Near Infrared Spectroscopy for Bacterial Detection in the Dairy Industry

This article discusses the use of near-infrared (NIR) spectroscopy combined with multivariate classification methods for detecting bacterial contamination in milk in the dairy industry. In the first experiment, the study found that NIR was accurate and reliable in detecting the presence of biofilms...

Full description

Saved in:
Bibliographic Details
Published in:IEEE sensors journal 2023-11, Vol.23 (21), p.26107-26113
Main Authors: Allende-Prieto, Cristina, Fernandez, Lucia, Agun, Seila, Rodriguez-Gonzalvez, Pablo, Martinez, Beatriz, Garcia, Pilar, Rodriguez, Ana
Format: Article
Language:English
Subjects:
Bacteria
biofilm
Biofilms
Biological system modeling
Classification
Contamination
Dairy industry
Dairy products
Data models
Food contamination & poisoning
Infrared spectroscopy
Milk
milk contamination
Near infrared radiation
Spectroscopy
Spectrum analysis
Strain
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This article discusses the use of near-infrared (NIR) spectroscopy combined with multivariate classification methods for detecting bacterial contamination in milk in the dairy industry. In the first experiment, the study found that NIR was accurate and reliable in detecting the presence of biofilms in milk. Our results showed that the technology was effective in distinguishing between contaminated and uncontaminated samples with an area under the receiver operating characteristic (ROC) curve (AUC) greater than 99%. It was also effective in classifying the samples belonging to different strains. In a second experiment, we used the same methodology to assess their effectiveness in detecting bacterial contamination proportions in milk. Our results showed that the technology was effective in classifying milk samples contaminated with four different bacteria and uncontaminated controls with an AUC greater than 97%. Moreover, results were still good when data from all bacteria were analyzed together, even at low bacterial concentrations, obtaining an average precision of 70%. These results demonstrate the potential of this technology to be used as a rapid and accurate method for identifying bacterial contamination in the dairy sector.
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2023.3311516