Open AccessPrediction of Forest Fire using Hybrid SOM-AdaBoost Method
Author(s) -
Dedi Rosadi,
Widyastuti Andriyani,
Deasy Arisanty,
Dina Agustina
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2123/1/012030
Subject(s) - adaboost , boosting (machine learning) , cluster analysis , computer science , artificial intelligence , pattern recognition (psychology) , machine learning , data mining , support vector machine
Prediction of the occurrences of forest fire has become interest of various research studies for instances, it is found that the hybrid method based on clustering using fuzzy c-means before doing the classification approach will improve the performance of prediction than directly apply the classification approach. In this study, we will consider the new hybrid approach between clustering based on Self Organizing Map (SOM) approach and classification using Boosting (AdaBoost) approach. Our empirical analysis shows using the same public data set, which has been used in several previous studies, the performance of hybrid SOM-AdaBoost will outperforms other methods in literatures.