Machine Learning-Assisted Ratiometric Fluorescence Electrospun Nanofiber Films for Portable and Intelligent Monitoring of Multiple Alkylresorcinol Homologues in Whole Wheat Foods
Bibliographic record
Abstract
The intelligent authentication of whole wheat products remains a significant challenge due to the difficulty in simultaneously monitoring multiple alkylresorcinol (AR) homologues within complex food matrices. To address this, we have developed a novel sensing platform integrating machine learning (ML) algorithms with advanced ratiometric fluorescence (FL) materials. The core component is a dual-emission g-C 3 N 4 /Ru, leveraging the blue fluorescence from g-C 3 N 4 nanosheets as the analytical signal and the red fluorescence from [Ru(bpy) 3 ] 2+ as an internal reference. Upon interaction with AR homologues, a visible color change from blue-violet to pink occured due to multiple synergistic effects of IFE, a-PET, electrostatic attraction, and π-π interactions. The system exhibited exceptional sensitivity for quantitative detection of five AR homologues (C17:0, C19:0, C21:0, C23:0, C25:0) within the concentration range of 0–60 μg·mL –1, achieving ultralow limit of detections (LODs) ranging from 2.1 to 9.9 ng·mL –1 . For precise and portable quantitative analysis, a random forest-back-propagation neural network (RF-BPNN) algorithm-assisted FL electrospun film (RuCN PAN NFs) was employed, enabling reliable on-site monitoring. RGB features were extracted using the OpenCV library, and 252 samples were evenly divided through stratified sampling to maintain data balance, yielding exceptional prediction accuracy ( R 2 = 0.9822) and robust performance by training with the RF-BPNN. Application to commercial wheat samples confirms the system’s utility for AR detection and whole wheat authentication. This integrated approach overcomes traditional analytical limitations by combining ML algorithms with advanced materials, enabling intelligent, rapid, and on-site detection of AR homologues. It provides a promising tool for verifying the authenticity of whole wheat products, offering significant potential for food safety monitoring and quality control applications.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".