Machine Learning-Assisted Multicolor Fluorescence Assay for Visual Data Acquisition and Intelligent Inspection of Multiple Food Hazards Regardless of Matrix Interference DOI

Tong Zhai,

Wentao Gu, Miao Yu

и другие.

ACS Sensors, Год журнала: 2025, Номер unknown

Опубликована: Май 19, 2025

Regarding the significant health risks of pesticide residue in foods, while current sensors still suffer from limited efficiency and stability, as well difficulties qualitative identification quantitative detection mixtures, development innovative techniques combined with advanced methodology holds great research value. Herein, a highly efficient intelligent food risk evaluation system was proposed by integrating multicolor fluorescent responsive assay machine learning (ML) algorithms for quantification multiple pesticides, carbendazim (CBZ), heptachlor (HEP), chlordimeform (CDF), their mixtures. This method leveraged color changes generated interaction between carbon dots (CDs) target molecules. By extracting signal feature values these reactions visual data acquisition ML models, this enables regardless matrix interference through dual-source strategy without large instruments. The developed via ″stepwise prediction″ automatically demonstrated robust capability discrimination accuracy 99.3% categorization achieving prediction (R2 ≥ 0.8946) concentration detection, verified six kinds matrix. significantly improves stability efficiency, providing promising tool safety monitoring.

Язык: Английский

Applications of Machine Learning in Food Safety and HACCP Monitoring of Animal-Source Foods DOI Creative Commons
Panagiota‐Kyriaki Revelou, Efstathia Tsakali, Anthimia Batrinou

и другие.

Foods, Год журнала: 2025, Номер 14(6), С. 922 - 922

Опубликована: Март 8, 2025

Integrating advanced computing techniques into food safety management has attracted significant attention recently. Machine learning (ML) algorithms offer innovative solutions for Hazard Analysis Critical Control Point (HACCP) monitoring by providing data analysis capabilities and have proven to be powerful tools assessing the of Animal-Source Foods (ASFs). Studies that link ML with HACCP in ASFs are limited. The present review provides an overview ML, feature extraction, selection employed safety. Several non-destructive presented, including spectroscopic methods, smartphone-based sensors, paper chromogenic arrays, machine vision, hyperspectral imaging combined algorithms. Prospects include enhancing predictive models development hybrid Artificial Intelligence (AI) automation quality control processes using AI-driven computer which could revolutionize inspections. However, handling conceivable inclinations AI is vital guaranteeing reasonable exact hazard assessments assortment nourishment generation settings. Moreover, moving forward, interpretability will make them more straightforward dependable. Conclusively, applying allows real-time analytics can significantly reduce risks associated ASF consumption.

Язык: Английский

Процитировано

0
SERS-based approaches in the investigation of bacterial metabolism, antibiotic resistance, and species identification DOI
Zhihong Nie, Zhijun Huang,

Zhongying Wu

и другие.

Spectrochimica Acta Part A Molecular and Biomolecular Spectroscopy, Год журнала: 2025, Номер 336, С. 126051 - 126051

Опубликована: Март 13, 2025

Язык: Английский

Процитировано

0
Machine Learning-Assisted Multicolor Fluorescence Assay for Visual Data Acquisition and Intelligent Inspection of Multiple Food Hazards Regardless of Matrix Interference DOI

Tong Zhai,

Wentao Gu, Miao Yu

и другие.

ACS Sensors, Год журнала: 2025, Номер unknown

Опубликована: Май 19, 2025

Regarding the significant health risks of pesticide residue in foods, while current sensors still suffer from limited efficiency and stability, as well difficulties qualitative identification quantitative detection mixtures, development innovative techniques combined with advanced methodology holds great research value. Herein, a highly efficient intelligent food risk evaluation system was proposed by integrating multicolor fluorescent responsive assay machine learning (ML) algorithms for quantification multiple pesticides, carbendazim (CBZ), heptachlor (HEP), chlordimeform (CDF), their mixtures. This method leveraged color changes generated interaction between carbon dots (CDs) target molecules. By extracting signal feature values these reactions visual data acquisition ML models, this enables regardless matrix interference through dual-source strategy without large instruments. The developed via ″stepwise prediction″ automatically demonstrated robust capability discrimination accuracy 99.3% categorization achieving prediction (R2 ≥ 0.8946) concentration detection, verified six kinds matrix. significantly improves stability efficiency, providing promising tool safety monitoring.

Язык: Английский

Процитировано

0