ASABE Technical Library - Abstract

Abstract.

Optical methods have the potential to detect chemical or biological samples rapidly with the advantage of minimum or no sample preparation. Hyperspectral microscopy is an emerging technology for rapid detection of foodborne pathogenic bacteria. Since scattering spectral signatures from hyperspectral microscopic images (HMI) vary with lighting sources, it is important to select optimal lights. The objective of this study is to compare tungsten halogen (TH) to metal-halide (MH) lighting source, assessing detection accuracies and robustness between the two light sources. HMI of live foodborne bacterial cells from five Salmonella serotypes were collected with both lighting sources. It was found that key spectral wavelengths in the visible ranges could be used for classification of the bacterial samples with MH. The experiments were repeated for validation of models with image subsets from images collected with MH and TH lighting sources. In this study, the spectra generated from HMI of five live Salmonella serotypes with two lighting sources, MH and TH were compared to assess classification accuracy and robustness with wavelength range of 450~800 nm. Ten key wavelengths between 594 and 630 nm were identified from MH HMI; however TH band reduction decreased classification accuracy. Multivariate data analysis methods were applied with the principal component-linear discriminate analysis (PC-LDA) algorithm for the classification of the five Salmonella serotypes. PC regression was applied to the second and third repetitions to assess the repeatability of the experiment. PC-LDA classified serotype subsets (n = 1,800), reporting both MH and TH accuracies at 100%, while the reduced key MH bands achieved up to 99.3% accuracy. PC regression calculated the root mean squared error of cross–validation < 0.014 and a R² > 0.948 for both full spectrum lights..