E-Nose accurately detects if meat is fresh or spoiled

An NTU Singapore-led team of scientists have developed a new AI-powered electronic nose (e-nose) that can accurately measure the freshness of meat. Led by NTU professor Chen Xiaodong, the team – which includes scientists Jiangnan University, China, and Monash University, Australia – believes their artificial olfactory system could help reduce food wastage by confirming to consumers whether the purchased meat is fit for consumption, much more accurately than a ‘Best Before’ label can. The e-nose comprises of two elements: a colored ‘barcode’ that reacts with gases produced by decaying meat; and a barcode ‘reader’ in the form of a smartphone app that uses AI to interpret the combination of colors on the barcode. According to Xiaodong, the e-nose can be easily integrated into packaging materials  – like the underside of the PVC film that the meat is packaged in – and yields results within 30 seconds without the bulky wiring typically used for electrical signal collection. The e-nose’s non-destructive, automated and real-time monitoring capability can also be used to recognise the types of gases that other types of perishable food emit as they become less fresh, providing a broadly applicable new platform for food quality control. When tested on commercially packaged chicken, fish and beef meat samples that were left to age, the team found that their e-nose’s ‘deep convolutional neural network’ AI algorithm predicted the freshness of the meats with a 98.5% accuracy. In comparison, the prediction accuracy of a commonly used algorithm to measure the response of sensors like the barcode used in this e-nose stood at 61.7%.  Just like how gases produced by decaying meat bind to receptors in the mammalian nose, the 20 bars in the e-nose’s barcode act as its receptors. Each bar is made of chitosan embedded on a cellulose derivative and loaded with a different […]