Identification of Pinelliae Rhizoma Decoction Pieces by Hyperspectral
Imaging Combined With Machine Learning
LI Ruo-tong1, HU Hui-qiang2, CAO Shi-yu1, LU Meng-yao1, LIU Meng-ran1, FU Jia-yue1, MAO Xiao-bo2, WANG Hai-bo3*, FU Ling1, 3*
1. College of Pharmacy, Zhengzhou University, Zhengzhou 450000, China
2. College of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450000, China
3. NMPA Key Laboratory for Quality Control of Traditional Chinese Medicine, Henan Institute for Drug and Medical Device Inspection, Zhengzhou 450018, China
Abstract：There are four kinds of decoction pieces for Pinelliae Rhizoma, namely Pinelliae Rhizoma, Pinelliae Rhizoma praeparatum cum alumine, Pinelliae Rhizoma praeparatum cum zingibere et alumine, and Pinelliae Rhizoma praeparatum, recorded in the current Chinese Pharmacopoeia (2020 edition). Due to their similar appearance and weak odor characteristics, it's easy to confuse their manufacturing management, market circulation, and clinical application. Because of the requirement for instruments, reagents, and intricate detection steps, exploring and establishing an accurate, rapid, and non-destructive detection method for Pinelliae Rhizoma decoction pieces is necessary.This paper used hyperspectral imaging combined with machine learning to identify the four kinds of Pinelliae Rhizom adecoction pieces. The principal component analysis (PCA) was utilized to extract features from the hyperspectral data, and support vector machine (SVM), logistic regression (LR), multi-layer perceptron (MLP), and random forest (RF) classification models were established based on the full-band data model. The accuracy of both training and test sets of four classification models was evaluated, along with an analysis ofthe principal component proportion of the four models under optimal performance. Additionally, the t-distributed stochastic neighbor embedding (t-SNE)visual dimensionality reduction analysiswas conducted on the hyperspectral data of the fourkinds of decoction pieces. The SVM, LR, MLP, and RF classification models based on PCA can achieve accurate identification for PinelliaeRhizoma decoction pieces. The accuracy of the test set is 80.76%, 96.45%, 96.59%, and 86.77%; in addition, the proportion of principal components is 60%, 80%, 70%, and 80%, respectively. The t-SNE analysis by dimensionality reduction showed that the components of Pinelliae Rhizoma praeparatum cum zingibere et alumine and Pinelliae Rhizoma praeparatum cum alumine were relatively close and partly changed compared with Pinelliae Rhizoma. However, the chemical composition of Pinelliae Rhizoma praeparatum changed greatly after processing, which was very different from the above three kinds of decoction pieces. These results also agree with the average spectral reflectance result. It's the first application of hyperspectral imaging combined with machine learning to develop a predictive model for different decoction pieces of Pinelliae Rhizoma. This approach -successfully identifies Pinelliae Rhizoma decoction pieces accurately, rapidly, and non-destructively, thereby providing a novel identification method and scientific foundation for these products' rational production, circulation, and clinical application.
李若彤，胡会强，曹诗宇，卢孟瑶，刘梦然，付嘉玥，毛晓波，王海波，符 玲. 基于高光谱成像结合机器学习的半夏饮片鉴别[J]. 光谱学与光谱分析, 2025, 45(05): 1236-1242.
LI Ruo-tong, HU Hui-qiang, CAO Shi-yu, LU Meng-yao, LIU Meng-ran, FU Jia-yue, MAO Xiao-bo, WANG Hai-bo, FU Ling. Identification of Pinelliae Rhizoma Decoction Pieces by Hyperspectral
Imaging Combined With Machine Learning. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(05): 1236-1242.
[1] Chinese Pharmacopoeia Commission(国家药典委员会). Pharmacopoeia of the People's Republic of China(中华人民共和国药典). Beijing: China Medical Sience Press(北京：中国医药科技出版社)，2020，123.
[2] YANG Bing-yue，JING Yong，LAI Yue-yue，et al(杨冰月，敬 勇，赖月月，等). Chinese Journal of Pharmaceutical Analysis(药物分析杂志)，2019，39(11)：1992.
[3] ZHEN Zi-xuan，GE Shu-jun(甄子萱，葛淑俊). Journal of Chinese Medicinal Materials(中药材)，2017，40(12)：2820.
[4] Soni A，Dixit Y，Reis M M，et al. Comprehensive Reviews in Food Science and Food Safety，2022，21(4)，3717.
[5] DUAN Long，YAN Tian-xing，WANG Jiang-li，et al(段 龙，鄢天荥，王江丽，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2021，41(12)：3857.
[6] LIU Yin-nian，XUE Yong-qi(刘银年，薛永祺). Acta Geodaetica et Cartographica Sinica(测绘学报)，2023，52(7)：1045.
[7] ZHANG Li-fu，WANG Sa，ZHANG Yan，et al(张立福，王 飒，张 燕，等). Acta Geodaetica et Cartographica Sinica(测绘学报)，2023，52(7)：1126.
[8] Xu Z Y，Hu H Q，Wang T T，et al. Computers and Electronics in Agriculture，2023，214：108332.
[9] ZHENG Jie，RU Chen-lei，ZHANG Lu，et al(郑 洁，茹晨雷，张 璐，等). China Journal of Chinese Materia Medica(中国中药杂志)，2021，46(10)：2571.
[10] ZHOU Cong，WANG Hui，YANG Jian，et al(周 聪，王 慧，杨 健，等). China Journal of Chinese Materia Medica(中国中药杂志)，2022，47(22)：6027.
[11] YIN Wen-jun，RU Chen-lei，ZHENG Jie，et al(殷文俊，茹晨雷，郑 洁，等). China Journal of Chinese Materia Medica(中国中药杂志)，2021，46(4)：923.
[12] Sun J，Yao K S，Cheng J H，et al. Journal of Pharmaceutical and Biomedical Analysis，2024, 242：116015.
[13] Ji Y M，Sun L J，Li Y S，et al. Infrared Physics & Technology，2019，99：71.
[14] Erkinbaev C，Derksen K，Paliwal J. Infrared Physics & Technology，2019，98：250.
[15] Ru C L，Li Z H，Tang R Z. Sensors，2019，19(9)：2045.
[16] Jin J，Wang Q. Ecological Informatics，2016，35：1.
[17] Baranowski P，Mazurek W，Pastuszka-Wozniak J. Postharvest Biology and Technology，2013，86：249.
[18] ZHU Li-hui，LI Xiao-ning，ZHANG Ying，et al(朱黎辉，李晓宁，张 莹，等). Computer Engineering and Design(计算机工程与设计)，2014，35(11)：3903.
[19] HU Yi-lei，JIANG Hong-zhe，ZHOU Hong-ping，et al(胡逸磊，姜洪喆，周宏平，等). Food Science(食品科学)，2022，43(16)：324.
[20] Okwuashi O，Ndehedehe C E. Pattern Recognition，2020，103：107298.
[21] Zhang C，Guo C T，Liu F，et al. Journal of Food Engineering，2016，179：11.
[22] Jamal M Z，Lee D H，Hyun D J. IEEE Transactions on Instrumentation and Measurement，2022，71：2504612.
[23] Meng Z，Zhao F，Liang M M. Remote Sensing，2021，13(20)：4060.
[24] Zhao C H，Gao B，Zhang L J，et al. Infrared Physics & Technology，2018，95：61.
