Advanced search

Genetic algorithm and greedy stepwise methods for optimization of predictive Azolla filiculoides (Lam.) based on classification trees

Author
Organization
Abstract
Cover percentage of Azolla and 33 wetland characteristics were collected at the Selkeh wildlife refuge, in Anzali wetland, northern Iran in over the study period 2007-2008. Classification tree (CT) was developed in order to find the relationship between the wetland characteristics and the dynamic pattern of Azolla. Greedy stepwise and genetic algorithms were combined with CT so as to select the most important explanatory variables for the prediction of Azolla distribution. The applied methods were assessed based on the percentage of Correctly Classified Instances and Cohen's kappa statistics. The results of the present study demonstrated that after variable selection, the predictive performances of CT improved drastically and hence resulted in to an easy interpretation of CT model.
Keywords
classification tree, Ecological modelling, genetic algorithm., greedy stepwise

Citation

Please use this url to cite or link to this publication:

Chicago
Sadeghi Pasvisheh, Roghayeh, Rahmat Zarkami, Karim Sabetraftar, and Patrick Van Damme. 2012. “Genetic Algorithm and Greedy Stepwise Methods for Optimization of Predictive Azolla Filiculoides (Lam.) Based on Classification Trees.” In Applied Biological Sciences, 17th PhD Symposium, Posters.
APA
Sadeghi Pasvisheh, R., Zarkami, R., Sabetraftar, K., & Van Damme, P. (2012). Genetic algorithm and greedy stepwise methods for optimization of predictive Azolla filiculoides (Lam.) based on classification trees. Applied Biological Sciences, 17th PhD Symposium, Posters. Presented at the 17th PhD Symposium on Applied Biological Sciences.
Vancouver
1.
Sadeghi Pasvisheh R, Zarkami R, Sabetraftar K, Van Damme P. Genetic algorithm and greedy stepwise methods for optimization of predictive Azolla filiculoides (Lam.) based on classification trees. Applied Biological Sciences, 17th PhD Symposium, Posters. 2012.
MLA
Sadeghi Pasvisheh, Roghayeh, Rahmat Zarkami, Karim Sabetraftar, et al. “Genetic Algorithm and Greedy Stepwise Methods for Optimization of Predictive Azolla Filiculoides (Lam.) Based on Classification Trees.” Applied Biological Sciences, 17th PhD Symposium, Posters. 2012. Print.
@inproceedings{3039613,
  abstract     = {Cover percentage of Azolla and 33 wetland characteristics were collected at the Selkeh wildlife refuge, in Anzali wetland, northern Iran in over the study period 2007-2008. Classification tree (CT) was developed in order to find the relationship between the wetland characteristics and the dynamic pattern of Azolla. Greedy stepwise and genetic algorithms were combined with CT so as to select the most important explanatory variables for the prediction of Azolla distribution. The applied methods were assessed based on the percentage of Correctly Classified Instances and Cohen's kappa statistics. The results of the present study demonstrated that after variable selection, the predictive performances of CT improved drastically and hence resulted in to an easy interpretation of CT model.},
  author       = {Sadeghi Pasvisheh, Roghayeh and Zarkami, Rahmat and Sabetraftar, Karim and Van Damme, Patrick},
  booktitle    = {Applied Biological Sciences, 17th PhD Symposium, Posters},
  keyword      = {classification tree,Ecological modelling,genetic algorithm.,greedy stepwise},
  language     = {eng},
  location     = {Leuven, Belgium},
  title        = {Genetic algorithm and greedy stepwise methods for optimization of predictive Azolla filiculoides (Lam.) based on classification trees},
  year         = {2012},
}