Utilize este identificador para referenciar este registo: https://hdl.handle.net/1822/8039

Registo completo
Campo DCValorIdioma
dc.contributor.authorCortez, Paulo-
dc.contributor.authorMorais, Aníbal de Jesus Raimundo-
dc.date.accessioned2008-08-29T18:44:14Z-
dc.date.available2008-08-29T18:44:14Z-
dc.date.issued2007-12-
dc.identifier.citationNEVES, José Maia ; SANTOS, Manuel Filipe ; MACHADO, José Manuel, eds. - “New trends in artificial intelligence : proceedings of the 13th Portuguese Conference on Artificial Intelligence (EPIA 2007), Guimarães, Portugal, 2007”. [Lisboa] : APPIA, 2007. ISBN 978-989-95618-0-9. p. 512-523.eng
dc.identifier.isbn978-989-95618-0-9-
dc.identifier.urihttps://hdl.handle.net/1822/8039-
dc.description.abstractForest fires are a major environmental issue, creating economical and ecological damage while endangering human lives. Fast detection is a key element for controlling such phenomenon. To achieve this, one alternative is to use automatic tools based on local sensors, such as provided by meteorological stations. In effect, meteorological conditions (e.g. temperature, wind) are known to influence forest fires and several fire indexes, such as the forest Fire Weather Index (FWI), use such data. In this work, we explore a DataMining (DM) approach to predict the burned area of forest fires. Five different DM techniques, e.g. Support Vector Machines (SVM) and Random Forests, and four distinct feature selection setups (using spatial, temporal, FWI components and weather attributes), were tested on recent real-world data collected from the northeast region of Portugal. The best configuration uses a SVM and four meteorological inputs (i.e. temperature, relative humidity, rain and wind) and it is capable of predicting the burned area of small fires, which are more frequent. Such knowledge is particularly useful for improving firefighting resource management (e.g. prioritizing targets for air tankers and ground crews).eng
dc.language.isoengeng
dc.publisherAssociação Portuguesa para a Inteligência Artificial (APPIA)eng
dc.rightsopenAccesseng
dc.subjectData mining applicationeng
dc.subjectFire scienceeng
dc.subjectRegressioneng
dc.subjectSupport vector machineseng
dc.titleA data mining approach to predict forest fires using meteorological dataeng
dc.typeconferencePapereng
dc.peerreviewedyeseng
Aparece nas coleções:CAlg - Artigos em livros de atas/Papers in proceedings
DSI - Engenharia da Programação e dos Sistemas Informáticos

Ficheiros deste registo:
Ficheiro Descrição TamanhoFormato 
fires.pdfMain article968,16 kBAdobe PDFVer/Abrir

Partilhe no FacebookPartilhe no TwitterPartilhe no DeliciousPartilhe no LinkedInPartilhe no DiggAdicionar ao Google BookmarksPartilhe no MySpacePartilhe no Orkut
Exporte no formato BibTex mendeley Exporte no formato Endnote Adicione ao seu ORCID