EUVIMEDEUVIMED entdecken
Crossref

Polarization standard filtering enables multi-attribute tobacco grading by near-infrared spectroscopy

Xu Ye, Xinyi Chen, Jinglan Zhang, Mingyu Cheng, Bo Fu, Bin Ai

Analytica Chimica Acta · 2025-12 · 1377 · 344676

DOI: 10.1016/j.aca.2025.344676 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Analytica Chimica Acta, 2025-12. Verfasst von Xu Ye und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Microelectronics and Communication Engineering, Chongqing Key Laboratory of Bio-perception & Intelligent Information Processing, Chongqing …. Hauptthemen laut MEDLINE: Nicotiana. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: Chongqing Municipal Science and Technology Bureau, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Objective, non-destructive grading of tobacco remains elusive because near-infrared (NIR) spectra of leaves from different quality classes are almost indistinguishable. Here we combine a large multi-label spectral data set with a single-pass pre-processing operator to resolve these subtleties. RESULTS: High-resolution NIR reflectance spectra were collected from 971 flue-cured samples and annotated by expert tasters for ten sensory attributes, each compressed into 7-10 calibrated grades. We introduce Polarization-Standard Filtering (PSF), an analytic fusion of modified max-min scaling, variance-aware centering, Centralization transformation and Savitzky-Golay smoothing. PSF increases inter-sample Euclidean distances sevenfold while preserving spectral envelopes, overcoming the 0.99 cosine similarity that hampers raw data. Support-vector machines trained on PSF spectra achieve 99.7 % accuracy for seven-level quality grading-75 % higher than models using unprocessed spectra and 23 % above the best conventional pipeline. Across nine additional sensory attributes, accuracy ranged from 67 % to 98 %, with a median accuracy of 85.2 %. Notably, Fragrance 98.3 %, Impurity 98.3 %, and Mellow 94.9 % also achieved high accuracies. Sliding-window occlusion localizes the most informative wavelengths (1700-1850 nm and 2080-2300 nm) to O-H, N-H and C-H combination bands, enabling chemically interpretable feature reduction to ≤ 8 % of the original channels with minimal accuracy loss. SIGNIFICANCE: The open PSF-NIR framework transforms tobacco flavor evaluation from subjective bench tests to an inline, multi-attribute, machine-readable process.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NicotianaSpectroscopy, Near-InfraredPlant LeavesSupport Vector Machine

Stichwörter der Autor:innen

Machine learningNear infrared spectrumSensory evaluationSignal processingTobacco

Autor:innen und Institutionen

  • School of Microelectronics and Communication Engineering, Chongqing Key Laboratory of Bio-perception & Intelligent Information Processing, Chongqing University, Chongqing, 401331, China.
  • College of Tobacco Science, Henan Agricultural University, Zhengzhou, 450002, China. Electronic address: fubo@henau.edu.cn.
  • School of Microelectronics and Communication Engineering, Chongqing Key Laboratory of Bio-perception & Intelligent Information Processing, Chongqing University, Chongqing, 401331, China. Electronic address: binai@cqu.ed…

Förderung

  • Chongqing Municipal Science and Technology Bureau
  • National Natural Science Foundation of China

Zitieren

APA

Ye, X., Chen, X., Zhang, J., Cheng, M., Fu, B., & Ai, B. (2025). Polarization standard filtering enables multi-attribute tobacco grading by near-infrared spectroscopy. Analytica Chimica Acta, 1377, 344676. https://doi.org/10.1016/j.aca.2025.344676

Vancouver

Ye X, Chen X, Zhang J, Cheng M, Fu B, Ai B. Polarization standard filtering enables multi-attribute tobacco grading by near-infrared spectroscopy. Analytica Chimica Acta. 2025;1377:344676. doi:10.1016/j.aca.2025.344676

BibTeX
@article{Ye2025,
  author = {Ye, Xu and Chen, Xinyi and Zhang, Jinglan and Cheng, Mingyu and Fu, Bo and Ai, Bin},
  title = {Polarization standard filtering enables multi-attribute tobacco grading by near-infrared spectroscopy},
  journal = {Analytica Chimica Acta},
  year = {2025},
  volume = {1377},
  pages = {344676},
  doi = {10.1016/j.aca.2025.344676}
}
Kostenlos starten →