EUVIMEDEUVIMED entdecken
Crossref

Early apple moldy core classification via multi-modal sensing and SE-ResNet18

Ruifeng Wang, Ninghua Zhu, Xuexia Ma, Na Li, Tingting Li, Jiaxue Ma, Zhongxiong Zhang, Songlei Wang, Haifeng Li

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-11 · 360 · 128056

DOI: 10.1016/j.saa.2026.128056 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-11. Verfasst von Ruifeng Wang und 8 weiteren Autor:innen. Beteiligte Einrichtung: College of Food Science and Engineering, Ningxia University, Yinchuan 750021, China. Hauptthemen laut MEDLINE: Malus, Plant Diseases, Electronic Nose. Die Arbeit nennt 35 Literaturangaben. Gefördert von: Natural Science Foundation of Ningxia Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Apple moldy core disease is a major pathogenic disease that severely degrades the postharvest quality of apples, and its early internal lesions cannot be directly identified through visual appearance observation. To realize efficient and non-destructive early diagnosis, this study proposes a multimodal image coding method fusing Visible-Near Infrared Spectroscopy (Vis-NIR) and Electronic Nose (E-nose) data, which is combined with the SE-ResNet18 deep learning model for disease classification. By virtue of coding techniques including Gramian Angular Field (GAF), Markov Transition Field (MTF), and Recurrence Plot (RP), one-dimensional time-series and spectral data were converted into image representations, so as to visualize their spatiotemporal patterns and enhance subtle disease-related features. On this basis, a two-branch SE-ResNet18 model based on the channel attention mechanism was constructed to improve the feature representation capability and achieve effective modal fusion. Experimental results show that the multimodal fusion model achieves a classification accuracy of 95.93%, which is significantly superior to single-modal methods, thus verifying the effectiveness of multi-source information complementarity. Ablation experiments further indicate that the SE attention module plays a crucial role in feature calibration and modal balance. Information entropy analysis reveals that the proposed method effectively enhances the discriminability of information during the feature extraction process. This study provides a solution with a clear theoretical basis and reliable performance for the non-destructive detection of early diseases in agricultural products, which has favorable application prospects and popularization potential.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MalusPlant DiseasesElectronic NoseSpectroscopy, Near-InfraredDeep LearningConvolutional Neural Networks

Stichwörter der Autor:innen

Attention mechanismDeep learningEarly-stage apple moldy core diseaseElectronic noseVisible-near infrared spectroscopy

Autor:innen und Institutionen

  • College of Food Science and Engineering, Ningxia University, Yinchuan 750021, China.
  • College of Food Science and Engineering, Ningxia University, Yinchuan 750021, China. Electronic address: zzx9519@nwafu.edu.cn.
  • College of Food Science and Engineering, Ningxia University, Yinchuan 750021, China. Electronic address: lihaifeng0426@nxu.edu.cn.

Förderung

  • Natural Science Foundation of Ningxia Province

Zitieren

APA

Wang, R., Zhu, N., Ma, X., Li, N., Li, T., Ma, J., Zhang, Z., Wang, S., & Li, H. (2026). Early apple moldy core classification via multi-modal sensing and SE-ResNet18. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 360, 128056. https://doi.org/10.1016/j.saa.2026.128056

Vancouver

Wang R, Zhu N, Ma X, Li N, Li T, Ma J, et al. Early apple moldy core classification via multi-modal sensing and SE-ResNet18. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;360:128056. doi:10.1016/j.saa.2026.128056

BibTeX
@article{Wang2026,
  author = {Wang, Ruifeng and Zhu, Ninghua and Ma, Xuexia and Li, Na and Li, Tingting and Ma, Jiaxue and Zhang, Zhongxiong and Wang, Songlei and Li, Haifeng},
  title = {Early apple moldy core classification via multi-modal sensing and SE-ResNet18},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  volume = {360},
  pages = {128056},
  doi = {10.1016/j.saa.2026.128056}
}
Kostenlos starten →