Fusion vs. Isolation: evaluating the performance of multi-sensor integration for meat spoilage prediction

Simple item page
dc.contributor.authorHeffer, Samuel
dc.contributor.authorAnastasiadi, Maria
dc.contributor.authorNychas, George-John
dc.contributor.authorMohareb, Fady
dc.date.accessioned2025-05-23T15:15:48Z
dc.date.available2025-05-23T15:15:48Z
dc.date.freetoread2025-05-23
dc.date.issued2025-05-01
dc.date.pubOnline2025-05-02
dc.description.abstractHigh-throughput and portable sensor technologies are increasingly used in food production/distribution tasks as rapid and non-invasive platforms offering real-time or near real-time monitoring of quality and safety. These are often coupled with analytical techniques, including machine learning, for the estimation of sample quality and safety through monitoring of key physical attributes. However, the developed predictive models often show varying degrees of accuracy, depending on food type, storage conditions, sensor platform, and sample sizes. This work explores various fusion approaches for potential predictive enhancement, through the summation of information gathered from different observational spaces: infrared spectroscopy is supplemented with multispectral imaging for the prediction of chicken and beef spoilage through the estimation of bacterial counts in differing environmental conditions. For most circumstances, at least one of the fusion methodologies outperformed single-sensor models in prediction accuracy. Improvement in aerobic, vacuum, and mixed aerobic/vacuum chicken spoilage scenarios was observed, with performance enhanced by up to 15%. The improved cross-batch performance of these models proves an enhanced model robustness using the presented multi-sensor fusion approach. The batch-based results were corroborated with a repeated nested cross-validation approach, to give an out-of-sample generalised view of model performance across the whole dataset. Overall, this work suggests potential avenues for performance improvements in real-world, minimally invasive food monitoring scenarios.
dc.description.journalNameFoods
dc.description.sponsorshipThis research was funded as part of the Horizon 2020 ‘DiTECT’ project, (Grant Agreement No 861915)—https://ditect.eu and the Horizon Europe FOODGUARD Project, (Grant Agreement No 101136542)
dc.format.mediumElectronic
dc.identifier.citationHeffer S, Anastasiadi M, Nychas G-J, Mohareb F. (2025) Fusion vs. Isolation: evaluating the performance of multi-sensor integration for meat spoilage prediction. Foods, Volume 14, Issue 9, May 2025, Article number 1613
dc.identifier.eissn2304-8158
dc.identifier.elementsID673120
dc.identifier.issn2304-8158
dc.identifier.issueNo9
dc.identifier.paperNo1613
dc.identifier.urihttps://doi.org/10.3390/foods14091613
dc.identifier.urihttps://dspace.lib.cranfield.ac.uk/handle/1826/23925
dc.identifier.volumeNo14
dc.languageEnglish
dc.language.isoen
dc.publisherMDPI
dc.publisher.urihttps://www.mdpi.com/2304-8158/14/9/1613
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subject30 Agricultural, Veterinary and Food Sciences
dc.subject31 Biological Sciences
dc.subject3006 Food Sciences
dc.subject3106 Industrial Biotechnology
dc.subjectMachine Learning and Artificial Intelligence
dc.subject2 Zero Hunger
dc.subjectmachine learning
dc.subjectspoilage
dc.titleFusion vs. Isolation: evaluating the performance of multi-sensor integration for meat spoilage prediction
dc.typeArticle
dc.type.subtyperesearch-article
dc.type.subtypeJournal Article
dcterms.dateAccepted2025-04-29

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Fusion_vs_Isolation-meat spoilage prediction-2025.pdf
Size:
3.92 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.63 KB
Format:
Plain Text
Description:
Download

Collections

Staff publications (ES)