PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
April 26, 2026Journal of Food Composition and Analysis0 citationsOpen Access

Bionic feature selection strategy for integrated filters empowers ATR-FTIR spectroscopy to trace the geographic origins of Sichuan-style Nongxiangxing Baijiu

View Full Paper
RZRui ZhouSouthwest University of Science and TechnologyXCXiaoming ChenSouthwest University of Science and TechnologyDXDefu XuFirst Affiliated Hospital of Sichuan Medical University

Key Points

  • This study aims to trace the geographic origins of Sichuan-style Nongxiangxing Baijiu using ATR-FTIR spectroscopy and machine learning techniques.
  • Developed a non-destructive analytical strategy using ATR-FTIR spectroscopy integrated with spectral preprocessing and feature selection.
  • Applied the Synthetic Minority Oversampling Technique (SMOTE) alongside classifiers like k-Nearest Neighbors (KNN) and Support Vector Machines (SVM).
  • Evaluated model performance on validation and independent test sets to ensure classification accuracy.
  • KNN achieved 100% classification performance on the validation set under specific model configurations.
  • Bionic feature selection improved model generalization, resulting in a 91.67% accuracy on the independent test set, a 41.67% improvement over the baseline model.
  • Vital spectral features identified at wavenumbers 2360 cm⁻¹, 2343 cm⁻¹, and 2336 cm⁻¹ significantly influenced classification decisions.

Abstract

The misuse of Baijiu origin labeling poses significant risks to both producers and consumers. In this study, the geographic origin of Sichuan-style Nongxiangxing Baijiu was investigated using attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy combined with machine learning techniques. A rapid, non-destructive, and cost-effective analytical strategy was developed by integrating spectral preprocessing, the Synthetic Minority Oversampling Technique (SMOTE), and feature selection. Under specific model configurations, SMOTE combined with k-Nearest Neighbors (KNN) and Support Vector Machines (SVM) achieved 100% classification performance on the validation set, indicating strong discriminative capability under controlled experimental conditions. Furthermore, the introduction of a bionic feature selection strategy improved model generalization performance. The KNN model constructed using 14 selected spectral markers achieved an accuracy of 91.67% on an independent test set, representing a 41.67% improvement compared with the model without feature selection. Shapley additive explanations identified wavenumbers at 2360 cm⁻¹, 2343 cm⁻¹, and 2336 cm⁻¹ as the most influential spectral features contributing to classification. Overall, this study demonstrates the potential of ATR-FTIR spectroscopy integrated with intelligent data-driven strategies for Baijiu origin tracing and provides a transferable framework for non-targeted spectral classification tasks. • A non-destructive method was developed to trace the origin of baijiu. • Category imbalance will affect the training and identification of classifiers. • A bionic feature selection strategy effectively enhanced model generalizability. • Independent test set validation highlights the practical application of the model. • SHAP analysis revealed critical wavelengths contributing to classification decisions.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Zhou et al. (2026) studied this question.

synapsesocial.com/papers/69edacbd4a46254e215b47d4https://doi.org/10.1016/j.jfca.2026.109190
Ask AI
Helpful
Bookmark
Share
View Full Paper