Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 53 min ago
Peer-reviewedCC BYFood Science & Nutrition

Counterfeit Citri Reticulatae Pericarpium Identification: Multi‐Class Detection Using Vis/ NIR Spectroscopy and Residual Neural Networks

  • Chao Ma1
  • Mingkun Zhang1
  • Jianwei Ma1
  • Sudan Chen2
  • Yunxia Yuan3
  • Mingtong Du4
  • Zhiyong Dai5
5 affiliations
  1. 1College of Information Engineering Henan University of Science and Technology Luoyang China
  2. 2College of Horticulture and Plant Protection Henan University of Science and Technology Luoyang China
  3. 3College of Food and Bioengineering Henan University of Science and Technology Luoyang China
  4. 4College of Computing and Data Science Nanyang Technological University Singapore Singapore
  5. 5Complex Systems Intelligent Control Laboratory Shanghai Jiao Tong University Shanghai China
Open at sourceDOICite

Abstract

(CRP) have led to frequent counterfeiting. Rapid and non-destructive identification of counterfeit CRP is therefore essential. This study proposes a novel detection model that integrates visible/near-infrared (Vis/NIR) spectroscopy with deep learning algorithms. Authentic CRP and four types of counterfeit CRP samples were collected, and their multispectral Vis/NIR data were acquired. Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) data augmentation enhanced model generalization, further improving classification robustness. After spectral preprocessing, deep learning models were applied to classify and detect different CRP types, aiming to identify the optimal network for counterfeit discrimination. The experimental results demonstrated that the Inception-ResNet model achieved the test set accuracy of 96.56% in identifying authentic CRP from four counterfeit categories, outperforming conventional machine learning approaches. This study provides a precise and efficient model for non-destructive authentication and adulteration analysis of CRP.

Related

  1. Identification of twelve frequently processed wood species from Ivorian forests by carpenters using near-infrared spectroscopy
    Jean Louis Lepetit N’guessan, Bobelé Forence Niamké, Hakim Abdel Aziz Ouattara +4
    Sciences des Structures et de la MatierePeer-reviewedCC BY 4.0Full textAnalytical chemistryHAL
  2. Detection Defines Dephasing in Two-Dimensional Electronic Spectroscopy of Materials: Coherent Field Emission versus Incoherent Population Observables
    Simón Paiva-Ortega, Hao Li, Eric R. Bittner +1
    arXivPreprintCC BY 4.0Full textPhysical chemistryCondensed matterarXiv
  3. Detection of Thermally Induced Damage in Large-Format Lithium-Ion Batteries Using Electrochemical Impedance Spectroscopy
    Christoph Drießen, Shubham Bhoir, Christian Ellersdorfer
    BatteriesPeer-reviewedCC BY 4.0Full textElectrochemistry & energyCrossrefDOAJ
  4. Crack identification and detection in mine boreholes using deep learning: A case study of hexi coal mine
    Ruifeng Huang, Wanshun He, Lu Chen +2
    PLOS OnePeer-reviewedCC BY 4.0Materials & polymersPLOS
  5. Donor-level validation of Raman spectroscopy for breast cancer subtype classification
    ali khoshnami, Seyedeh Rahemeh Amiri
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv

Cite

BibTeXRIS
BibTeX
@article{ma2026counterfeit,
  title = {{Counterfeit Citri Reticulatae Pericarpium Identification: Multi‐Class Detection Using Vis/ NIR Spectroscopy and Residual Neural Networks}},
  author = {Chao Ma and Mingkun Zhang and Jianwei Ma and Sudan Chen and Yunxia Yuan and Mingtong Du and Zhiyong Dai},
  journal = {Food Science \& Nutrition},
  year = {2026},
  month = jun,
  doi = {10.1002/fsn3.71975},
  url = {https://doi.org/10.1002/fsn3.71975},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Counterfeit Citri Reticulatae Pericarpium Identification: Multi‐Class Detection Using Vis/ NIR Spectroscopy and Residual Neural Networks
AU  - Chao Ma
AU  - Mingkun Zhang
AU  - Jianwei Ma
AU  - Sudan Chen
AU  - Yunxia Yuan
AU  - Mingtong Du
AU  - Zhiyong Dai
PY  - 2026
DA  - 2026/06/01
JO  - Food Science & Nutrition
DO  - 10.1002/fsn3.71975
UR  - https://doi.org/10.1002/fsn3.71975
AB  - (CRP) have led to frequent counterfeiting. Rapid and non-destructive identification of counterfeit CRP is therefore essential. This study proposes a novel detection model that integrates visible/near-infrared (Vis/NIR) spectroscopy with deep learning algorithms. Authentic CRP and four types of counterfeit CRP samples were collected, and their multispectral Vis/NIR data were acquired. Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) data augmentation enhanced model generalization, further improving classification robustness. After spectral preprocessing, deep learning models were applied to classify and detect different CRP types, aiming to identify the optimal network for counterfeit discrimination. The experimental results demonstrated that the Inception-ResNet model achieved the test set accuracy of 96.56% in identifying authentic CRP from four counterfeit categories, outperforming conventional machine learning approaches. This study provides a precise and efficient model for non-destructive authentication and adulteration analysis of CRP.
SN  - 2048-7177
ER  -