Comparative Study of Different Data Mining Techniques in Predicting Forest Fire in Lebanon and Mediterranean

TitreComparative Study of Different Data Mining Techniques in Predicting Forest Fire in Lebanon and Mediterranean
Type de publicationCommunications avec actes
Année de publication2016
Titre de la Conférence/colloqueProceedings of SAI Intelligent Systems Conference (IntelliSys) 2016
Titre des actes ou de la revue15
Numéro de sectionLecture Notes in Networks and Systems
Pagination747 - 762
Date de publication2016
Auteur(s)Hamadeh, N., Karouni A., Daya B. et Chauvet P.
Directeur(s)Bi, Y., Kapoor S. et Bhatia R.
Université, organismeSpringer International Publishing
Ville, PaysLondon, UK
Numéro ISBN978-3-319-56994-9
Résumé

Forest fire is one of the most complex phenomena which can cause great economic losses and make eco-environment seriously disordered. Forest fire has caused the loss of many green acres in Lebanon due to the lack of governmental policies in order to mange forest fires. This paper presents an overview of the exciting applications of data mining techniques in different fields. This study aims to predict forest fires in North Lebanon in order to reduce fire occurrence based on 4 meteorological parameters (Temperature, Humidity, Precipitation and Wind speed) using different data mining techniques: Neural networks, decision tree (J48), fuzzy logic, support vector machine (SVM) and linear discriminant analysis (LDA). A comparative study is then made to find the best performing technique tending to manage such a natural crisis. Decision tree (J48) recorded the best accuracy in forest fire prediction (97.8%).

DOI10.1007/978-3-319-56994-9_51