EUVIMEDEUVIMED entdecken
Crossref

High-precision apple classification and traceability based on enhanced CBAM for near-infrared spectroscopy

Shupeng Gao, Minlan Jiang, Yulong Fan, Weifeng Gao, Weixing Zhang, Mohammed A A Al-Qaness

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026

DOI: 10.1016/j.saa.2026.127766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026. Verfasst von Shupeng Gao und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321004, China. Electronic address: MeltBaka@zjnu.edu.cn. Hauptthemen laut MEDLINE: Malus. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 47 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Apple origin traceability is crucial in modern agriculture and the food industry for ensuring food safety, protecting consumer rights, and enhancing brand value. However, traditional spectral analysis methods often exhibit low recognition accuracy due to limited feature extraction and class imbalance. To address these challenges, this study proposes a one-dimensional convolutional neural network (1D-CNN) enhanced with a Convolutional Block Attention Module (CBAM). We collected 2400 near-infrared spectral signatures from 200 apple samples covering four varieties: Gala, Red Marshal, Luochuan, and Jonagold, to construct the experimental dataset. We apply the Multiplicative Scatter Correction (MSC) to preprocess spectral data, effectively eliminating scattering effects and baseline inconsistencies, providing high-quality input data. We design an enhanced CBAM module by introducing standard deviation pooling into channel attention to form a triple pooling strategy, and employ multi-scale convolution to adaptively select spectral features. The dense residual connection architecture ensures the full transmission of deep feature information. Meanwhile, the Balance Softmax Cross-Entropy loss function addresses class imbalance in the dataset, thereby enhancing the model's robustness and generalization. Experimental results demonstrate the model's superior performance, achieving 97.12% ± 0.74% accuracy in apple origin classification.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MalusSpectroscopy, Near-InfraredConvolutional Neural NetworksClassification AlgorithmsFruit

Stichwörter der Autor:innen

CBAM, apple, balance softmaxConvolutional neural networksFood industryMultiplicative scatter correction

Autor:innen und Institutionen

  • College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321004, China. Electronic address: MeltBaka@zjnu.edu.cn.
  • College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321004, China; Zhejiang Institute of Optoelectronics, Jinhua 321004, China. Electronic address: xx99@zjnu.cn.
  • Hangzhou Huacheng Software Technology Co., Ltd., Hangzhou 310000, China. Electronic address: 13646626959@163.com.
  • College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321004, China; Zhejiang Institute of Optoelectronics, Jinhua 321004, China. Electronic address: gaoweifeng@zjnu.edu.cn.
  • College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321004, China. Electronic address: zwx0915@zjnu.edu.cn.
  • College of Physics and Electronic Information Engineering, Zhejiang Normal University, Jinhua 321004, China; Zhejiang Institute of Optoelectronics, Jinhua 321004, China. Electronic address: alqaness@zjnu.edu.cn.

Zitieren

APA

Gao, S., Jiang, M., Fan, Y., Gao, W., Zhang, W., & Al-Qaness, M. A. A. (2026). High-precision apple classification and traceability based on enhanced CBAM for near-infrared spectroscopy. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. https://doi.org/10.1016/j.saa.2026.127766

Vancouver

Gao S, Jiang M, Fan Y, Gao W, Zhang W, Al-Qaness MAA. High-precision apple classification and traceability based on enhanced CBAM for near-infrared spectroscopy. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026. doi:10.1016/j.saa.2026.127766

BibTeX
@article{Gao2026,
  author = {Gao, Shupeng and Jiang, Minlan and Fan, Yulong and Gao, Weifeng and Zhang, Weixing and Al-Qaness, Mohammed A A},
  title = {High-precision apple classification and traceability based on enhanced CBAM for near-infrared spectroscopy},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  doi = {10.1016/j.saa.2026.127766}
}
Kostenlos starten →