An Integrated Food Freshness Sensor Array System Augmented by a Metal-Organic Framework Mixed-Matrix Membrane and...

Area of Science:

• Materials Science
• Analytical Chemistry
• Food Science

Background:

• Current static food labels are inadequate for perishable products, leading to safety risks and waste.
• Existing real-time freshness monitoring systems lack sufficient sensitivity and accuracy.
• There is a need for reliable, integrated systems to assess food quality throughout the supply chain.

Purpose of the Study:

• To develop an advanced sensor system for accurate, real-time food freshness estimation.
• To overcome the limitations of existing freshness monitoring technologies.
• To enhance the reliability, safety, and sustainability of the food supply chain.

Main Methods:

• Fabrication of a metal-organic framework (UiO-66-OH) mixed-matrix membrane with polyvinyl alcohol and chromogenic indicators.
• Development of a sensor array capable of detecting ammonia and trimethylamine.
• Application of deep convolutional neural networks (e.g., WISeR-50 algorithm) for color change analysis and freshness prediction.
• Conceptualization of a 3D-printed portable detector platform.

Main Results:

• The sensor array exhibited color changes in response to ammonia at varying pH levels.
• Achieved a limit of detection of 80 ppm for trimethylamine, suitable for food industry applications.
• Deep learning algorithms provided high-accuracy freshness estimation, with the WISeR-50 algorithm reaching 98.95% accuracy for chicken freshness.
• Demonstrated potential for scalable production using 3D printing.

Conclusions:

• The integrated metal-organic framework and deep learning approach offers a significant advancement in real-time food freshness monitoring.
• This technology has the potential to reduce food waste and improve consumer safety.
• The developed system provides a foundation for practical, portable, and scalable food freshness detection solutions.