Utilization of artificial neural networks in the prediction of the bunches’ weight in banana plants

Soares, J. D. R.; Pasqual, Moacir; Lacerda, Wilian Soares; Silva, S.O.; Donato, Sérgio Luíz Rodrigues

doi:10.1016/j.scienta.2013.01.026

Cited by 41 publications

(24 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Similar results were obtained by Soares (2013), with the Tropical cultivar which denotes a general pattern of straight variation of bunch mass with the stem diameter, an expected result. This happens because bunches are composed of hands (fruits) and stem (rachis), and the bigger bunches have longer rachises (Jaramillo, 1982), although the percentual participation of the rachis in the bunch mass decreases with the increase on its mass.…”

Section: Resultssupporting

confidence: 86%

“…However, this result does not agree with Donato (2006a) and Soares (2013), who state that bunch weight and pseudostem perimeter correlation is not significant and positive, which may indicate that, regardless of pseudostem thickness, the bunch mass may have a satisfactory value. However, genotypes with higher and lower height showed, respectively, higher and lower pseudostem perimeter as well.…”

Section: Resultscontrasting

confidence: 75%

“…In this context, Soares (2013) observed that, despite being significant and positive, the relation bunch mass and number of green leaves showed a correlation coefficient of low magnitude. This indicates that the bunch mass varies in a direct way in relation to the number of green leaves, but, if the minimum demands of number of leaves is met, this influence is not expressive.…”

Section: Resultsmentioning

confidence: 88%

“…However, the magnitude of this correlation was the lowest among the vegetative variables evaluated for hybrid BRS Platina (Table 3). Soares (2013) stated the same for the cultivar tropical. However, Siqueira (1984) found, from clones of 'Prata' bananas, that it is possible to select smaller genotypes without production impairing, as plant height, in most of the evaluated clones, did not correlate with any yield-associated character.…”

Section: Resultsmentioning

confidence: 93%

“…Donato et al (2006a) did not observe stable correlations for the relation bunch mass and stem length during the production cycles for the studied genotypes. Soares (2013) states that the bunch mass does not depend of the stem length. Thus, it can be suggested that it is not a consistent and reliable variable to compose a harvest prediction equation, although it is an easily measured and non-destructive variable.…”

Section: Resultsmentioning

confidence: 99%

See 4 more Smart Citations

Phenotypical correlations between agronomical characters in Prata type bananas (Musa) and its implications on yield estimat

Vinícius¹,

Guimarães²,

Donato³

et al. 2014

Afr. J. Agric. Res

View full text Add to dashboard Cite

This research aims to estimate correlations between agronomic traits and yield in Pome bananas, contributing to the elaboration of models for estimation of harvest. Agronomic traits were evaluated in 98 plants of 'Dwarf Prata' and 96 'BRS Platina', considered replicates and sampled at random. Correlations between the masses of the bunch, and hands and plant height; pseudostem perimeter at ground level, at 30 cm and at 100 cm in height; number of green leaves; mass of the bunch; number of hands and fruits per bunch; mass of the hands; mass, length and diameter of the stem, and mass of the fruit of the external row from the first to the tenth hand were estimated. The highest correlation coefficient between yield and vegetative traits for 'Dwarf Prata' and 'BRS Platina', was obtained for pseudostem perimeter at ground level, indicating its greater potential to compose harvest estimation models. The correlations between the masses of the bunch and hands with yield traits, for both genotypes, showed a higher potential for predicting the number of hands and fruits. Appropriate correlation estimates are associated with the fourth and fifth bunch, for the 'Dwarf Prata' and 'BRS Platina', respectively, using the mass of the fruit of the external row.

show abstract

Section: Resultssupporting

confidence: 86%

Section: Resultscontrasting

confidence: 75%

Section: Resultsmentioning

confidence: 88%

Section: Resultsmentioning

confidence: 93%

Section: Resultsmentioning

confidence: 99%

See 3 more Smart Citations

Phenotypical correlations between agronomical characters in Prata type bananas (Musa) and its implications on yield estimat

Vinícius¹,

Guimarães²,

Donato³

et al. 2014

Afr. J. Agric. Res

View full text Add to dashboard Cite

show abstract

Comparison of using regression modeling and an artificial neural network for herbage dry matter yield forecasting

Majkovič¹,

O’Kiely

Kramberger

et al. 2016

Journal of Chemometrics

View full text Add to dashboard Cite

This study presents an application of artificial neural network and regression modeling techniques for forecasting grassland dry matter yield. Using data from a field plot experiment on semi-natural grassland in Maribor (Slovenia), the multiple regression and artificial neural network methodologies were employed to explain the patterns of dry matter yield during a 6-year period. On the basis of the two proposed approaches forecasts were conducted for the independent, validation year (6). The results in terms of Theil inequality coefficient, mean absolute error, and correlation coefficient show a better forecasting performance for the artificial neural network (likely due to the non-linear relationships prevailing among regressors and regressand) while relationships between observables can be better explained by regression modeling results.

show abstract

Prediction of Walnut Mass Based on Physical Attributes by Artificial Neural Network (ANN)

et al. 2020

View full text Add to dashboard Cite

Utilization of artificial neural networks in the prediction of the bunches’ weight in banana plants

Cited by 41 publications

References 18 publications

Phenotypical correlations between agronomical characters in Prata type bananas (Musa) and its implications on yield estimat

Phenotypical correlations between agronomical characters in Prata type bananas (Musa) and its implications on yield estimat

Comparison of using regression modeling and an artificial neural network for herbage dry matter yield forecasting

Prediction of Walnut Mass Based on Physical Attributes by Artificial Neural Network (ANN)

Contact Info

Product

Resources

About