Related Experiment Video
Updated: Jun 27, 2026
09:46
Qualitative Identification of Carboxylic Acids, Boronic Acids, and Amines Using Cruciform Fluorophores
Published on: August 19, 2013
15.6K
Deep learning-assisted flavonoid-based fluorescent sensor array for the nondestructive detection of meat freshness
Min Li1, Jianguo Xu2, Chifang Peng3
1State Key Laboratory of Food Science and Resources, Jiangnan University, Wuxi 214122, PR China; School of Food Science and Technology, Jiangnan University, Wuxi 214122, PR China.
Food Chemistry
|March 14, 2024
Summary
This study developed a novel fluorescent sensor array using flavonoids for non-toxic meat freshness testing. A deep convolutional neural network achieved 97.1% accuracy in predicting meat freshness non-destructively.
Area of Science:
- Food Science
- Analytical Chemistry
- Biomaterials Science
Background:
- Traditional meat freshness testing methods often involve toxic indicators or destructive analysis.
- Concerns regarding the toxicity of conventional indicators hinder the commercialization of meat freshness sensors.
- Developing non-toxic, real-time, and non-destructive methods for meat freshness assessment is crucial for food safety.
Purpose of the Study:
- To develop a novel, non-toxic fluorescent sensor array for meat freshness indication.
- To utilize a deep convolutional neural network (DCNN) for accurate and real-time meat freshness detection.
- To establish a smartphone-based system for accessible meat freshness monitoring.
Main Methods:
- Three fluorescent sensors were fabricated by complexing flavonoids (fisetin, puerarin, daidzein) with flexible films, creating a sensor array.
- The sensor array was applied as a freshness indication label on packaged meat.
- Smartphone imaging of the sensor labels under varying meat freshness levels, followed by DCNN model training and validation.
Main Results:
- A fluorescent sensor array based on natural flavonoids was successfully developed.
- A DCNN model achieved a high prediction accuracy of 97.1% for meat freshness.
- The developed method offers a non-destructive and real-time alternative to traditional methods like TVB-N measurement.
Conclusions:
- Flavonoid-based fluorescent sensor arrays offer a promising non-toxic approach for meat freshness indication.
- The integration of DCNN and smartphone imaging enables efficient and accurate non-destructive meat freshness assessment.
- This technology has the potential to enhance food safety and reduce food waste through reliable freshness monitoring.
