Supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data

Abstract Strawberry is one of the most popular fruits in the market. To meet the demanding consumer and market quality standards, there is a strong need for an on-site, accurate and reliable grading system during the whole harvesting process. In this work, a total of 923 strawberry fruit were measur...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pietro Ibba, Christian Tronstad, Roberto Moscetti, Tanja Mimmo, Giuseppe Cantarella, Luisa Petti, Ørjan G. Martinsen, Stefano Cesco, Paolo Lugli
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/7c67d5a035204cbbac622f15df99398c
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7c67d5a035204cbbac622f15df99398c
record_format dspace
spelling oai:doaj.org-article:7c67d5a035204cbbac622f15df99398c2021-12-02T14:49:25ZSupervised binary classification methods for strawberry ripeness discrimination from bioimpedance data10.1038/s41598-021-90471-52045-2322https://doaj.org/article/7c67d5a035204cbbac622f15df99398c2021-05-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-90471-5https://doaj.org/toc/2045-2322Abstract Strawberry is one of the most popular fruits in the market. To meet the demanding consumer and market quality standards, there is a strong need for an on-site, accurate and reliable grading system during the whole harvesting process. In this work, a total of 923 strawberry fruit were measured directly on-plant at different ripening stages by means of bioimpedance data, collected at frequencies between 20 Hz and 300 kHz. The fruit batch was then splitted in 2 classes (i.e. ripe and unripe) based on surface color data. Starting from these data, six of the most commonly used supervised machine learning classification techniques, i.e. Logistic Regression (LR), Binary Decision Trees (DT), Naive Bayes Classifiers (NBC), K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Multi-Layer Perceptron Networks (MLP), were employed, optimized, tested and compared in view of their performance in predicting the strawberry fruit ripening stage. Such models were trained to develop a complete feature selection and optimization pipeline, not yet available for bioimpedance data analysis of fruit. The classification results highlighted that, among all the tested methods, MLP networks had the best performances on the test set, with 0.72, 0.82 and 0.73 for the F $$_1$$ 1 , F $$_{0.5}$$ 0.5 and F $$_2$$ 2 -score, respectively, and improved the training results, showing good generalization capability, adapting well to new, previously unseen data. Consequently, the MLP models, trained with bioimpedance data, are a promising alternative for real-time estimation of strawberry ripeness directly on-field, which could be a potential application technique for evaluating the harvesting time management for farmers and producers.Pietro IbbaChristian TronstadRoberto MoscettiTanja MimmoGiuseppe CantarellaLuisa PettiØrjan G. MartinsenStefano CescoPaolo LugliNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-13 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Pietro Ibba
Christian Tronstad
Roberto Moscetti
Tanja Mimmo
Giuseppe Cantarella
Luisa Petti
Ørjan G. Martinsen
Stefano Cesco
Paolo Lugli
Supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data
description Abstract Strawberry is one of the most popular fruits in the market. To meet the demanding consumer and market quality standards, there is a strong need for an on-site, accurate and reliable grading system during the whole harvesting process. In this work, a total of 923 strawberry fruit were measured directly on-plant at different ripening stages by means of bioimpedance data, collected at frequencies between 20 Hz and 300 kHz. The fruit batch was then splitted in 2 classes (i.e. ripe and unripe) based on surface color data. Starting from these data, six of the most commonly used supervised machine learning classification techniques, i.e. Logistic Regression (LR), Binary Decision Trees (DT), Naive Bayes Classifiers (NBC), K-Nearest Neighbors (KNN), Support Vector Machine (SVM) and Multi-Layer Perceptron Networks (MLP), were employed, optimized, tested and compared in view of their performance in predicting the strawberry fruit ripening stage. Such models were trained to develop a complete feature selection and optimization pipeline, not yet available for bioimpedance data analysis of fruit. The classification results highlighted that, among all the tested methods, MLP networks had the best performances on the test set, with 0.72, 0.82 and 0.73 for the F $$_1$$ 1 , F $$_{0.5}$$ 0.5 and F $$_2$$ 2 -score, respectively, and improved the training results, showing good generalization capability, adapting well to new, previously unseen data. Consequently, the MLP models, trained with bioimpedance data, are a promising alternative for real-time estimation of strawberry ripeness directly on-field, which could be a potential application technique for evaluating the harvesting time management for farmers and producers.
format article
author Pietro Ibba
Christian Tronstad
Roberto Moscetti
Tanja Mimmo
Giuseppe Cantarella
Luisa Petti
Ørjan G. Martinsen
Stefano Cesco
Paolo Lugli
author_facet Pietro Ibba
Christian Tronstad
Roberto Moscetti
Tanja Mimmo
Giuseppe Cantarella
Luisa Petti
Ørjan G. Martinsen
Stefano Cesco
Paolo Lugli
author_sort Pietro Ibba
title Supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data
title_short Supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data
title_full Supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data
title_fullStr Supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data
title_full_unstemmed Supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data
title_sort supervised binary classification methods for strawberry ripeness discrimination from bioimpedance data
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/7c67d5a035204cbbac622f15df99398c
work_keys_str_mv AT pietroibba supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
AT christiantronstad supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
AT robertomoscetti supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
AT tanjamimmo supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
AT giuseppecantarella supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
AT luisapetti supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
AT ørjangmartinsen supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
AT stefanocesco supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
AT paololugli supervisedbinaryclassificationmethodsforstrawberryripenessdiscriminationfrombioimpedancedata
_version_ 1718389455654486016