A machine learning workflow for raw food spectroscopic classification in a future industry

Abstract Over the years, technology has changed the way we produce and have access to our food through the development of applications, robotics, data analysis, and processing techniques. The implementation of these approaches by the food industry ensure quality and affordability, reducing at the sa...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Panagiotis Tsakanikas, Apostolos Karnavas, Efstathios Z. Panagou, George-John Nychas
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
R
Q
Acceso en línea:https://doaj.org/article/5e30514efc6247cab929d114789321c6
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5e30514efc6247cab929d114789321c6
record_format dspace
spelling oai:doaj.org-article:5e30514efc6247cab929d114789321c62021-12-02T16:24:49ZA machine learning workflow for raw food spectroscopic classification in a future industry10.1038/s41598-020-68156-22045-2322https://doaj.org/article/5e30514efc6247cab929d114789321c62020-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-020-68156-2https://doaj.org/toc/2045-2322Abstract Over the years, technology has changed the way we produce and have access to our food through the development of applications, robotics, data analysis, and processing techniques. The implementation of these approaches by the food industry ensure quality and affordability, reducing at the same time the costs of keeping the food fresh and increase productivity. A system, as the one presented herein, for raw food categorization is needed in future food industries to automate food classification according to type, the process of algorithm approaches that will be applied to every different food origin and also for serving disabled people. The purpose of this work was to develop a machine learning workflow based on supervised PLS regression and SVM classification, towards automated raw food categorization from FTIR. The system exhibited high efficiency in multi-class classification of 7 different types of raw food. The selected food samples, were diverse in terms of storage conditions (temperature, storage time and packaging), while the variability within each food was also taken into account by several different batches; leading in a classifier able to embed this variation towards increased robustness and efficiency, ready for real life applications targeting to the digital transformation of the food industry.Panagiotis TsakanikasApostolos KarnavasEfstathios Z. PanagouGeorge-John NychasNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 10, Iss 1, Pp 1-11 (2020)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Panagiotis Tsakanikas
Apostolos Karnavas
Efstathios Z. Panagou
George-John Nychas
A machine learning workflow for raw food spectroscopic classification in a future industry
description Abstract Over the years, technology has changed the way we produce and have access to our food through the development of applications, robotics, data analysis, and processing techniques. The implementation of these approaches by the food industry ensure quality and affordability, reducing at the same time the costs of keeping the food fresh and increase productivity. A system, as the one presented herein, for raw food categorization is needed in future food industries to automate food classification according to type, the process of algorithm approaches that will be applied to every different food origin and also for serving disabled people. The purpose of this work was to develop a machine learning workflow based on supervised PLS regression and SVM classification, towards automated raw food categorization from FTIR. The system exhibited high efficiency in multi-class classification of 7 different types of raw food. The selected food samples, were diverse in terms of storage conditions (temperature, storage time and packaging), while the variability within each food was also taken into account by several different batches; leading in a classifier able to embed this variation towards increased robustness and efficiency, ready for real life applications targeting to the digital transformation of the food industry.
format article
author Panagiotis Tsakanikas
Apostolos Karnavas
Efstathios Z. Panagou
George-John Nychas
author_facet Panagiotis Tsakanikas
Apostolos Karnavas
Efstathios Z. Panagou
George-John Nychas
author_sort Panagiotis Tsakanikas
title A machine learning workflow for raw food spectroscopic classification in a future industry
title_short A machine learning workflow for raw food spectroscopic classification in a future industry
title_full A machine learning workflow for raw food spectroscopic classification in a future industry
title_fullStr A machine learning workflow for raw food spectroscopic classification in a future industry
title_full_unstemmed A machine learning workflow for raw food spectroscopic classification in a future industry
title_sort machine learning workflow for raw food spectroscopic classification in a future industry
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/5e30514efc6247cab929d114789321c6
work_keys_str_mv AT panagiotistsakanikas amachinelearningworkflowforrawfoodspectroscopicclassificationinafutureindustry
AT apostoloskarnavas amachinelearningworkflowforrawfoodspectroscopicclassificationinafutureindustry
AT efstathioszpanagou amachinelearningworkflowforrawfoodspectroscopicclassificationinafutureindustry
AT georgejohnnychas amachinelearningworkflowforrawfoodspectroscopicclassificationinafutureindustry
AT panagiotistsakanikas machinelearningworkflowforrawfoodspectroscopicclassificationinafutureindustry
AT apostoloskarnavas machinelearningworkflowforrawfoodspectroscopicclassificationinafutureindustry
AT efstathioszpanagou machinelearningworkflowforrawfoodspectroscopicclassificationinafutureindustry
AT georgejohnnychas machinelearningworkflowforrawfoodspectroscopicclassificationinafutureindustry
_version_ 1718384112777035776