Portable food freshness prediction platform based on colorimetric barcode combinatorics and deep convolutional neural networks
Lingling Guo1Ting Wang2Zhonghua Wu3Jianwu Wang2Ming Wang2Zequn Cui2Shaobo Ji2Jianfei Cai3Chuanlai Xu2Xiaodong Chen2
1. State Key Lab of Food Science and Technology,Jiangnan University2. Innovative Center for Flexible Devices (iFLEX),Max Planck-NTU Joint Lab for Artificial Senses,School of Materials Science and Engineering,Nanyang Technological University3. School of Computer Science and Engineering,Nanyang Technological University
摘要：Artificial scent screening systems（known as electronic noses, E-nose） have been researched extensively. A portable, automatic, and accurate, real-time E-nose requires both robust cross-reactive sensing and fingerprint pattern recognition. Few E-noses have been commercialized because they suffer from either sensing or pattern recognition issues. Here, we combined cross-reactive colorimetric barcode combinatorics and deep convolutional neural networks（DCNN） to form a meat freshness monitoring system that concurrently provides scent fingerprint and fingerprint recognition. The barcodes-compris-ing of 20 different types of porous nanocomposites of chitosan, dye and cellulose acetate-form scent fingerprints that are identifiable by DCNN. A fully supervised DCNN trained using 3475 labeled barcode images predicted meat freshness with an overall accuracy of 98.5%. Incorporating DCNN into a smartphone application formed a simple platform for rapid barcode scanning and food freshness identifica-tion in real time. Our system is fast, accurate and non-destructive, enabling consumers and all stakeholders in the food supply chain to monitor food freshness.