chai Q Q , Zeng J , Lin D H , Li X H , Huang J , Wang W . J. Pharm. Biomed. Anal. , 2021 , 199 : 114035 .
Benmouna B , García-Mateos G , Sabzi S , Fernandez-Beltran R , Parras-Burgos D , Molina-Martínez J M . Food Bioprocess Technol. , 2022 , 15 : 2226 - 2236 .
Singh T , Garg N M , Iyengar S R . J. Food Process Eng. , 2021 , 44 ( 10 ): 13821 .
Hwang S W , Park G , Kim J , Kang K H , Lee W H . BioResources , 2024 , 19 ( 1 ): 1633 .
Xu L , Skoularidou M , Cuesta-Infante A , Veeramachaneni K . Adv . Neural Inf. Process. Syst. , 2019 , 659 : 7335 - 7345 .
Tang L , Mao Y H , Cai J , Liu H Q , Min H , An Y R , Liu S . J. Instrum. Anal. (唐磊,茅晔辉,蔡婧,刘恒钦,闵红,安雅睿,刘曙. 分析测试学报), 2025 , 44 ( 6 ): 1227 - 1236 .
0
浏览量
5
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构