Electronic nose can recognize, predict meat freshness

Researchers at Nanyang Technical University, Singapore have developed an electronic nose able to detect and assess the freshness of packaged poultry, meat and fish.

Doughman Headshot3 Headshot
(Andrea Gantz)
(Andrea Gantz)

Researchers at Nanyang Technical University, Singapore have developed an electronic nose able to detect and assess the freshness of packaged poultry, meat and fish.

“Food safety is always one of the top issues in food industry, and meat freshness greatly affects the meat safety as meat that is not fresh has many potential safety issues,” explained co-lead author Professor Chen Xiaodong, the Director of Innovative Centre for Flexible Devices at Nanyang Technical University.

More than 48 million Americans get sick from a foodborne illness each year and 3,000 people die as a result, the Center for Disease Control and Prevention (CDC) estimates. Contaminated poultry meat is the underlying cause of 19% of deaths attributed to foodborne illnesses.

The technology provides food safety surveillance via real-time freshness monitoring and food quality classification strategies to help improve the profits of meat suppliers and retailers, resulting in a transparent monitoring system that helps consumers feel confident about the safety of the meat and poultry they buy.

How it works

The artificial olfactory system is comprised of a barcode that changes color in the presence of the gases produced by decaying meat and a smartphone app that uses artificial intelligence to function as a barcode reader.

The barcode contains 20 bars made of a natural sugar called chitosan loaded with a different dye, changing into unique color combinations that change intensity depending on the freshness of the meat.

“We combined cross-reactive colorimetric barcode combinatorics and deep convolutional neural networks (DCNN). The former provides a ‘scent fingerprint’ and DCNN helps with the fingerprint recognition,” Xiaodong said. 

98.5% accuracy

In research described in the journal Advanced Materials, the electronic nose predicted the freshness of aged commercially packaged chicken, fish and beef meat samples with 98.5% accuracy.

“The barcode ‘reader’ powered by artificial intelligence (AI) - a fully supervised DCNN trained using 3475 labelled barcode images - recognized and predicted meat freshness from a large library of barcode colors with accuracy of 98.5%,” said Xiaodong.

“Incorporating the DCNN into a smartphone application formed a simple platform for rapid barcode scanning and food freshness identification in real time.”

Like what you just read? Sign up now for free to receive the Poultry Future Newsletter.

Page 1 of 37
Next Page