Discretizing environmental data for learning Bayesian-networkclassifiers
tFor predicting the presence of different bird species in Andalusia from land-use data, we compare the performances of Bayesian-network classifiers and logistic-regression models. In our study, both well balanced and less balanced data sets are used, and models are learned from both the original con...
| Main Authors: | , , |
|---|---|
| Format: | info:eu-repo/semantics/article |
| Language: | English |
| Published: |
Elsevier
2024
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10835/15031 |
| _version_ | 1789406342012731392 |
|---|---|
| author | Fernández Ropero, Rosa María Renooij, Siljia van der Gaag, Linda C. |
| author_facet | Fernández Ropero, Rosa María Renooij, Siljia van der Gaag, Linda C. |
| author_sort | Fernández Ropero, Rosa María |
| collection | DSpace |
| description | tFor predicting the presence of different bird species in Andalusia from land-use data, we compare the performances of Bayesian-network classifiers and logistic-regression models. In our study, both well balanced and less balanced data sets are used, and models are learned from both the original continuous data and from the data after discretization. For the latter purpose, four different discretization methods, called Equal Frequency, Equal Width, Chi-Merge and MDLP, are compared. The experimental results from our species data sets suggest that the simple Naive Bayesian classifiers are preferable to logistic-regression models and that the relatively unknown Chi-Merge method is the preferred method for discretizing these environmental data. |
| format | info:eu-repo/semantics/article |
| id | oai:repositorio.ual.es:10835-15031 |
| institution | Universidad de Cuenca |
| language | English |
| publishDate | 2024 |
| publisher | Elsevier |
| record_format | dspace |
| spelling | oai:repositorio.ual.es:10835-150312024-01-10T08:38:54Z Discretizing environmental data for learning Bayesian-networkclassifiers Fernández Ropero, Rosa María Renooij, Siljia van der Gaag, Linda C. Species distribution models Bayesian-network classifiers Logistic-regression models Discretization methods tFor predicting the presence of different bird species in Andalusia from land-use data, we compare the performances of Bayesian-network classifiers and logistic-regression models. In our study, both well balanced and less balanced data sets are used, and models are learned from both the original continuous data and from the data after discretization. For the latter purpose, four different discretization methods, called Equal Frequency, Equal Width, Chi-Merge and MDLP, are compared. The experimental results from our species data sets suggest that the simple Naive Bayesian classifiers are preferable to logistic-regression models and that the relatively unknown Chi-Merge method is the preferred method for discretizing these environmental data. 2024-01-10T08:38:53Z 2024-01-10T08:38:53Z 2018 info:eu-repo/semantics/article R.F. Ropero, S. Renooij, L.C. van Der Gaag. Discretizing environmental data for learning Bayesian-networkclassifiers. Ecological Modelling, 2018, 368, pag. 391-403 http://hdl.handle.net/10835/15031 en https://www.sciencedirect.com/science/article/pii/S0304380016308377 Attribution-NonCommercial-NoDerivatives 4.0 Internacional http://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess Elsevier |
| spellingShingle | Species distribution models Bayesian-network classifiers Logistic-regression models Discretization methods Fernández Ropero, Rosa María Renooij, Siljia van der Gaag, Linda C. Discretizing environmental data for learning Bayesian-networkclassifiers |
| title | Discretizing environmental data for learning Bayesian-networkclassifiers |
| title_full | Discretizing environmental data for learning Bayesian-networkclassifiers |
| title_fullStr | Discretizing environmental data for learning Bayesian-networkclassifiers |
| title_full_unstemmed | Discretizing environmental data for learning Bayesian-networkclassifiers |
| title_short | Discretizing environmental data for learning Bayesian-networkclassifiers |
| title_sort | discretizing environmental data for learning bayesian-networkclassifiers |
| topic | Species distribution models Bayesian-network classifiers Logistic-regression models Discretization methods |
| url | http://hdl.handle.net/10835/15031 |
| work_keys_str_mv | AT fernandezroperorosamaria discretizingenvironmentaldataforlearningbayesiannetworkclassifiers AT renooijsiljia discretizingenvironmentaldataforlearningbayesiannetworkclassifiers AT vandergaaglindac discretizingenvironmentaldataforlearningbayesiannetworkclassifiers |