NEURAL-NETWORK PATTERN-RECOGNITION OF PHOTOACOUSTIC FTIR SPECTRA AND KNOWLEDGE-BASED TECHNIQUES FOR DETECTION OF MYCOTOXIGENIC FUNGI IN FOOD GRAINS

Fourier transform infrared photoacoustic spectroscopy (FTIR-PAS), a hi ghly sensitive probe of the surfaces of solid substrates, is used to d etect toxigenic fungal contamination in corn. Kernels of corn infected with mycotoxigenic fungi, such as Aspergillus flavus, display FTIR-PA S spectra that differ significantly from spectra of uninfected kernels . Photoacoustic infrared spectral features were identified, and an art ificial neural network was trained to distinguish contaminated from un contaminated corn by pattern recognition. Work is in progress to integ rate epidemiological information about cereal crop fungal disease into the pattern recognition program to produce a more knowledge-based, an d hence more reliable and specific, technique. A model of a hierarchic ally organized expert system is proposed, using epidemiological factor s such as corn variety, plant stress and susceptibility to infection, geographic location, weather, insect vectors, and handling and storage conditions, in addition to the analytical data, to predict A. flavus and other kinds of toxigenic fungal contamination that might be presen t in food grains.