Ai Dreams Forum
Artificial Intelligence => AI News => Topic started by: frankinstien on February 01, 2021, 11:16:40 am
-
Here's a paper (http://"https://www3.ntu.edu.sg/CorpComms2/Research%20Papers/E-nose.pdf") describing the use of a colorimetric barcode that is made up of 20 different types of porous nanocomposite comprised of dye-loaded chitosan nanoparticles (CNP-dye) embedded on cellulose acetate (CA). The halochromic dyes in the barcode cross-react according to the type and concentration of gases to form a scent fingerprint (in the form of a colorful barcode) that is identified using DCNN (Deep Convolutional Neural Networks). Using fully supervised training techniques and 3475 labeled barcode images as the training source, they obtained a DCNN that predicted meat freshness with an overall accuracy of 98.5%.