CINECA IRIS Institutional Research Information System
IRIS è il sistema di gestione integrata dei dati della ricerca (persone, progetti, pubblicazioni, attività) adottato dall'Università degli Studi di Torino.
AperTO è l'archivio istituzionale Open Access destinato a raccogliere, rendere visibile e conservare la produzione scientifica dell'Università degli Studi di Torino.
EnglishAlburnus alburnus alborella is a fish species native to northern Italy. It has suffered a very sharp decrease in population over the last 20 years due to human impact. Therefore, it was selected for reintroduction projects. In this research project, support vector machines (SVM) were tested as possible tools for building reliable models of presence/absence of the species. A system of 198 sites located along the rivers of Piedmont in North-Western Italy was investigated. At each site, 19 physical-chemical and environmental variables were measured. We verified that performances did not improve after feature selection but, instead, they slightly decreased (from Correctly Classified Instances [CCI] = 84.34 and Cohen's k [k] = 0.69 to CCI = 82.81 and k = 0.66). However, feature selection is crucial in identifying the relevant features for the presence/absence of the species. We then compared SVMs performances with decision trees (DTs) and artificial neural networks (ANNs) built using the same dataset. SVMs outperformed DTs (CCI = 81.39 and k = 0.63) but not ANNs (CCI = 83.03 and k = 0.66), showing that SVMs and ANNs are the best performing models, proving that their application in freshwater management is more promising than traditional and other machine-learning techniques.
| Titolo: | Support vector machines to model presence/absence of Alburnus alburnus alborella (Teleostea, Cyprinidae) in North-Western Italy: Comparison with other machine learning techniques |
| Autori Riconosciuti: | |
| Autori: | Tina Tirelli; Marco Gamba; Daniela Pessani |
| Data di pubblicazione: | 2012 |
| Abstract: | Alburnus alburnus alborella is a fish species native to northern Italy. It has suffered a very sharp decrease in population over the last 20 years due to human impact. Therefore, it was selected for reintroduction projects. In this research project, support vector machines (SVM) were tested as possible tools for building reliable models of presence/absence of the species. A system of 198 sites located along the rivers of Piedmont in North-Western Italy was investigated. At each site, 19 physical-chemical and environmental variables were measured. We verified that performances did not improve after feature selection but, instead, they slightly decreased (from Correctly Classified Instances [CCI] = 84.34 and Cohen's k [k] = 0.69 to CCI = 82.81 and k = 0.66). However, feature selection is crucial in identifying the relevant features for the presence/absence of the species. We then compared SVMs performances with decision trees (DTs) and artificial neural networks (ANNs) built using the same dataset. SVMs outperformed DTs (CCI = 81.39 and k = 0.63) but not ANNs (CCI = 83.03 and k = 0.66), showing that SVMs and ANNs are the best performing models, proving that their application in freshwater management is more promising than traditional and other machine-learning techniques. |
| Volume: | 335 |
| Pagina iniziale: | 680 |
| Pagina finale: | 686 |
| Digital Object Identifier (DOI): | 10.1016/j.crvi.2012.09.001 |
| URL: | http://www.sciencedirect.com/science/article/pii/S1631069112002272 |
| Parole Chiave: | Freshwater ecosystem; Decision trees; Artificial neural network; Support vector machines; Machine learning |
| Rivista: | COMPTES RENDUS BIOLOGIES |
| Appare nelle tipologie: | 03A-Articolo su Rivista |
File in questo prodotto:
| File | Descrizione | Tipologia | Licenza | |
|---|---|---|---|---|
| Tirelli_et_al_CRB_printed.pdf | 1 Ver. finale autore | Accesso riservato | Utenti riconosciuti Richiedi una copia | |
| crb_tirelli_2012.pdf | 1 Ver. finale autore | Accesso riservato | Utenti riconosciuti Richiedi una copia |
http://hdl.handle.net/2318/122442
Copyright © 2019