Related Experiment Video
Updated: Aug 16, 2025
12:22
Automated Quantification of Synaptic Fluorescence in C. elegans
Published on: August 10, 2012
10.4K
Machine Learning-Assisted Synchronous Fluorescence Sensing Approach for Rapid and Simultaneous Quantification of
Jia-Rong He1, Jia-Wen Wei1, Shi-Yi Chen1
1The MOE Key Laboratory of Spectrochemical Analysis & Instrumentation, Department of Chemistry, College of Chemistry and Chemical Engineering, Xiamen University, 422 Siming South Road, Siming District, Xiamen 361005, China.
Sensors (Basel, Switzerland)
|December 23, 2022
Summary
This study introduces a machine learning-assisted fluorescence method for quickly detecting two pesticides, thiabendazole (TBZ) and fuberidazole (FBZ), in red wine. The approach offers efficient and accurate pesticide residue analysis for food safety without complex sample preparation.
Area of Science:
- Analytical Chemistry
- Food Science
- Biotechnology
Background:
- Detecting pesticide residues in food matrices is crucial for public health and requires efficient analytical methods.
- Traditional methods for analyzing multiple pesticides often involve time-consuming and costly sample preparation steps.
- Simultaneous detection of different pesticide types in complex samples like red wine presents a significant analytical challenge.
Purpose of the Study:
- To develop a rapid and simultaneous quantitative detection method for thiabendazole (TBZ) and fuberidazole (FBZ) in red wine.
- To integrate machine learning with synchronous fluorescence spectroscopy for enhanced analytical performance.
- To provide an efficient alternative to conventional methods for pesticide residue monitoring in food safety.
Main Methods:
- Utilized a second derivative constant-energy synchronous fluorescence sensor for data acquisition.
- Employed a machine learning approach to establish a predictive model for pesticide quantification.
- Applied the developed method to analyze pesticide residues directly in red wine samples.
Main Results:
- Achieved high recovery rates for thiabendazole (TBZ) at 101% ± 5% and fuberidazole (FBZ) at 101% ± 15%.
- Demonstrated the capability for simultaneous quantitative detection of both pesticides.
- Eliminated the need for complicated and time-consuming sample pretreatment procedures.
Conclusions:
- The machine learning-assisted synchronous fluorescence sensing approach enables rapid and accurate multi-component analysis of pesticide residues.
- This method offers a cost-effective and efficient solution for food safety monitoring.
- Highlights the potential of combining machine learning and fluorescence techniques for complex analytical challenges in real-world applications.
