BibSonomy :: publication ::

tag user group author concept BibTeX key search:all search:brazovayeye

The blue social bookmark and publication sharing system.

entry of brazovayeye:

(0)

This publication has not been reviewed yet.

rating distribution

average user rating

The average rating is computed over all reviews. However, some of them may be invisible to you due to the visibility setting chosen by the reviewers.

(0.0 of 5.0 based on 0 reviews)

Machine learning of poorly predictable ecological data

by: Y. Shan, D. Paull, and R. I. McKay

In: Ecological Modelling, Vol. 195, Nr. 1-2 (March 2007) , p. 129--138.

Abstract

a variety of machine learning techniques to a difficult modelling problem, the spatial distribution of an endangered Australian marsupial, the southern brown bandicoot Isoodon obesulus. Four learning techniques decision trees/rules, neural networks, support vector machines and genetic programming were applied to the problem. Support vector and neural network approaches gave marginally better predictivity, but in the context of low overall accuracy, decision trees and genetic programming gave more useful results because of the human comprehensibility of their models.

BibTeX record

@article{Shan:2006:EM,
  abstract = {a variety of machine learning techniques to a
                 difficult modelling problem, the spatial distribution
                 of an endangered Australian marsupial, the southern
                 brown bandicoot (Isoodon obesulus). Four learning
                 techniques decision trees/rules, neural networks,
                 support vector machines and genetic programming were
                 applied to the problem. Support vector and neural
                 network approaches gave marginally better predictivity,
                 but in the context of low overall accuracy, decision
                 trees and genetic programming gave more useful results
                 because of the human comprehensibility of their
                 models.},
  added-at = {2008-06-19T17:35:00.000+0200},
  author = {Shan, Y. and Paull, D. and McKay, R. I.},
  biburl = {http://www.bibsonomy.org/bibtex/2160c07f3f871ab47885e74c23aee167f/brazovayeye},
  doi = {doi:10.1016/j.ecolmodel.2005.11.015},
  interhash = {d20c8ba8231dd3190933dde3e4addcf2},
  intrahash = {160c07f3f871ab47885e74c23aee167f},
  journal = {Ecological Modelling},
  keywords = {Decision Neural Southern Spatial Support algorithms, bandicoot, brown distribution genetic machines, modelling networks, programming, trees, vector},
  month = {15 May},
  note = {Selected Papers from the Third Conference of the
                 International Society for Ecological Informatics
                 (ISEI), August 26--30, 2002, Grottaferrata, Rome,
                 Italy},
  number = {1-2},
  pages = {129--138},
  timestamp = {2008-06-19T17:35:00.000+0200},
  title = {Machine learning of poorly predictable ecological
                 data},
  volume = 195,
  year = 2006
}

Endnote record

%0 Journal Article
%1 Shan:2006:EM
%A Shan, Y.
%A Paull, D.
%A McKay, R. I.
%D 2006
%J Ecological Modelling
%K 
%N 1-2
%P 129--138
%T Machine learning of poorly predictable ecological
                 data
%R doi:10.1016/j.ecolmodel.2005.11.015
%V 195
%X a variety of machine learning techniques to a
                 difficult modelling problem, the spatial distribution
                 of an endangered Australian marsupial, the southern
                 brown bandicoot (Isoodon obesulus). Four learning
                 techniques decision trees/rules, neural networks,
                 support vector machines and genetic programming were
                 applied to the problem. Support vector and neural
                 network approaches gave marginally better predictivity,
                 but in the context of low overall accuracy, decision
                 trees and genetic programming gave more useful results
                 because of the human comprehensibility of their
                 models.