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

Computers and Electronics in Agriculture

Volumn 117, Issue , 2015, Pages 186-193

  Brillante, Luca ^a   Gaiotti, Federica ^a   Lovat, Lorenzo ^a   Vincenzi, Simone ^b   Giacosa, Simone ^c   Torchio, Fabrizio ^c   Segade, Susana Río ^c   Rolle, Luca ^c   Tomasi, Diego ^a  

^a Center for Research in Viticulture   (Italy)

^b UNIVERSITY OF PADOVA   (Italy)

^c UNIVERSITY OF TURIN   (Italy)

Author keywords

Flavonoids; Gradient Boosting Machine (GBM); Random forest; Texture analysis; Wine grape

Indexed keywords

ADAPTIVE BOOSTING; ARTIFICIAL INTELLIGENCE; COST EFFECTIVENESS; DECISION TREES; FLAVONOIDS; FRUITS; LEARNING ALGORITHMS; MEAN SQUARE ERROR; WINE;

GRADIENT BOOSTING; MACHINE LEARNING TECHNIQUES; MECHANICAL CHARACTERISTICS; RANDOM FORESTS; RMSE (ROOT MEAN SQUARE ERROR); TEXTURE ANALYSIS; TOTAL FLAVONOID CONTENTS; WINE GRAPES;

LEARNING SYSTEMS;

ALCOHOL; BIOACTIVITY; BIOMECHANICS; CULTIVAR; MACHINE LEARNING; MACHINERY; METABOLITE; NUMERICAL MODEL; PHYSICAL PROPERTY; VINE;

VITACEAE; VITIS; VITIS VINIFERA;

EID: 84939787273     PISSN: 01681699     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.compag.2015.07.017     Document Type: Article

References (48)

1. Ambroise C., McLachlan G.J. Selection bias in gene extraction on the basis of microarray gene-expression data. PNAS 2002, 99:6562-6566.
2. Barbagallo M.G., Guidoni S., Hunter J.J. Berry size and qualitative characteristics of Vitis vinifera L. cv. Syrah. S. Afr. J. Enol. Vitic. 2011, 32:129-136.
3. Battista F., Tomasi D., Porro D., Caicci F., Giacosa S., Rolle L. Winegrape berry skin thickness determination: comparison between histological observations and texture analysis determination. Ital. J. Food Sci. 2015, 27:136-141.
4. Braidot E., Zancani M., Petrussa E., Peresson C., Bertolini A., Patui S., Macri F., Vianello A. Transport and accumulation of flavonoids in grapevine (Vitis vinifera L.). Plant Signal. Behav. 2008, 3:626-632.
5. Breiman, L., 1996. Bias, variance, and arcing classifiers. In: Technical report 460 Statistics Department University of California.
6. Breiman L. Bagging predictors. Mach. Learn. 1996, 24:123-140.
7. Breiman L., Friedman J.H., Olshen R.A., Stone C.J. Classification and Regression Trees 1984, Statistics and probaility series, Wadsworth, Belmont, CA.
8. Breiman L. Random forests. Mach. Learn. 2001, 45:5-32.
9. Cozzolino D. The role of visible and infrared spectroscopy combined with chemometrics to measure phenolic compounds in grape and wine samples. Molecules 2015, 20:726-737.
10. Caruana, R., Munson, A., Alexandru, N.-M. Getting the most out of ensemble selection. Int. Conf. Data Min., 2006, pp. 1-12.
11. Caruana, R., Niculescu-Mizil, A., Crew, G., Ksikes, A., 2011. Ensemble selection from libraries of models. Proc. ICML '04 2011, vol. 34, pp. 1-21.
12. Di Stefano R., Cravero M.C. Metodi per lo studio dei polifenoli dell'uva. Riv. di Vitic. ed Enol. 1991, 44:37-45.
13. Efron B., Tibshirani R. Improvements on cross-validation: the 632+ bootstrap method. J. Am. Stat. Assoc. 1997, 92(438):548-560.
14. Ferrer-Gallego R., Hernàndez-Hierro, Rivas.-Gonzalo J., Escribano-Bailón M.T. Determination of phenolic compounds of grape skins during ripening by NIR spectroscopy. LWT-Food Sci. Technol. 2011, 44:847-853.
15. Freund Y., Schapire R. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 1997, 55:119-139.
16. Friedman J.H. Greedy function approximation: a gradient boosting machine. Ann. Stat. 2001, 29:1189-1232.
17. Giordano M., Zecca O., Belviso S., Reinotti M., Gerbi V., Rolle L. Volatile fingerprint and physico-mechanical properties of 'Muscat blanc' grapes grown in mountain area: a first evidence of the influence of water regimes. Ital. J. Food Sci. 2013, 25:329-338.
18. Gonzalez J., Donoso W., Sandoval N., Reyes M., Gonzalez P., Gajardo M., Morales E., Neira A., Razmilic I., Yuri J.A., Moore-Carrasco R. Apple peel supplemented diet reduces parameters of metabolic syndrome and atherogenic progression in ApoE -/- Mice. Evidence-Based Complement. Altern. Med. 2015.
19. González-Neves G., Charamelo D., Balado J., Barreiro L., Bochicchio R., Gatto G., Gil G., Tessore A., Carbonneau A., Moutonet M. Phenolic potential of Tannat, Cabernet-Sauvignon and Merlot grapes and their correspondence with wine composition. Anal. Chim. Acta 2004, 513:191-196.
20. Guyon I., Weston J., Barnhill S., Vladimir V. Gene selection for cancer classification using Support Vector Machines. Mach. Learn. 2002, 46:389-422.
21. Harnly J.M., Doherty R.F., Beecher G.R., Holden J.M., Haytowitz D.B., Bhagwat, Gebhardt S. Flavonoid content of U.S. fruits, vegetables, and nuts. J. Agric. Food Chem. 2006, 54:9966-9977.
22. Hastie T., Tibshirani R., Friedman J. The elements of statistical learning: data mining, inference, and prediction 2009, Springer, Netherlands. second ed.
23. Ignat I., Volf I., Popa V.I. A critical review of methods for characterisation of polyphenolic compounds in fruits and vegetables. Food Chem. 2011, 126:1821-1835.
24. Kuhn N., Guan L., Dai Z.W., Wu B.H., Lauvergeat V., Gomès E., Li S.H., Godoy F., Arce-Johnson P., Delrot S. Berry ripening: recently heard through the grapevine. J. Exp. Bot. 2013, 65:4543-4559.
25. Kuhn, M., Wing, J., Weston, S., Williams, A., Keefer, C., Engelhardt, A., Cooper, T., 2014. Caret: classification and regression training. R package version 6.0-37. http://www.CRAN.R-project.org/package=caret.
26. Koundouras S., Marinos V., Gkoulioti A., Kotseridis Y., Van Leeuwen C. Influence of vineyard location and vine water status on fruit maturation of non-irrigated cv. Agiorgitiko (Vitis vinifera L.). Effects on wine phenolic and aroma components. J. Agric. Food Chem. 2006, 54:5077-5086.
27. Liaw A., Wiener M. Classification and regression by randomForest. R News 2002, 2(3):18-22.
28. Letaief H., Rolle L., Gerbi V. Mechanical behavior of wine grapes under compression tests. Am. J. Enol. Vitic. 2008, 59:323-329.
29. Lorrain B., Ky I., Pechamat L., Teissedre P.L. Evolution of analysis of polyhenols from grapes, wines, and extracts. Molecules 2013, 18(1):1076-1100.
30. Lourenço F., Gago B., Barbosa R.M., De Freitas V., Laranjinha J. LDL isolated from plasma-loaded red wine procyanidins resist lipid oxidation and tocopherol depletion. J. Agric. Food Chem. 2008, 56:3798-3804.
31. Maloney K.O., Schmid M., Weller D.E. Applying additive modelling and gradient boosting to assess the effects of watershed and reach characteristics on riverine assemblages. Methods Ecol. Evol. 2012, 3:116-128.
32. Noll C., Hamelet J., Matulewicz E., Paul J.L., Delabar J.M., Janel N. Effects of red wine polyphenolic compounds on paraoxonase-1 and lectin-like oxidized low-density lipoprotein receptor-1 in hyperhomocysteinemic mice. J. Nutr. Biochem. 2009, 20:586-596.
33. R Core Team R: A language and environment for statistical computing 2014, R Foundation for Statistical Computing, Vienna, Austria, http://www.R-project.org/
34. Ridgeway, G., 2013. Gbm: generalized boosted regression models. R package version 2.1. http://www.CRAN.R-project.org/package=gbm.
35. Ristic R., Bindon K., Francis L.I., Herderich M.J., Iland P.G. Flavonoids and C13-norisoprenoids in Vitis vinifera L. cv. Shiraz: Relationships between grape and wine composition, wine colour and wine sensory properties. Aust. J. Grape Wine Res. 2010, 16:369-388.
36. Río Segade S., Rolle L., Gerbi V., Orriols I. Phenolic ripeness assessment of grape skin by texture analysis. J. Food Compos. Anal. 2008, 21:644-649.
37. Río Segade S., Orriols I., Giacosa S., Rolle L. Instrumental texture analysis parameters as winegrapes varietal markers and ripeness predictors. Int. J. Food Prop. 2011, 14:1318-1329.
38. Río Segade S., Soto Vázquez E., Orriols I., Giacosa S., Rolle L. Possible use of texture characteristics of winegrapes as markers for zoning and their relationship with anthocyanin extractability index. Int. J. Food Sci. Technol. 2011, 46:386-394.
39. Río Segade S., Giacosa S., Gerbi V., Rolle L. Berry skin thickness as main texture parameter to predict anthocyanin extractability in winegrapes. LWT-Food Sci. Technol. 2011, 44:392-398.
40. Rolle L., Rio Segade S., Torchio F., Giacosa S., Cagnasso E., Marengo F. Influence of grape density at harvest date on changes in phenolic composition, phenol extractability indices, and instrumental texture properties during ripening. J. Agric. Food Chem. 2011, 59:8796-8805.
41. Rolle L., Torchio F., Lorrain B., Giacosa S., Río Segade S., Cagnasso E., Gerbi V., Teissedre P.L. Rapid methods for the evaluation of total phenol content and extractability in intact grape seeds of Cabernet-Sauvignon: Instrumental mechanical properties and FT-NIR spectrum. J. Int. Sci. Vigne Vin 2012, 46:29-40.
42. Rolle L., Torchio F., Ferrandino A., Guidoni S. Influence of wine-grape skin hardness on the kinetics of anthocyanin extraction. Int. J. Food Prop. 2012, 15:249-261.
43. Rolle L., Giacosa S., Torchio F., Perenzoni D., Río Segade S., Gerbi V., Mattivi F. Use of instrumental acoustic parameters of winegrape seeds as possible predictors of extractable phenolic compounds. J. Agric. Food Chem. 2013, 61:8752-8764.
44. Scott I.M., Lin W., Liakata M., Wood J.E., Vermeer C.P., Allaway D., Ward J.L., Draper J., Beale M.H., Corol D.I., Baker J.M., King R.D. Merits of random forests emerge in evaluation of chemometric classifiers by external validation. Anal. Chim. Acta 2013, 801:22-33.
45. Therneau, T., Atkinson, B., Ripley, B., 2015. rpart: Recursive Partitioning and Regression Trees. R package version 4.1-9. http://www.CRAN.R-project.org/package=rpart.
46. Strobl C., Boulesteix A.-L., Zeileis A., Hothorn T. Bias in random forest variable importance measures: illustrations, sources and a solution. BMC Bioinformatics 2007, 8:25.
47. Yao L.H., Jiang Y.M., Shi J., Tomás-Barberán F.A., Datta N., Singanusong R. Flavonoids in food and their health benefits. Plant Foods Hum. Nutr. 2004, 59:113-122.
48. Zouid I., Siret R., Jourjon F., Mehinagic E., Rolle L. Impact of grapes heterogeneity according to sugar level on both physical and mechanical berries properties and their anthocyanins extractability at harvest. J. Texture Stud. 2013, 44:95-103.