Nondestructive multiplex detection of foodborne pathogens with background microflora and symbiosis using a paper chromogenic array and advanced neural network

We have developed an inexpensive, standardized paper chromogenic array (PCA) integrated with a machine learning approach to accurately identify single pathogens (Listeria monocytogenes, Salmonella Enteritidis, or Escherichia coli O157:H7) multiple (either in monocultures, cocktail culture), the presence of background microflora on food. Cantaloupe, commodity significant volatile organic compound (VOC) emission and large diverse populations microflora, was used as model The PCA fabricated from microarray via photolithography microfluidics, into which 22 dye spots were infused three red/green/blue color-standard dots taped. When exposed VOCs emitted by interest, exhibited distinguishable color changes pattern shifts, automatically segmented digitized ?R/?G/?B database. advanced deep feedforward neural network rate scheduler, L2 regularization, shortcut connections. After training database, demonstrated excellent performance identifying culture, distinguishing them signal cantaloupe, providing accuracy up 93% 91% under ambient refrigerated conditions, respectively. With its combination speed, reliability, portability, low cost, this nondestructive holds great potential significantly advance culture-free pathogen detection identification food, is readily extendable other food commodities complex microflora.