Next Article in Journal
Lutein Modulates Stress-Responsive Signaling Pathways in THLE-2 Human Hepatocytes Under Intestinal Failure–Associated Liver Disease Conditions
Next Article in Special Issue
Machine Learning-Enabled Intelligent Analysis of Surface-Enhanced Raman Scattering: Methods, Applications, and Perspectives
Previous Article in Journal
Chalcone and Trans-Chalcone Induce Transcriptomic Changes in Caenorhabditis elegans Compatible with a Novel Cumulative Damage Mode of Action
Previous Article in Special Issue
Developing an Integrated Toolbox for Raman Spectral Analysis with Both Artificial Neural Networks and Machine Learning Algorithms
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Molecules
Volume 31
Issue 9
10.3390/molecules31091412
molecules-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

SERS Mixture Recognition from Pure-Substance Spectra via Component Evidence Learning and Two-Stage Inference

by
Li Fan
1,2,3,
Daoyu Lin
1,2,3,
Liang Shen
4,
Junjun Guo
4,
Ting Lian
1,2,3 and
Yazhou Qin
5,*
1
Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China
2
Key Laboratory of Target Cognition and Application Technology (TCAT), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China
3
School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
4
Keqiao Branch, Shaoxing Municipal Public Security Bureau, Shaoxing 312000, China
5
Key Laboratory of Drug Prevention and Control Technology of Zhejiang Province, Zhejiang Police College, 555 Binwen Road, Binjiang District, Hangzhou 310053, China
*
Author to whom correspondence should be addressed.
Molecules 2026, 31(9), 1412; https://doi.org/10.3390/molecules31091412
Submission received: 31 March 2026 / Revised: 21 April 2026 / Accepted: 21 April 2026 / Published: 24 April 2026
(This article belongs to the Special Issue Advanced Vibrational Spectroscopy)
Browse Figures
Versions Notes

Abstract

Surface-enhanced Raman spectroscopy (SERS) is a powerful tool for molecular analysis, yet the recognition of mixed spectra remains challenging because severe peak overlap makes mixture-specific data expensive to acquire and difficult to cover exhaustively. Current machine-learning approaches often rely on labeled mixture datasets, synthetic mixed spectra, or prior component-matching schemes, making their performance strongly dependent on task-specific mixture data. A pure-spectrum-trained framework for SERS mixture recognition is presented here based on component evidence learning and two-stage inference. Using paraquat, thiram, and tricyclazole as representative target compounds, the framework learns reusable constituent-level evidence directly from pure-substance spectra and converts it into mixture-category predictions within a unified recognition model. This design avoids mixture-specific parameter training while enabling direct recognition of binary and ternary mixtures. Experiments on SERS spectral datasets yielded a mixture recognition accuracy of 98.58%. The results show that pure-substance spectral learning can support accurate recognition of complex SERS mixtures and provide a scalable strategy for mixture analysis when labeled mixture data are limited.
Keywords: surface-enhanced Raman spectroscopy (SERS); spectral mixture recognition; component evidence learning; two-stage inference surface-enhanced Raman spectroscopy (SERS); spectral mixture recognition; component evidence learning; two-stage inference
Graphical Abstract

Share and Cite

MDPI and ACS Style

Fan, L.; Lin, D.; Shen, L.; Guo, J.; Lian, T.; Qin, Y. SERS Mixture Recognition from Pure-Substance Spectra via Component Evidence Learning and Two-Stage Inference. Molecules 2026, 31, 1412. https://doi.org/10.3390/molecules31091412

AMA Style

Fan L, Lin D, Shen L, Guo J, Lian T, Qin Y. SERS Mixture Recognition from Pure-Substance Spectra via Component Evidence Learning and Two-Stage Inference. Molecules. 2026; 31(9):1412. https://doi.org/10.3390/molecules31091412

Chicago/Turabian Style

Fan, Li, Daoyu Lin, Liang Shen, Junjun Guo, Ting Lian, and Yazhou Qin. 2026. "SERS Mixture Recognition from Pure-Substance Spectra via Component Evidence Learning and Two-Stage Inference" Molecules 31, no. 9: 1412. https://doi.org/10.3390/molecules31091412

APA Style

Fan, L., Lin, D., Shen, L., Guo, J., Lian, T., & Qin, Y. (2026). SERS Mixture Recognition from Pure-Substance Spectra via Component Evidence Learning and Two-Stage Inference. Molecules, 31(9), 1412. https://doi.org/10.3390/molecules31091412

Article Metrics

Back to TopTop