Random Forest RF is a successful technique of ensemble prediction that uses the majority voting or an average depending on the combination. However, it is clear that each tree in a random forest can have different contribution to the treatment of some instance. In this paper, we show that the prediction performance of RF's can still be improved by replacing the GINI index with another index (twoing or deviance). Our experiments also indicate that weighted voting gives better results compared to the majority vote.
Before the routine anesthesia, an airway examination must be performed during the pre-anesthetic examination for all patients who need a surgical operation in order to decide whether the tracheal intubation is easy or hard. In the field of anesthesia and intensive care, many works have been performed in order to reduce as much as possible the anesthetic risks and the mortality rate as well as to provide assistance to the Doctors Specialized in Anesthesia (DSA's).In this work, we suggest a system of Computer Aided Diagnosis for the DSA's during the anesthetic examination. This system was conceived to determine whether the patient's tracheal intubation is easy or hard. For this we tested four different classifiers which are the Multi-Layer Perceptron (MLP), the C4.5 decision tree, the Support Vector Machine (SVM) and the K-Nearest Neighbors algorithm (KNN) applied on a new database which was collected locally.We obtained promising results which are a proof of the reliability and the coherence of our database.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.