ESTIMATION OF EUCALYPTUS HEIGHT BY MEANS OF NONLINEAR REGRESSION AND ARTIFICIAL NEURAL NETWORKS
Main Article Content
Abstract
In this work was evaluated the nonlinear regression modeling and artificial neural networks to estimate the eucalyptus trees tall. The stands are located in Itiquira, MT. Data were obtained from 23 parcels measured at four years old. The database was divided into two sets, one for the adjustment of regression models and training the networks (70%) and the other to validate the regression and validating the trained networks (30%). The nonlinear regression model was used the Gompertz and the networks of the multilayer perceptron (MLP). The evaluation of the estimates accuracy was by the multiple correlation coefficient between the observed and estimated heights, square root of the average error in percentage and graphical analysis. Both evaluated techniques are effective for predicting the height of trees. However, neural networks statistical criteria showed slightly higher relative to the regression.
Article Details
How to Cite
VENDRUSCOLO, D. G. S., DRESCHER, R., SOUZA, H. S., MOURA, J. P. V. M., MAMORÉ, F. M. D., & SIQUEIRA, T. A. da S. (2015). ESTIMATION OF EUCALYPTUS HEIGHT BY MEANS OF NONLINEAR REGRESSION AND ARTIFICIAL NEURAL NETWORKS. Brazilian Journal of Biometrics, 33(4), 556–569. Retrieved from http://200.131.250.9/index.php/BBJ/article/view/33
Issue
Section
Articles
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).