There are several well known Machine Learning techniques highly suitable for habitat modeling. We applied classification trees and artificial neutral networks (ANNs) to model presence/absence of Telestes muticellus, in order to evaluate their reliability and to compare their performances. The best performance of ANNs stressed their usefulness, as evidenced by their predictive power - not based on chance - and good discrimination.

Use of two data mining techniques to model presence/absence of Telestes muticellus, in Piedmont (North-Western Italy). Short note

TIRELLI, Santina;PESSANI, Daniela
2010-01-01

Abstract

There are several well known Machine Learning techniques highly suitable for habitat modeling. We applied classification trees and artificial neutral networks (ANNs) to model presence/absence of Telestes muticellus, in order to evaluate their reliability and to compare their performances. The best performance of ANNs stressed their usefulness, as evidenced by their predictive power - not based on chance - and good discrimination.
2010
87
255
256
http://www.mtsn.tn.it/pubblicazioni/18/87/52%20tirelli.pdf
decision tree; artificial neural network; ecological modelling; pruning; Piedmont; species prediction
Tirelli T.; Pessani D.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2318/71483
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact