Effect of colony age on near infrared hyperspectral images of foodborne bacteria

Simple item page
dc.contributor.authorWilliams, Paul J.en_ZA
dc.contributor.authorKammies, Terri-Leeen_ZA
dc.contributor.authorGouws, Pieter A.en_ZA
dc.contributor.authorManley, Marenaen_ZA
dc.date.accessioned2021-10-14T13:16:53Z
dc.date.available2021-10-14T13:16:53Z
dc.date.issued2019-01-30
dc.descriptionCITATION: Williams, P. J., et al. 2019. Effect of colony age on near infrared hyperspectral images of foodborne bacteria. Journal of Spectral Imaging, 8(Article ID a5):1-12, doi:10.1255/jsi.2019.a5.
dc.descriptionThe original publication is available at https://www.impopen.com
dc.description.abstractNear infrared hyperspectral imaging (NIR-HSI) and multivariate image analysis were used to distinguish between foodborne pathogenic bacteria, Bacillus cereus, Escherichia coli, Salmonella Enteritidis, Staphylococcus aureus and a non-pathogenic bacterium, Staphylococcus epidermidis. Hyperspectral images of bacteria, streaked out on Luria—Bertani agar, were acquired after 20 h, 40 h and 60 h growth at 37 °C using a SisuCHEMA hyperspectral pushbroom imaging system with a spectral range of 920–2514 nm. Three different pre-processing methods: standard normal variate (SNV), Savitzky—Golay (1stderivative, 2nd order polynomial, 15-point smoothing) and Savitzky—Golay (2nd derivative, 3rd order polynomial, 15-point smoothing) were evaluated. SNV provided the most distinct clustering in the principal component score plots and was thus used as the sole pre-processing method. Partial least squares discriminant analysis (PLS-DA) models were developed for each growth period and was tested on a second set of plates, to determine the effect the age of the colony has on classification accuracies. The highest overall prediction accuracies where test plates required the least amount of growth time, was found with models built after 60 h growth and tested on plates after 20 h growth. Predictions for bacteria differentiation within these models ranged from 83.1 % to 98.8 % correctly predicted pixels.en_ZA
dc.description.urihttps://www.impopen.com/jsi-abstract/I08_a5
dc.description.versionPublisher’s version
dc.format.extent12 pages : illustrations (some color)en_ZA
dc.identifier.citationWilliams, P. J., et al. 2019. Effect of colony age on near infrared hyperspectral images of foodborne bacteria. Journal of Spectral Imaging, 8(Article ID a5):1-12, doi:10.1255/jsi.2019.a5
dc.identifier.issn2040-4565 (online)
dc.identifier.otherdoi:10.1255/jsi.2019.a5
dc.identifier.urihttp://hdl.handle.net/10019.1/123229
dc.language.isoen_ZAen_ZA
dc.publisherIM Publications
dc.rights.holderAuthors retain rights
dc.subjectFoodborne bacteriaen_ZA
dc.subjectFoodborne diseasesen_ZA
dc.subjectPathogenic microorganisms -- Detectionen_ZA
dc.subjectPathogenic bacteria -- Spectroscopic imagingen_ZA
dc.subjectNIR hyperspectral imagingen_ZA
dc.titleEffect of colony age on near infrared hyperspectral images of foodborne bacteriaen_ZA
dc.typeArticleen_ZA
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
williams_effect_2019.pdf
Size:
1.71 MB
Format:
Adobe Portable Document Format
Description:
Download article
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Articles (Food Science)