Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Food Quality Laboratory » Research » Publications at this Location » Publication #391789

Research Project: Reducing Postharvest Loss and Improving Fresh Produce Marketability and Nutritive Values through Technological Innovations and Process Optimization

Location: Food Quality Laboratory

Title: An integrated food freshness sensor array system augmented by metal-organic framework mixed-matrix membrane and deep learning

Author
item MA, PEIHUA - University Of Maryland
item XU, WENHAO - University Of Maryland
item TENG, ZI - University Of Maryland
item Luo, Yaguang - Sunny
item GONG, CHENG - University Of Maryland
item WANG, QIN - University Of Maryland
item Nou, Xiangwu

Submitted to: ACS Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 7/14/2022
Publication Date: 7/16/2022
Citation: Ma, P., Xu, W., Teng, Z., Luo, Y., Gong, C., Wang, Q., Nou, X. 2022. An integrated food freshness sensor array system augmented by metal-organic framework mixed-matrix membrane and deep learning. ACS Sensors. 7:1847-1454. https://doi.org/10.1021/acssensors.2c00255?urlappend=%3Fref%3DPDF&jav=VoR&rel=cite-as.
DOI: https://doi.org/10.1021/acssensors.2c00255?urlappend=%3Fref%3DPDF&jav=VoR&rel=cite-as

Interpretive Summary: A significant amount of food products in the supply chain are discarded due to the storage time exceeds certain pre-established expiration date, rather the loss of food quality or safety. Smart sensors capable of real-time detection of actual food quality are urgently needed to guide evidence-based decision making in inventory management. Hereby, we report the development and testing of a novel sensor array system for the food quality and freshness detection. The result is delivered as intuitive freshness scores through a user-friendly device. The system features high stability, accuracy in detection, and reduced cost due to process optimization. This new technology will benefit both consumers and retailers by providing a tool for them to monitor food quality in real time and thus reduce food waste caused by expiration date or consumption of poor quality food products.

Technical Abstract: The static labels presently prevalent on the food market are confronted with challenges due to its assumption that a food product only experiences a limited range of predefined handling and storage conditions, which cause the rise of uncertain safety risks or waste of perishable food products. Hence, integrated systems for measuring real-time food freshness have been developed for improving the reliability, safety, and sustainability of the food supply. However, these systems are limited by poor sensitivity and accuracy. Here, metal-organic framework mixed-matrix membrane (MOF-MMM) and deep learning technology were combined to tackle these challenges. UiO-66-OH and polyvinyl alcohol (PVA) were fabricated as colorimetric sensor array composites, which were impregnated with five chromogenic indicators. The sensor array system underwent color changes after being exposed to volatile organic compounds (VOCs) at different pH conditions. Four state-of-art deep convolutional neural networks (DCNNs) were applied to recognize the color change, endowing it with high-accuracy freshness estimation. The limitation of detection (LOD) of 80 ppm for trimethylamine was obtained, which was practically acceptable for the food industry. Moreover, 3D printing was applied to create a mold for possible scale-up production. The simulation test for food freshness estimation achieved accuracy up to 98.95% by the WISeR-50 algorithm. A portable food freshness detector platform was conceptually built. This approach has the potentials to advance integrated and real-time food freshness estimation.