Neural network committee to predict the AMEn of poultry feedstuffs

Mariano, Flávia C Q; Lima, Renato Ribeiro de; Alvarenga, Renata Ribeiro; Rodrigues, Paulo Borges; Lacerda, Wilian Soares

doi:10.1007/s00521-014-1680-3

Cited by 6 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the present study, a multilayer-perceptron (MLP) committee neural network was considered, which was developed to predict AMEn values of energetic and protein concentrates for poultry (Mariano et al, 2014). All networks considered in the committee had the same MLP architecture 7-5-3-1, which represents: 7 inputs, 5 neurons in the first hidden layer, 3 neurons in the second hidden layer, and 1 output.…”

Section: Methodsmentioning

confidence: 99%

“…The choice of this committee was based on the value of the 95.83% correct predictions. Further information on the development of this committee can be obtained from Mariano et al (2014). Mariano et al (2012) proposed and evaluated some of the AMEn prediction equations of poultry feedstuffs based on their chemical composition.…”

Section: Methodsmentioning

confidence: 99%

“…In the poultry science area, Mariano et al (2014) have developed a committee network to predict the AMEn of poultry, in which the mode of the empirical distribution was the estimator that ensured more accurate predictions for these energy values. Furthermore, they recommended its use because it allows associating some uncertainty with the prediction, using a highest probability density (HPD) interval.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs

Mariano

Lima

Alvarenga

et al. 2020

Pesq. agropec. bras.

View full text Add to dashboard Cite

How to citeMARIAno, F.C.M.Q.; LIMA, R.R. de; ALvAREnGA, R.R.; RoDRIGUES, P.B. Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs. Pesquisa Agropecuária Brasileira, v.55, e01199, 2020. Abstract -The objective of this work was to compare the committee neural network (CNN) and weighted multiple linear regression (WMLR) models, in order to estimate the nitrogen-corrected apparent metabolizable energy (AMEn) of poultry feedstuffs. The prediction equation was adjusted by using a WMLR model and the meta-analysis principle. The models were compared by considering the correct prediction percentages, based on the classic prediction intervals and on the highest-probability density intervals, and by using a comparison test for proportions. The accuracy of the models was evaluated based on the values of the mean squared error, coefficient of determination, mean absolute deviation, mean absolute percentage error, and bias. Data from metabolic trials were used to compare the selected models. The committee neural network is the model that showed the highest accuracy of prediction, being recommended as the most accurate model to predict AMEn values for energetic concentrate feedstuffs used by the poultry feed industry.Index terms: broilers, highest-probability density interval, meta-analysis, metabolizable energy, percentage of success. Comitê de redes neurais e regressão múltipla ponderada para a predição de valores energéticos de alimentos para aves de corteResumo -O objetivo deste trabalho foi comparar o modelo comitê de redes neurais e o modelo de regressão linear múltipla ponderada (RLMP), para estimar a energia metabolizável aparente corrigida por nitrogênio (EMAn) de alimentos para aves. A equação de predição foi ajustada por RLMP e pelo princípio da meta-análise. Os modelos foram comparados tendo-se considerando as percentagens de acerto de predição, com base em intervalos de predição clássicos e intervalos de credibilidade da máxima densidade de probabilidade, e utilizado um teste para comparação de proporções. A acurácia dos modelos foi avaliada com base nos valores de erro médio quadrático, coeficiente de determinação, desvio médio absoluto, erro percentual absoluto médio e viés. Dados provenientes de ensaios metabólicos foram utilizados na comparação dos modelos selecionados. O comitê de redes neurais é o modelo que forneceu predições mais acuradas, sendo recomendado como o de maior acurácia, para prever os valores de EMAn de alimentos concentrados utilizados na indústria alimentícia para aves.Termos para indexação: frangos de corte, intervalo de credibilidade da máxima probabilidade, meta-análise, energia metabolizável, percentagem de acerto. 2 F.C.M.Q. Mariano et al.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs

Mariano

Lima

Alvarenga

et al. 2020

Pesq. agropec. bras.

View full text Add to dashboard Cite

show abstract

“…This process, known as cross validation, was performed as outlined in Mariano et al (2014), who stated that data used in this process are randomly clustered in two distinct sets known as training and validation data sets.…”

Section: Methodsmentioning

confidence: 99%

“…The following parameters were also used to define the statistical quality of the model as described in Mariano et al (2014): Mean error (ME), mean absolute deviation (MAD), mean absolute percentage error (MAPE), and mean square error (MSE). These parameters described measurements of the prediction error obtained from the existing difference between observed and predicted values.…”

Section: Methodsmentioning

confidence: 99%

Validation of a phenological model for coffee tree productivity in Southern State of Minas Gerais, Brazil

Miranda¹,

Carvalho²,

Fahl³

et al. 2017

Afr. J. Agric. Res.

View full text Add to dashboard Cite

There are studies on the current state of understanding productivity models, focusing on the applicability of different estimation models for coffee tree productivity; the majority involving a considerable level of complexity. Thus, when searching for a simple and direct association between phenological characteristics and coffee productivity, doing research on this hypothesis is necessary. In this study, we aimed to validate a phenological model for coffee tree productivity by using phenological indices, under given edaphoclimatic conditions of Southern State of Minas Gerais, Brazil. We used 10 sample plots obtained from the municipalities of Lavras, Varginha, Carmo de Minas, Ijaci and Santo Antônio do Amparo. Plots were chosen based on the existing history about coffee productivity, which is over 40 sacks ha -1 . Phenological data were collected in September-October, December-January and March to April of the harvesting seasons 2012/2013 and 2013/2014. The number of flowers and fruits were obtained at the fourth and fifth productive nodes of coffee plagiotropic branches sampled at the middle third of each coffee plant. Forty plants were sampled in each plot for the measurement of plant height and estimates of productivity phenological indices. Data regarding the observed production were obtained for models comparison and validation and, then, statistical tests were run. Results showed that these models are suitable for the coffee crop in the region under study. In addition, productivity phenological indices showed good correlation with the observed productivity.

show abstract

Ensemble of hybrid Bayesian networks for predicting the AMEn of broiler feedstuffs

Alvarenga

Lima

Simão

et al. 2022

Computers and Electronics in Agriculture

View full text Add to dashboard Cite

Neural network committee to predict the AMEn of poultry feedstuffs

Cited by 6 publications

References 18 publications

Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs

Committee neural network and weighted multiple regression to predict the energetic values of poultry feedstuffs

Validation of a phenological model for coffee tree productivity in Southern State of Minas Gerais, Brazil

Ensemble of hybrid Bayesian networks for predicting the AMEn of broiler feedstuffs

Contact Info

Product

Resources

About