Adaptation of the random forest method
Mourad Azhari, Altaf Alaoui, Zakia Achraoui, Badia Ettaki, Jamal Zerouaoui · Proceedings of the 4th International Conference on Smart City Applications · 2019
Random Forest Algorithm is a method of machine learning that refers to train individual classifiers and aggregates their predictors. It is specifically reserved to decision tree classifiers and used for classification and regression problems in several areas. Beyond the choice of the most appropriate algorithm to the study context and the database criteria, another challenge can be faced on the input parameters of each algorithm, which can have a significant influence on the result performance. In the context of the pulsar detection candidates, this work aims to study the influence of the parameters on the result performance and suggest an optimum scenario. We explore our result experiments using the R language.