EUVIMEDEUVIMED entdecken
Crossref

Bayesian Semi-Supervised Learning (BSSL) for spectral variable selection

Haoran Li, Youhui Jiang, Pengcheng Wu, Yang Zhang, Tao Chen, Xiaobo Zou

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2025-12 · 343 · 126483

DOI: 10.1016/j.saa.2025.126483 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2025-12. Verfasst von Haoran Li und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China. Electronic address: hrli@ujs.edu.cn. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Earmarked Fund for China Agriculture Research System, China Postdoctoral Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Variable selection are increasingly developed and deployed in spectra analysis, ensuring their reliability has become crucial. However, external disturbances during spectrum measurement, such as noise and distribution shifts, can introduce uncertainties that challenge the reliability of variable selection. To address these challenges, a Bayesian Semi-Supervised Learning (BSSL) framework for variable selection and model updating was developed. First, we propose a Bayesian variable selection method based on maximum likelihood estimation (MLE) and posterior variance, which assesses variable uncertainty by probabilistic framework. Second, we develop a semi-supervised learning framework that incorporates unlabeled target samples for model adaptation. A pseudo-labeling update strategy is employed, allowing neighboring variables to be adjusted, thereby enhancing the model's performance on the target dataset. Extensive experiments on publicly available datasets validate the effectiveness of the proposed algorithm. Moreover, the selected variables consistently align with the sensitive spectral regions associated with the target analytes, and updates tend to occur in neighboring regions. These results not only indicate the enhanced predictive performance but also prove the interpretability and robustness of the method.

Schlagwörter

Stichwörter der Autor:innen

Bayesian inferenceModel updatingMultivariate calibrationSemi-supervised learningVariable selection

Autor:innen und Institutionen

  • School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China. Electronic address: hrli@ujs.edu.cn.
  • School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China.
  • School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, China.
  • Department of Chemical and Process Engineering, University of Surrey, Guildford GU2 7XH, United Kingdom.
  • School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, China. Electronic address: xiaobo@ujs.edu.cn.

Förderung

  • National Key Research and Development Program of China
  • Earmarked Fund for China Agriculture Research System
  • China Postdoctoral Science Foundation

Zitieren

APA

Li, H., Jiang, Y., Wu, P., Zhang, Y., Chen, T., & Zou, X. (2025). Bayesian Semi-Supervised Learning (BSSL) for spectral variable selection. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 343, 126483. https://doi.org/10.1016/j.saa.2025.126483

Vancouver

Li H, Jiang Y, Wu P, Zhang Y, Chen T, Zou X. Bayesian Semi-Supervised Learning (BSSL) for spectral variable selection. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2025;343:126483. doi:10.1016/j.saa.2025.126483

BibTeX
@article{Li2025,
  author = {Li, Haoran and Jiang, Youhui and Wu, Pengcheng and Zhang, Yang and Chen, Tao and Zou, Xiaobo},
  title = {Bayesian Semi-Supervised Learning (BSSL) for spectral variable selection},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2025},
  volume = {343},
  pages = {126483},
  doi = {10.1016/j.saa.2025.126483}
}
Kostenlos starten →