AI-powered 'electronic nose' sniffs out meat freshness
A team of scientists led by Nanyang Technological University, Singapore (NTU Singapore) has invented an artificial olfactory system that mimics the human nose to accurately assess the freshness of meat.
The e-nose comprises a ‘barcode’ that changes colour over time in reaction to the gases produced by meat as it decays, as well as a barcode ‘reader’ in the form of a smartphone app powered by artificial intelligence (AI). The e-nose has been trained to recognise and predict meat freshness from a large library of barcode colours (see Figure 1).
When tested on commercially packaged chicken, fish and beef meat samples, the team found that the AI system predicted the freshness of the meats with a 98.5% accuracy. As a comparison, the commonly used algorithm analysis only showed an overall accuracy of 61.7%.
The e-nose has been described in paper published in the scientific journal Advanced Materials as more accurate than a ‘best before’ label, which could help to reduce food waste.
Co-lead author Professor Chen Xiaodong, Director of the Innovative Centre for Flexible Devices at NTU, said: “Our proof-of-concept artificial olfactory system, which we tested in real-life scenarios, can be easily integrated into packaging materials and yields results in a short time without the bulky wiring used for electrical signal collection in some e-noses that were developed recently.
“These barcodes help consumers to save money by ensuring that they do not discard products that are still fit for consumption, which also helps the environment. The biodegradable and non-toxic nature of the barcodes also means they could be safely applied in all parts of the food supply chain to ensure food freshness.”
A patent has been filed for this method of real-time monitoring of food freshness, and the team is now working with a Singapore agribusiness company to extend this concept to other types of perishables.
How it works
In the e-nose, the 20 bars in the barcode act as the receptors. Each bar is made of chitosan (a natural sugar) embedded on a cellulose derivative and loaded with a different type of dye. These dyes react with the gases emitted by decaying meat and change colour in response to the different types and concentrations of gases, resulting in a unique combination of colours that serves as a ‘scent fingerprint’ for the state of any meat.
For instance, the first bar in the barcode contains a yellow dye that is weakly acidic. When exposed to nitrogen-containing compounds produced by decaying meat (called bioamines), this yellow dye changes into blue as the dye reacts with these compounds. The colour intensity changes with an increasing concentration of bioamines as meat decays further.
For this study, the scientists first developed a classification system (fresh, less fresh or spoiled) using an international standard that determines meat freshness. This is done by extracting and measuring the amount of ammonia and two other bioamines found in fish packages wrapped in widely used transparent PVC (polyvinyl chloride) packaging film and stored at 4°C over five days at different intervals.
They concurrently monitored the freshness of these fish packages with barcodes glued on the inner side of the PVC film without touching the fish. Images of these barcodes were taken at different intervals over five days.
A type of AI algorithm known as deep convolutional neural networks was then trained with images of different barcodes to identify patterns in the scent fingerprint that correspond to each category of freshness.
To gauge the prediction accuracy of their e-nose, the NTU scientists monitored the freshness of commercially packed chicken, fish and beef, with barcodes glued on the packaging film, stored at 25°C. Over 4000 images of the barcodes from six meat packages were taken at different time intervals over 48 hours without opening the different meat packages.
The research team first trained their system to pick out patterns among the scent fingerprints captured in 3475 barcode images, before testing the system’s accuracy on the remaining images.
The results revealed an overall 98.5% accuracy — 100% accuracy in identifying spoiled meats, and 96 to 99% accuracy for fresh and less fresh meats.
As a comparison, the research team randomly selected 20 barcode images from each freshness category to assess the prediction accuracy of Euclidean distance analysis, a commonly used method to measure the response of sensors like the barcode used in this e-nose. This analysis showed an overall accuracy of 61.7%.
Results of a study have shown that targeted cleaning, demonstrated by ATP monitoring, can improve...
Advanced fire sensing technology detects smoke at the earliest stage while reducing false alarms...
It is possible to produce a shelf life of up to 16 weeks for refrigerated liquid egg products...