Flavonoids are a class of bioactive compounds largely represented in grapevine and wine. They also affect the sensory quality of fruits and vegetables, and derived products. Methods available for flavonoid measurement are time-consuming, thus a rapid and cost-effective determination of these compounds is an important research objective. This work tests if applying machine learning techniques to texture analysis data allows to reach good performances for flavonoid estimation in grape berries. Whole berry and skin texture analysis was applied to berries from 22 red wine grape cultivars and linked to the total flavonoid content. Three machine-learning techniques (regression tree, random forest and gradient boosting machine) were then applied. Models reached a high accuracy both in the external and internal validation. The R2 ranged from 0.75 to 0.85 for the external validation and from 0.65 to 0.75 for the internal validation, while RMSE (Root Mean Square Error) went from 0.95 mg g1 to 0.7 mg g1 in the external validation and from 1.3 mg g1 to 1.1 mg g1 in the internal validation.

Investigating the use of gradient boosting machine, random forest and their ensemble to predict skin flavonoid content from berry physical-mechanical characteristics in wine grapes

GIACOSA, SIMONE;TORCHIO, FABRIZIO;RIO SEGADE, SUSANA;ROLLE, Luca Giorgio Carlo;
2015-01-01

Abstract

Flavonoids are a class of bioactive compounds largely represented in grapevine and wine. They also affect the sensory quality of fruits and vegetables, and derived products. Methods available for flavonoid measurement are time-consuming, thus a rapid and cost-effective determination of these compounds is an important research objective. This work tests if applying machine learning techniques to texture analysis data allows to reach good performances for flavonoid estimation in grape berries. Whole berry and skin texture analysis was applied to berries from 22 red wine grape cultivars and linked to the total flavonoid content. Three machine-learning techniques (regression tree, random forest and gradient boosting machine) were then applied. Models reached a high accuracy both in the external and internal validation. The R2 ranged from 0.75 to 0.85 for the external validation and from 0.65 to 0.75 for the internal validation, while RMSE (Root Mean Square Error) went from 0.95 mg g1 to 0.7 mg g1 in the external validation and from 1.3 mg g1 to 1.1 mg g1 in the internal validation.
2015
117
186
193
www.elsevier.com/inca/publications/store/5/0/3/3/0/4
Flavonoids; Gradient Boosting Machine (GBM); Random forest; Texture analysis; Wine-grape; Agronomy and Crop Science; Horticulture; Forestry; Computer Science Applications1707 Computer Vision and Pattern Recognition; Animal Science and Zoology
Brillante, Luca; Gaiotti, Federica; Lovat, Lorenzo; Vincenzi, Simone; Giacosa, Simone; Torchio, Fabrizio; Rio Segade, Susana; Rolle, Luca; Tomasi, Diego
File in questo prodotto:
File Dimensione Formato  
87 A - 2015 CEA - Investigating the use of gradient boosting machine, random forest and their ensemble to predict skin flavonoid content from berry physical-mechanical.pdf

Open Access dal 02/09/2017

Tipo di file: POSTPRINT (VERSIONE FINALE DELL’AUTORE)
Dimensione 720.91 kB
Formato Adobe PDF
720.91 kB Adobe PDF Visualizza/Apri
87 - 2015 CEA - Investigating the use of gradient boosting machine, random forest and their ensemble to predict skin flavonoid content from berry physical-mechanical characteristics in wine.pdf

Accesso riservato

Tipo di file: PDF EDITORIALE
Dimensione 566.29 kB
Formato Adobe PDF
566.29 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/1526764
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 37
  • ???jsp.display-item.citation.isi??? 33
social impact