Online First

 Preview Page

Research Article

Classification Model of Ziziphi spinosae semen and Ziziphi mauritianae semen Using Hyperspectral Imaging
Soo Hyun Shin123
,
Da Hye Ryu1
,
Jwa Yeong Cho1
,
Yu Jin Kwon14
,
Gyeongmin Lee1
,
Jung-Seok Yang1
,
Ho-Youn Kim15
,
Soo Hyun Park14*
1Smart Farm Research Center, Korea Institute of Science and Technology (KIST), Gangneung 25451, Korea
2Department of Smart Farm Science, Kyung Hee University, Yongin 17104, Korea
3Department of Biosystems Engineering, College of Agriculture and Life Sciences, Seoul National University, Seoul 08826, Korea
4Department of Plant Biotechnology, College of Life Sciences and Biotechnology, Korea University, Seoul 02841, Korea
5Natural Product Applied Science, KIST school, University of Science and Technology (UST), Gangneung, Gangwon 25451, Korea
*Corresponding Author
PDF XML Citation
Abstract

This study aimed to develop a hyperspectral imaging (HSI)-based classification model for distinguishing Ziziphi spinosae semen (ZSS) from Ziziphi mauritianae semen (ZMS) using AutoGluon, an automated machine learning (AutoML) framework. Conventional morphological and genetic identification methods are often costly, destructive, and time-consuming, whereas HSI enables rapid, non-contact, and nondestructive acquisition of extensive spectral information, making it suitable for large-scale verification of herbal medicine samples. A diverse set of ZSS and ZMS samples was collected, and spectral data were acquired over the 400–1,000 nm range. Sample authenticity was verified using ultra-performance liquid chromatography (UPLC) to improve dataset reliability. After spectral preprocessing using Savitzky–Golay smoothing, standard normal variate, and first-derivative transformation, AutoGluon was used to construct the classification model. The final model achieved a mean pixel-level accuracy of 98.40% ± 0.91% under 5-fold GroupKFold cross-validation on the UPLC-verified dataset. At the individual-seed level, only 3 of 169 seeds were misclassified, including 2 ZMS seeds classified as ZSS and 1 ZSS seed classified as ZMS. Permutation-based feature importance identified 628.66 nm as the most influential wavelength, and all ten most important wavelengths were located within the 596–677 nm region. Point-biserial correlation analysis showed a similar tendency in this spectral region. Misclassified seeds exhibited lower raw reflectance, occupied borderline positions between the ZSS and ZMS clusters in the preprocessed feature space, and showed lower majority-vote margins than correctly classified seeds, suggesting that the remaining errors were associated with spectrally borderline samples rather than simple brightness differences. These findings demonstrate that HSI combined with AutoGluon provides a rapid, nondestructive, and high-precision approach for authenticating ZSS and detecting ZMS adulteration, with potential applications in herbal medicine quality control and related agricultural and food sectors.

Keywords
adulteration detection
automated machine learning
non-destructive analysis
spectral feature extraction
spectral preprocessing
stacked ensemble
References
1

An J, Kim IS, Kim KJ, Park JH, Kang H, Kim HJ, Kim YS, Ahn JH (2024) Efficacy of automated machine learning models and feature engineering for diagnosis of equivocal appendicitis using clinical and computed tomography findings. Sci Rep 14:22658. https://doi.org/10.1038/s41598-024-72889-9

10.1038/s41598-024-72889-939349512PMC11442641
2

Barnes RJ, Dhanoa MS, Lister SJ (1989) Standard normal variate transformation and de-trending of near-infrared diffuse reflectance spectra. Appl Spectrosc 43:772-777. https://doi.org/10.1366/0003702894202201

10.1366/0003702894202201
3

Bochkovskiy A, Wang CY, Liao HYM (2020) YOLOv4: Optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934

4

Boughorbel S, Jarray F, El-Anbari M (2017) Optimal classifier for imbalanced data using Matthews correlation coefficient metric. PLoS One 12:e0177678. https://doi.org/10.1371/journal.pone.0177678

10.1371/journal.pone.017767828574989PMC5456046
5

Chen CJ, Li M, Wang XL, Fang FF, Ling CQ (2011) Effect of sour date (Semen ziziphi spinosae) seed extract on treating insomnia and anxiety. In: Nuts and Seeds in Health and Disease Prevention. Elsevier, pp 1037-1043. https://doi.org/10.1016/B978-0-12-375688-6.10123-9

10.1016/B978-0-12-375688-6.10123-9
6

Chen P, Shao X, Wen G, Song Y, Fu R, Xiao X, Lu T, Zhou P, Guo Q, et al. (2024) Computer vision-based fire–ice ion algorithm for rapid and nondestructive authentication of Ziziphi Spinosae Semen and its counterfeits. Foods 14:5. https://doi.org/10.3390/foods14010005

10.3390/foods1401000539796295PMC11719666
7

Chlebda DK, Rogulska A, Łojewski T (2017) Assessment of hyperspectral imaging system for colour measurement. Spectrochim Acta A Mol Biomol Spectrosc 185:55-62. https://doi.org/10.1016/j.saa.2017.05.037

10.1016/j.saa.2017.05.037
8

Davies A (2007) Back to basics: spectral pre-treatments—derivatives. Spectrosc Eur 19:32-33

9

Erickson N, Mueller J, Shirkov A, Zhang H, Larroy P, Li M, Smola A (2020) AutoGluon-tabular: robust and accurate AutoML for structured data. arXiv preprint arXiv:2003.06505

10

Esquerre C, Gowen A, Burger J, Downey G, O’Donnell C (2012) Suppressing sample morphology effects in near infrared spectral imaging using chemometric data pre-treatments. Chemom Intell Lab Syst 117:129-137. https://doi.org/10.1016/j.chemolab.2012.02.006

10.1016/j.chemolab.2012.02.006
11

Fang XS, Hao J, Zhou H, Zhu L, Wang J, Song F (2010) Pharmacological studies on the sedative-hypnotic effect of Semen Ziziphi spinosae (Suanzaoren) and Radix et Rhizoma Salviae miltiorrhizae (Danshen) extracts and the synergistic effect of their combinations. Phytomedicine 17:75-80. https://doi.org/10.1016/j.phymed.2009.07.004

10.1016/j.phymed.2009.07.004
12

García V, Mollineda RA, Sánchez JS (2009) Index of balanced accuracy: a performance measure for skewed class distributions. In: Proc Iberian Conf Pattern Recognit Image Anal. Springer, pp 441-448. https://doi.org/10.1007/978-3-642-02172-5_57

10.1007/978-3-642-02172-5_57
13

Grewal R, Singh Kasana S, Kasana G (2023) Machine learning and deep learning techniques for spectral spatial classification of hyperspectral images: a comprehensive survey. Electronics 12:488. https://doi.org/10.3390/electronics12030488

10.3390/electronics12030488
14

Guo D, Zhu Q, Huang M, Guo Y, Qin J (2017) Model updating for the classification of different varieties of maize seeds from different years by hyperspectral imaging coupled with a pre-labeling method. Comput Electron Agric 142:1-8. https://doi.org/10.1016/j.compag.2017.08.015

10.1016/j.compag.2017.08.015
15

Hopkins DW (2001) What is a Norris derivative? NIR News 12:3-5. https://doi.org/10.1255/nirn.611

10.1255/nirn.611
16

Janse RJ, Hoekstra T, Jager KJ, Zoccali C, Tripepi G, Dekker FW, van Diepen M (2021) Conducting correlation analysis: important limitations and pitfalls. Clin Kidney J 14:2332-2337. https://doi.org/10.1093/ckj/sfab085

10.1093/ckj/sfab08534754428PMC8572982
17

Kim WI, Zhao BT, Zhang HY, Lee JH, Son JK, Woo MH (2014) Quantitative and pattern recognition analyses of magnoflorine, spinosin, 6'''-feruloyl spinosin and jujuboside A by HPLC in Zizyphi Semen. Arch Pharm Res 37:1139-1147. https://doi.org/10.1007/s12272-013-0295-z

10.1007/s12272-013-0295-z24310099PMC4143599
18

Li MX, Shi YB, Zhang JB, Wan X, Fang J, Wu Y, Fu R, Li Y, Li L, et al. (2023) Rapid evaluation of Ziziphi Spinosae Semen and its adulterants based on the combination of FT-NIR and multivariate algorithms. Food Chem X 20:101022. https://doi.org/10.1016/j.fochx.2023.101022

10.1016/j.fochx.2023.10102238144802PMC10740088
19

Li X, Jiang H, Jiang X, Shi M (2021) Identification of geographical origin of Chinese chestnuts using hyperspectral imaging with 1D-CNN algorithm. Agriculture 11:1274. https://doi.org/10.3390/agriculture11121274

10.3390/agriculture11121274
20

Li X, Zhai M, Zheng L, Zhou L, Xie X, Zhao W, Zhang W (2024) Efficient residual network using hyperspectral images for corn variety identification. Front Plant Sci 15:1376915. https://doi.org/10.3389/fpls.2024.1376915

10.3389/fpls.2024.137691538689841PMC11058231
21

Makantasis K, Doulamis AD, Doulamis ND, Nikitakis A (2018) Tensor-based classification models for hyperspectral data analysis. IEEE Trans Geosci Remote Sens 56:6884-6898. https://doi.org/10.1109/TGRS.2018.2845450

10.1109/TGRS.2018.2845450
22

Qiu Z, Chen J, Zhao Y, Zhu S, He Y, Zhang C (2018) Variety identification of single rice seed using hyperspectral imaging combined with convolutional neural network. Appl Sci 8:212. https://doi.org/10.3390/app8020212

10.3390/app8020212
23

Rinnan Å, van den Berg F, Engelsen SB (2009) Review of the most common pre-processing techniques for near-infrared spectra. TrAC Trends Anal Chem 28:1201-1222. https://doi.org/10.1016/j.trac.2009.07.007

10.1016/j.trac.2009.07.007
24

Savitzky A, Golay MJ (1964) Smoothing and differentiation of data by simplified least squares procedures. Anal Chem 36:1627-1639. https://doi.org/10.1021/ac60214a047

10.1021/ac60214a047
25

Sharabian VR, Noguchi N, Ishi K (2014) Significant wavelengths for prediction of winter wheat growth status and grain yield using multivariate analysis. Eng Agric Environ Food 7:14-21. https://doi.org/10.1016/j.eaef.2013.12.003

10.1016/j.eaef.2013.12.003
26

Shi X, Mueller J, Erickson N, Li M, Smola A (2021) Multimodal AutoML on structured tables with text fields. In: Proc ICML Workshop on automated machine learning (AutoML)

27

Sun S, Liu H, Xu S, Yan Y, Xie P (2014) Quality analysis of commercial samples of Ziziphi Spinosae Semen (suanzaoren) by means of chromatographic fingerprinting assisted by principal component analysis. J Pharm Anal 4:217-222. https://doi.org/10.1016/j.jpha.2014.01.003

10.1016/j.jpha.2014.01.00329403885PMC5761125
28

Taghizadeh M, Gowen AA, O’Donnell CP (2011) Comparison of hyperspectral imaging with conventional RGB imaging for quality evaluation of Agaricus bisporus mushrooms. Biosyst Eng 108:191-194. https://doi.org/10.1016/j.biosystemseng.2010.10.005

10.1016/j.biosystemseng.2010.10.005
29

Tang Z, Guo J, Xiang Y, Lu X, Wang Q, Wang H, Cheng M, Wang H, Wang X, et al. (2022) Estimation of leaf area index and above-ground biomass of winter wheat based on optimal spectral index. Agronomy 12:1729. https://doi.org/10.3390/agronomy12071729

10.3390/agronomy12071729
30

Velasco-Forero S, Manian V (2009) Improving hyperspectral image classification using spatial preprocessing. IEEE Geosci Remote Sens Lett 6:297-301. https://doi.org/10.1109/LGRS.2009.2012443

10.1109/LGRS.2009.2012443
31

Wang L, Pang L, Yan L, Zhang J (2022) Nondestructive rapid identification of soybean varieties using hyperspectral imaging technology. J Appl Spectrosc 89:84-91. https://doi.org/10.1007/s10812-022-01329-1

10.1007/s10812-022-01329-1
32

Wu N, Liu F, Meng F, Li M, Zhang C, He Y (2021) Rapid and accurate varieties classification of crop seeds under sample-limited conditions using hyperspectral imaging and deep transfer learning. Front Bioeng Biotechnol 9:696292. https://doi.org/10.3389/fbioe.2021.696292

10.3389/fbioe.2021.69629234368096PMC8343196
33

Xia FL, Cao HW, Gao LX, Qing K, Mei L, Wang CJ, Yang N (2023) Identification of Ziziphi Spinosae Semen from its adulterants based on RAPD. Pharmacogn Mag 19:763-771. https://doi.org/10.1177/09731296231171216

10.1177/09731296231171216
34

Xie Z (1996) Chinese Herbal Medicine Compilation. People’s Medical Publishing House, Beijing

35

Xu L, Cai F, Hu Y, Lin Z, Liu Q (2021) Using deep learning algorithms to perform accurate spectral classification. Optik 231:166423. https://doi.org/10.1016/j.ijleo.2021.166423

10.1016/j.ijleo.2021.166423
36

Xu Y, Wu W, Chen Y, Zhang T, Tu K, Hao Y, Cao H, Dong X, Sun Q (2022) Hyperspectral imaging with machine learning for non-destructive classification of Astragalus membranaceus var. mongholicus, Astragalus membranaceus, and similar seeds. Front Plant Sci 13:1031849. https://doi.org/10.3389/fpls.2022.1031849

10.3389/fpls.2022.103184936523615PMC9745075
37

Yan Y, Shen C, Pei X, Li A, Du H, Qin X, Du C (2020) Comparison of chemical profiling of Ziziphi Spinosae Semen and Ziziphi Mauritianae Semen using untargeted metabolomics. J Food Compos Anal 94:103635. https://doi.org/10.1016/j.jfca.2020.103635

10.1016/j.jfca.2020.103635
38

Yang CW, Chen S, Ouyang F, Yang IC, Tsai CY (2011) A robust identification model for herbal medicine using near infrared spectroscopy and artificial neural network. J Food Drug Anal 19:9. https://doi.org/10.38212/2224-6614.2193

10.38212/2224-6614.2193
39

Yeung WF, Chung KF, Poon MMK, Ho FYY, Zhang SP, Zhang ZJ, Ziea ETC, Wong VT (2012) Chinese herbal medicine for insomnia: a systematic review of randomized controlled trials. Sleep Med Rev 16:497-507. https://doi.org/10.1016/j.smrv.2011.12.005

10.1016/j.smrv.2011.12.005
40

Zhang FX, Li M, Qiao LR, Yao ZH, Li C, Shen XY, Wang Y, Yu K, Yao XS, et al. (2016) Rapid characterization of Ziziphi Spinosae Semen by UPLC/Qtof MS with novel informatics platform and its application in evaluation of two seeds from Ziziphus species. J Pharm Biomed Anal 122:59-80. https://doi.org/10.1016/j.jpba.2016.01.047

10.1016/j.jpba.2016.01.047
41

Zhang X, Ding C, Li H (2009) Research progress on chemical compositions and pharmacological effects of Semen ziziphi spinosae. Sci Technol Food Ind 3:348-350

42

Zhao X, Liu X, Xie P, Ma J, Shi Y, Jiang H, Zhao Z, Wang X, Li C, et al. (2024) Identification of geographical origin of Semen ziziphi spinosae using hyperspectral imaging and convolutional neural networks. Infrared Phys Technol 136:104982. https://doi.org/10.1016/j.infrared.2023.104982

10.1016/j.infrared.2023.104982
43

Zhu S, Chao M, Zhang J, Xu X, Song P, Zhang J, Huang Z (2019) Identification of soybean seed varieties using hyperspectral imaging technology. Sensors 19:5225. https://doi.org/10.3390/s19235225

10.3390/s1923522531795146PMC6929038
Information
  • Publisher :KOREAN SOCIETY FOR HORTICULTURAL SCIENCE
  • Publisher(Ko) :한국원예학회
  • Journal Title :Horticultural Science and Technology
  • Journal Title(Ko) :원예과학기술지
  • Received Date : 2026-03-04
  • Revised Date : 2026-07-17
  • Accepted Date : 2026-07-30
  • DOI :https://doi.org/10.7235/HORT.20260029
Journal Informaiton Horticultural Science and Technology Horticultural Science and Technology
Online Submission
  • scopus
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close