MétaCan
Menu
Back to cohort
Record W7113901560 · doi:10.1111/jfpe.70286

Detection of Peanut Contamination in Wheat Flour Using a Digital Light Processing ( <scp>DLP</scp> ) Based Near‐Infrared Spectrometer and Ensemble Machine Learning

2025· article· en· W7113901560 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueJournal of Food Process Engineering · 2025
Typearticle
Languageen
FieldChemistry
TopicSpectroscopy and Chemometric Analyses
Canadian institutionsUniversity of Guelph
FundersUniversity of Guelph
KeywordsLinear discriminant analysisRandom forestContaminationEnsemble learningSupport vector machinePreprocessorNormalization (sociology)Wheat flourPattern recognition (psychology)

Abstract

fetched live from OpenAlex

ABSTRACT Peanut flour contamination poses significant health and regulatory challenges within food production systems, often originating from adulterated raw materials or cross‐contamination during processing. Rapid and non‐destructive detection methods are essential for real‐time monitoring and mitigation. This study aimed to develop a non‐destructive detection system using a portable digital light processing (DLP) based near‐infrared (NIR) spectrometer integrated with machine learning (ML) models to identify and quantify peanut adulteration in wheat flour. Samples were systematically prepared by blending wheat flour with peanut flour at six contamination levels: 0%, 2%, 4%, 6%, 8%, and 10% (w/w). Spectral data were acquired using a handheld DLP‐NIR device operating in the 900–1700 nm range. Due to limited separability among contamination levels, a binary classification framework was adopted to distinguish pure wheat flour (0%) from contaminated samples (≥ 2%) using models such as Linear Discriminant Analysis, Logistic Regression, and boosted tree ensembles. Regression models including Extra Trees, Random Forest, and LightGBM were trained to estimate contamination levels. Spectral preprocessing involved normalization and Yeo‐Johnson transformation, while model evaluation employed stratified K‐fold cross‐validation with Optuna‐based hyperparameter tuning. The top five performing classifiers were selected for ensemble learning to enhance predictive performance. The final ensemble classifier achieved accuracy, precision, recall, and F1‐score values of 0.9937, 0.9976, 0.9948, and 0.9962, respectively. Ensemble regressors yielded R 2 = 0.7477, RMSE = 1.7157, and MAE = 1.148, demonstrating promising semi‐quantitative estimation capabilities. These results highlight the feasibility of combining portable NIR spectroscopy with ensemble ML for rapid, in‐line detection of peanut contamination in wheat flour.

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: Bench or experimental
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.177
Threshold uncertainty score0.715

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.007
GPT teacher head0.229
Teacher spread0.222 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it