Key Feature Analysis in Identification and Authenticity of Ziziphi Spinosae Semen by Using Hyperspectral Images Based on 1DCNN and PLSDA
ZHAO Xin1, 4, SHI Yu-na1, LIU Yi-tong1, JIANG Hong-zhe2, CHU Xuan3, ZHAO Zhi-lei1, 4, WANG Bao-jun1, 4*, CHEN Han1
1. School of Quality and Technical Supervision, Hebei University, Baoding 071002, China
2. College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China
3. College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
4. National & Local Joint Engineering Research Center of Metrology Instrument and System, Hebei University, Baoding 071002, China
Abstract：Ziziphi spinosae semen is an important raw material of health care products and traditional Chinese medicine preparations because it nourishes the heart and the liver, making it ideal for calming the nerves and helping sleep. At present, the adulteration of ziziphi spinosadsemen in the market is serious, which greatly damages the interests of consumers and disrupts the market order. Traditional manual detection or laboratory-based high-performance liquid chromatography methods have problems of low efficiency and difficult promotion. In this study, a hyperspectral imaging method for ziziphi spinosadsemen authenticity identification was proposed based on convolutional neural network and partial least squares discrimination, and the key spectral features in the two types of models were discussed and studied. The study will reference the subsequent development of multispectral systems and portable instruments. The average spectra of all single kernels in the hyperspectral images (400~1 000 nm) of ziziphi spinosae semen and its common counterfeits (Ziziphus mauritiana lam, Hovenia dulcis Thunb. and Lens culinaris) were extracted. The partialleast squares discriminant analysis (PLSDA) model and the one-dimensional convolutional neural network (1DCNN) model were respectively established based on the average spectra. The competitive adaptive reweighting algorithm (CARS) selects characteristic wavelengths before PLSDA modeling. A custom wavelength selection layer was added to the 1DCNN model. T-distributed stochastic neighborhood embedding (t-SNE) was applied to the outputs of convolutional and fully connected layers for visual analysis. To effectively compare with the CARS-PLSDA model, a 5W-1DCNN model based on five wavelengths was constructed. The results showed that both the CARS-PLSDA and1DCNN models could achieve precision prediction results, and the classification accuracies of both the calibration set and the prediction set are above 0.99. Comparing the feature wavelengths selected by CARS and custom layers, wavelengths near 670, 721, and 850 nm play important roles in both models. The research results provided a reference for multispectral systems and portable equipment for rapid detection of the authenticity of ziziphi spinosad semen.
赵 昕，石玉娜，刘怡彤，姜洪喆，褚 璇，赵志磊，王宝军，陈 晗. 基于1DCNN和PLSDA酸枣仁真伪高光谱图像鉴别中的关键特征分析[J]. 光谱学与光谱分析, 2025, 45(03): 869-877.
ZHAO Xin, SHI Yu-na, LIU Yi-tong, JIANG Hong-zhe, CHU Xuan, ZHAO Zhi-lei, WANG Bao-jun, CHEN Han. Key Feature Analysis in Identification and Authenticity of Ziziphi Spinosae Semen by Using Hyperspectral Images Based on 1DCNN and PLSDA. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(03): 869-877.
[1] LI Li-li, LÜ Yi-feng, ZHANG Hui, et al（李丽莉，吕轶峰，张 慧，等）. Chinese Journal of Pharmaceutical Analysis（药物分析杂志），2023，43(4)：693.
[2] CHEN Man, JIN Cheng-qian, MO Gong-wu, et al（陈 满，金诚谦，莫恭武，等）. Transactions of the Chinese Society for Agricultural Machinery（农业机械学报），2023，54(2)：73.
[3] Lintvedt T A, Andersen P V, Afseth N K, et al. Talanta, 2023, 254: 124113.
[4] Shang M, Xue L, Zhang Y, et al. Journal of Food Science, 2023, 88(6): 2488.
[5] LIN Long, WU Jing-zhu, LIU Cui-ling, et al（林 珑，吴静珠，刘翠玲，等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析），2020，40(3)：905.
[6] LI Wei, HUANG Yun-feng, DAI Zuo-xiao, et al（李 威，黄云峰，代作晓，等）. Journal of Food Safety & Quality（食品安全质量检测学报），2023，14(1)：98.
[7] Alzubaidi L, Zhang J, Humaidi A J, et al. Journal of Big Data, 2021, 8: 53.
[8] GAO Wen-qiang, XIAO Zhi-yun（高文强，肖志云）. Journal of Chinese Agricultural Mechanization（中国农机化学报），2022，43(7)：158.
[9] WANG Rong, ZHENG En-rang, CHEN Bei（王 蓉，郑恩让，陈 蓓）. Journal of the Chinese Cereals and Oils Association（中国粮油学报），2023，38(6)：141.
[10] Zhou L, Tan L, Zhang C, et al. LWT, 2022, 153: 112456.
[11] Meng S, Wang X, Hu X, et al. Computers and Electronics in Agriculture, 2021, 186: 106188.
[12] Van der Maaten L, Hinton G. Journal of Machine Learning Research, 2008, 9(11): 2579.
[13] Zerbini P E, Vanoli M, Rizzolo A, et al. Postharvest Biology and Technology, 2015, 101: 58.
[14] Siedliska A, Baranowski P, Zubik M, et al. Postharvest Biology and Technology, 2018, 139: 115.
[15] Martinsen P, Schaare P. Postharvest Biology and Technology, 1998, 14: 271.
[16] Guo Z, Wang M M, Agyekum A A, et al. Journal of Food Engineering, 2020, 279: 109955.
[17] Osborne B G. Near Infrared Spectroscopy in Food Analysis. Longman Scientific and Technical, 1986, 117.
