{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,17]],"date-time":"2026-01-17T21:21:16Z","timestamp":1768684876309,"version":"3.49.0"},"reference-count":45,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T00:00:00Z","timestamp":1682294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"EC Horizon 2020 Programme","award":["861915"],"award-info":[{"award-number":["861915"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Spectroscopic sensor imaging of food samples meta-processed by deep machine learning models can be used to assess the quality of the sample. This article presents an architecture for estimating microbial populations in meat samples using multispectral imaging and deep convolutional neural networks. The deep learning models operate on embedded platforms and not offline on a separate computer or a cloud server. Different storage conditions of the meat samples were used, and various deep learning models and embedded platforms were evaluated. In addition, the hardware boards were evaluated in terms of latency, throughput, efficiency and value on different data pre-processing and imaging-type setups. The experimental results showed the advantage of the XavierNX platform in terms of latency and throughput and the advantage of Nano and RP4 in terms of efficiency and value, respectively.<\/jats:p>","DOI":"10.3390\/s23094233","type":"journal-article","created":{"date-parts":[[2023,4,24]],"date-time":"2023-04-24T04:01:23Z","timestamp":1682308883000},"page":"4233","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Microbiological Quality Estimation of Meat Using Deep CNNs on Embedded Hardware Systems"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2116-785X","authenticated-orcid":false,"given":"Dimitrios","family":"Kolosov","sequence":"first","affiliation":[{"name":"School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UK"}]},{"given":"Lemonia-Christina","family":"Fengou","sequence":"additional","affiliation":[{"name":"Laboratory of Microbiology and Biotechnology of Foods, Department of Food Science and Human Nutrition, School of Food and Nutritional Sciences, Agricultural University of Athens, 11855 Athens, Greece"}]},{"given":"Jens Michael","family":"Carstensen","sequence":"additional","affiliation":[{"name":"Videometer A\/S, H\u00f8rk\u00e6r 12B, 2730 Herlev, Denmark"}]},{"given":"Nette","family":"Schultz","sequence":"additional","affiliation":[{"name":"Videometer A\/S, H\u00f8rk\u00e6r 12B, 2730 Herlev, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2673-6425","authenticated-orcid":false,"given":"George-John","family":"Nychas","sequence":"additional","affiliation":[{"name":"Laboratory of Microbiology and Biotechnology of Foods, Department of Food Science and Human Nutrition, School of Food and Nutritional Sciences, Agricultural University of Athens, 11855 Athens, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6984-0268","authenticated-orcid":false,"given":"Iosif","family":"Mporas","sequence":"additional","affiliation":[{"name":"School of Physics, Engineering and Computer Science, University of Hertfordshire, Hatfield AL10 9AB, UK"}]}],"member":"1968","published-online":{"date-parts":[[2023,4,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/j.crfs.2021.03.009","article-title":"Deep learning and machine vision for food processing: A survey","volume":"4","author":"Zhu","year":"2021","journal-title":"Curr. Res. Food Sci."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bodirsky, B.L., Rolinski, S., Biewald, A., Weindl, I., Popp, A., and Lotze-Campen, H. (2015). Global Food Demand Scenarios for the 21st Century. PLoS ONE, 10.","DOI":"10.1371\/journal.pone.0139201"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"106614","DOI":"10.1109\/ACCESS.2020.3000690","article-title":"Estimation of the Microbiological Quality of Meat Using Rapid and Non-Invasive Spectroscopic Sensors","volume":"8","author":"Fengou","year":"2020","journal-title":"IEEE Access"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.cofs.2016.06.005","article-title":"Novel approaches for food safety management and communication","volume":"12","author":"Nychas","year":"2016","journal-title":"Curr. Opin. Food Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"935","DOI":"10.2217\/fmb.14.61","article-title":"One day to one hour: How quickly can foodborne pathogens be detected?","volume":"9","author":"Bhunia","year":"2014","journal-title":"Future Microbiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1016\/j.fm.2012.11.017","article-title":"Monitoring the succession of the biota grown on a selective medium for pseudomonads during storage of minced beef with molecular-based methods","volume":"34","author":"Doulgeraki","year":"2013","journal-title":"Food Microbiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1016\/j.tifs.2015.02.010","article-title":"The current status of process analytical technologies in the dairy industry","volume":"43","author":"Munir","year":"2015","journal-title":"Trends Food Sci. Technol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.tifs.2012.04.007","article-title":"Process Analytical Technology in the food industry","volume":"31","author":"Lyndgaard","year":"2013","journal-title":"Trends Food Sci. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Govari, M., Tryfinopoulou, P., Parlapani, F.F., Boziaris, I.S., Panagou, E.Z., and Nychas, G.-J.E. (2021). Quest of Intelligent Research Tools for Rapid Evaluation of Fish Quality: FTIR Spectroscopy and Multispectral Imaging Versus Microbiological Analysis. Foods, 10.","DOI":"10.3390\/foods10020264"},{"key":"ref_10","first-page":"5845422","article-title":"Comparison of Machine Learning Classification Methods for Determining the Geographical Origin of Raw Milk Using Vibrational Spectroscopy","volume":"2021","author":"Mamad","year":"2021","journal-title":"J. Spectrosc."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"111339","DOI":"10.1016\/j.jfoodeng.2022.111339","article-title":"Near-infrared spectroscopy and machine learning for classification of food powders during a continuous process","volume":"341","author":"Ozturk","year":"2023","journal-title":"J. Food Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"131471","DOI":"10.1016\/j.foodchem.2021.131471","article-title":"The application of machine-learning and Raman spectroscopy for the rapid detection of edible oils type and adulteration","volume":"373","author":"Zhao","year":"2022","journal-title":"Food Chem."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1146\/annurev-biodatasci-020221-123602","article-title":"Data Science in the Food Industry","volume":"4","author":"Nychas","year":"2021","journal-title":"Annu. Rev. Biomed. Data Sci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.cofs.2020.04.008","article-title":"Miniaturization of optical sensors and their potential for high-throughput screening of foods","volume":"31","author":"Aykas","year":"2020","journal-title":"Curr. Opin. Food Sci."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"777","DOI":"10.1016\/j.tifs.2021.11.003","article-title":"Portable spectroscopy for high throughput food authenticity screening: Advancements in technology and integration into digital traceability systems","volume":"118","author":"McVey","year":"2021","journal-title":"Trends Food Sci. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"121350","DOI":"10.1016\/j.saa.2022.121350","article-title":"Probing 1D convolutional neural network adapted to near-infrared spectroscopy for efficient classification of mixed fish","volume":"279","author":"Chen","year":"2022","journal-title":"Spectrochim. Acta Part A Mol. Biomol. Spectrosc."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"108559","DOI":"10.1016\/j.microc.2023.108559","article-title":"Distinguishing fresh and frozen-thawed beef using hyperspectral imaging technology combined with convolutional neural networks","volume":"189","author":"Pu","year":"2023","journal-title":"Microchem. J."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Moon, E.J., Kim, Y., Xu, Y., Na, Y., Giaccia, A.J., and Lee, J.H. (2020). Evaluation of Salmon, Tuna, and Beef Freshness Using a Portable Spectrometer. Sensors, 20.","DOI":"10.3390\/s20154299"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.foodcont.2018.04.046","article-title":"First use of handheld Raman spectroscopic devices and on-board chemometric analysis for the detection of milk powder adulteration","volume":"92","author":"Karunathilaka","year":"2018","journal-title":"Food Control."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Kolosov, D., and Mporas, I. (2021, January 11\u201315). Face Masks Usage Monitoring for Public Health Security using Computer Vision on Hardware. Proceedings of the 2021 International Carnahan Conference on Security Technology (ICCST), Hatfield, UK.","DOI":"10.1109\/ICCST49569.2021.9717402"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"109167","DOI":"10.1109\/ACCESS.2022.3214214","article-title":"Anatomy of Deep Learning Image Classification and Object Detection on Commercial Edge Devices: A Case Study on Face Mask Detection","volume":"10","author":"Kolosov","year":"2022","journal-title":"IEEE Access"},{"key":"ref_22","unstructured":"Carstensen, J.M., and Folm-Hansen, J. (1999). An Apparatus and a Method of Recording an Image of an Object. (WO1999042900), Google Patents."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018, January 18\u201323). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21\u201326). Densely Connected Convolutional Networks. Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref_25","unstructured":"Tan, M., and Le, Q.V. (2019, January 9\u201315). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Proceedings of the International conference on Machine Learning (PMLR), Long Beach, CA, USA."},{"key":"ref_26","unstructured":"Simonyan, K., and Zisserman, A. (2015, January 7\u20139). Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of the International Conference on Learning Representations (ICLR), San Diego, CA, USA."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27\u201330). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_28","unstructured":"(2023, March 13). Raspberry Pi 4 Model B Specifications. Available online: https:\/\/www.raspberrypi.org\/products\/raspberry-pi-4-model-b\/."},{"key":"ref_29","unstructured":"(2023, March 13). Intel Neural Compute Stick 2 Product Specifications. Available online: https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/140109\/intel-neural-compute-stick-2.html."},{"key":"ref_30","unstructured":"(2023, March 13). Evaluation Kit for the i.MX 8M Plus Applications Processor. Available online: https:\/\/www.nxp.com\/design\/development-boards\/i-mx-evaluation-and-development-boards\/evaluation-kit-for-the-i-mx-8m-plus-applications-processor:8MPLUSLPD4-EVK."},{"key":"ref_31","unstructured":"(2023, March 13). Jetson Nano Developer Kit. Available online: https:\/\/developer.nvidia.com\/blog\/jetson-nano-ai-computing\/."},{"key":"ref_32","unstructured":"(2023, March 13). Jetson Xavier NX Series. Available online: https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-xavier-nx\/."},{"key":"ref_33","unstructured":"(2023, March 13). Ultra96. Available online: https:\/\/www.96boards.org\/product\/ultra96\/."},{"key":"ref_34","unstructured":"(2023, March 13). Kria KV260 Vision AI Starter Kit. Available online: https:\/\/www.xilinx.com\/products\/som\/kria\/kv260-vision-starter-kit.html."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1016\/j.fm.2018.10.020","article-title":"Evaluation of Fourier transform infrared spectroscopy and multispectral imaging as means of estimating the microbiological spoilage of farmed sea bream","volume":"79","author":"Fengou","year":"2019","journal-title":"Food Microbiol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1016\/j.compag.2018.10.025","article-title":"A unified spectra analysis workflow for the assessment of microbial contamination of ready-to-eat green salads: Comparative study and application of non-invasive sensors","volume":"155","author":"Tsakanikas","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.tifs.2016.01.011","article-title":"Data mining derived from food analyses using non-invasive\/non-destructive analytical techniques; determination of food authenticity, quality & safety in tandem with computer science disciplines","volume":"50","author":"Ropodi","year":"2016","journal-title":"Trends Food Sci. Technol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.tifs.2015.10.004","article-title":"Microbial evaluation of raw and processed food products by Visible\/Infrared, Raman and Fluorescence spectroscopy","volume":"46","author":"He","year":"2015","journal-title":"Trends Food Sci. Technol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.meatsci.2019.01.010","article-title":"Application of invasive weed optimization and least square support vector machine for prediction of beef adulteration with spoiled beef based on visible near-infrared (Vis-NIR) hyperspectral imaging","volume":"151","author":"Zhao","year":"2019","journal-title":"Meat Sci."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1016\/j.lwt.2015.01.021","article-title":"Rapid and non-invasive detection of fish microbial spoilage by visible and near infrared hyperspectral imaging and multivariate analysis","volume":"62","author":"Cheng","year":"2015","journal-title":"LWT-Food Sci. Technol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.foodcont.2017.07.013","article-title":"Hyperspectral imaging and multispectral imaging as the novel techniques for detecting defects in raw and processed meat products: Current state-of-the-art research advances","volume":"84","author":"Feng","year":"2018","journal-title":"Food Control"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"e12390","DOI":"10.1111\/jfs.12390","article-title":"Detection of total viable count in spiced beef using hyperspectral imaging combined with wavelet transform and multiway partial least squares algorithm","volume":"38","author":"Yang","year":"2018","journal-title":"J. Food Saf."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"107854","DOI":"10.1016\/j.foodcont.2020.107854","article-title":"Shortwave infrared hyperspectral imaging system coupled with multivariable method for TVB-N measurement in pork","volume":"124","author":"Baek","year":"2021","journal-title":"Food Control"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1016\/j.jfoodeng.2017.09.003","article-title":"Hyperspectral image-based multi-feature integration for TVB-N measurement in pork","volume":"218","author":"Guo","year":"2018","journal-title":"J. Food Eng."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"133673","DOI":"10.1016\/j.foodchem.2022.133673","article-title":"UV-fluorescence imaging for real-time non-destructive monitoring of pork freshness","volume":"396","author":"Zhuang","year":"2022","journal-title":"Food Chem."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/9\/4233\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:22:15Z","timestamp":1760124135000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/23\/9\/4233"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,24]]},"references-count":45,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["s23094233"],"URL":"https:\/\/doi.org\/10.3390\/s23094233","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,24]]}}}