Comparison of Multiple Linear Regression and Artificial Neural Network Models to Estimate of Amino acid Values in Pearl Millet Hybrid Based on Chemical Composition
Pearl millet has tolerance to harsh growing conditions such as drought. It is at least equivalent to maize and generally superior to sorghum in protein content and metabolizable energy levels. Thus it is of importance for poultry feeding. Amino acid (AA) determination is expensive and time consumi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | fas |
| Published: |
Ferdowsi University of Mashhad
2016-06-01
|
| Series: | پژوهشهای علوم دامی ایران |
| Subjects: | |
| Online Access: | http://ijasr.um.ac.ir/index.php/animal/article/view/12542 |
| _version_ | 1831686530966487040 |
|---|---|
| author | paresa soulimani aboulgasem golian moohamad sedegi |
| author_facet | paresa soulimani aboulgasem golian moohamad sedegi |
| author_sort | paresa soulimani |
| collection | DOAJ |
| description | Pearl millet has tolerance to harsh growing conditions such as drought. It is at least equivalent to maize and
generally superior to sorghum in protein content and metabolizable energy levels. Thus it is of importance for
poultry feeding. Amino acid (AA) determination is expensive and time consuming. Therefore nutritionists have
prompted a search for alternatives to estimate AA levels. Traditionally, two methods of predicting AA levels
have been developed using multiple linear regression (MLR) with an input of either CP or proximate analysis.
Artificial neural networks (ANN) may be more effective to predict AA concentration in feedstuff. Therefore a
study was conducted to predict the AAs level in pearl millet with either MLR or ANN. Fifty two samples of
pearl millet’s data lines contained chemical compositions and AAs which collected from literature were used to
find the relationship between chemical analysis as xi and AA contents as y. For both MLR and ANN models
chemical composition (dry matter, ash, crude fiber, crude protein, ether extract) was used as inputs and each
individual AA was the output in each model. The results of this study showed that it is possible to predict AAs
with a simple analytical determination of proximate analysis. Furthermore ANN models could more effectively
identify the relationship between AAs and proximate analysis than linear regression model. |
| first_indexed | 2024-12-20T08:41:16Z |
| format | Article |
| id | doaj.art-2c8955aef26f43b38ba5b220ee51854c |
| institution | Directory Open Access Journal |
| issn | 2008-3106 2423-4001 |
| language | fas |
| last_indexed | 2024-12-20T08:41:16Z |
| publishDate | 2016-06-01 |
| publisher | Ferdowsi University of Mashhad |
| record_format | Article |
| series | پژوهشهای علوم دامی ایران |
| spelling | doaj.art-2c8955aef26f43b38ba5b220ee51854c2022-12-21T19:46:23ZfasFerdowsi University of Mashhadپژوهشهای علوم دامی ایران2008-31062423-40012016-06-01344528Comparison of Multiple Linear Regression and Artificial Neural Network Models to Estimate of Amino acid Values in Pearl Millet Hybrid Based on Chemical Compositionparesa soulimani0aboulgasem golian1moohamad sedegi2Ferdowsi University of MashhadFerdwosi University of MashhadFerdowsi University of MashhadPearl millet has tolerance to harsh growing conditions such as drought. It is at least equivalent to maize and generally superior to sorghum in protein content and metabolizable energy levels. Thus it is of importance for poultry feeding. Amino acid (AA) determination is expensive and time consuming. Therefore nutritionists have prompted a search for alternatives to estimate AA levels. Traditionally, two methods of predicting AA levels have been developed using multiple linear regression (MLR) with an input of either CP or proximate analysis. Artificial neural networks (ANN) may be more effective to predict AA concentration in feedstuff. Therefore a study was conducted to predict the AAs level in pearl millet with either MLR or ANN. Fifty two samples of pearl millet’s data lines contained chemical compositions and AAs which collected from literature were used to find the relationship between chemical analysis as xi and AA contents as y. For both MLR and ANN models chemical composition (dry matter, ash, crude fiber, crude protein, ether extract) was used as inputs and each individual AA was the output in each model. The results of this study showed that it is possible to predict AAs with a simple analytical determination of proximate analysis. Furthermore ANN models could more effectively identify the relationship between AAs and proximate analysis than linear regression model.http://ijasr.um.ac.ir/index.php/animal/article/view/12542Amino acid, Neural network model, Pearl millet |
| spellingShingle | paresa soulimani aboulgasem golian moohamad sedegi Comparison of Multiple Linear Regression and Artificial Neural Network Models to Estimate of Amino acid Values in Pearl Millet Hybrid Based on Chemical Composition پژوهشهای علوم دامی ایران Amino acid, Neural network model, Pearl millet |
| title | Comparison of Multiple Linear Regression and Artificial Neural Network Models to Estimate of Amino acid Values in Pearl Millet Hybrid Based on Chemical Composition |
| title_full | Comparison of Multiple Linear Regression and Artificial Neural Network Models to Estimate of Amino acid Values in Pearl Millet Hybrid Based on Chemical Composition |
| title_fullStr | Comparison of Multiple Linear Regression and Artificial Neural Network Models to Estimate of Amino acid Values in Pearl Millet Hybrid Based on Chemical Composition |
| title_full_unstemmed | Comparison of Multiple Linear Regression and Artificial Neural Network Models to Estimate of Amino acid Values in Pearl Millet Hybrid Based on Chemical Composition |
| title_short | Comparison of Multiple Linear Regression and Artificial Neural Network Models to Estimate of Amino acid Values in Pearl Millet Hybrid Based on Chemical Composition |
| title_sort | comparison of multiple linear regression and artificial neural network models to estimate of amino acid values in pearl millet hybrid based on chemical composition |
| topic | Amino acid, Neural network model, Pearl millet |
| url | http://ijasr.um.ac.ir/index.php/animal/article/view/12542 |
| work_keys_str_mv | AT paresasoulimani comparisonofmultiplelinearregressionandartificialneuralnetworkmodelstoestimateofaminoacidvaluesinpearlmillethybridbasedonchemicalcomposition AT aboulgasemgolian comparisonofmultiplelinearregressionandartificialneuralnetworkmodelstoestimateofaminoacidvaluesinpearlmillethybridbasedonchemicalcomposition AT moohamadsedegi comparisonofmultiplelinearregressionandartificialneuralnetworkmodelstoestimateofaminoacidvaluesinpearlmillethybridbasedonchemicalcomposition |