Neutrosophic Sets and Systems
Abstract
This study is presented to investigate the influence of the neutrosophic (NS) domain on the performance of the most common machine learning (ML) models. Specifically, it evaluates the effectiveness of Random Forest (RF), Extra Trees (ET), K-Neighbors (KNN), Gaussian Naive Bayes (GaussianNB), and Decision Tree (DT) classifiers in detecting oral diseases. The NS domain divides any image into three membership components: falsity (��), indeterminacy (��) and truth (��), where T denotes the degree to which each pixel in an image is a member of a particular class or category, F denotes the degree to which the pixel is not a member of that class or category and I denotes the degree of uncertainty or indeterminacy. This domain is herein employed to divide the images into three datasets (T, I, and F). Those three datasets, in addition to the original dataset, one by one, are divided into training and testing datasets with a splitting ratio of 80% and 20%, respectively. Afterwards, the five studied ML models are trained on the training dataset before being assessed on the testing dataset to show their ability to generalize using four performance indicators, such as precision, accuracy, F1-score and recall. According to the experimental results, the I-domain, when compared to the other domains, could considerably increase the performance of four of the five studied ML models, meaning that the NS domain might improve the ML models' performance in categorizing oral diseases more correctly. Among all studied models, the RF classifier with the I-domain has the highest classification accuracy, indicating that it is a strong alternative for oral disease classification.
Recommended Citation
M. Elezmazy, Ibrahim and Doaa El-Shahat. "Neutrosophic-Supported Machine Learning Models for Oral Disease Classification." Neutrosophic Sets and Systems 79, 1 (2025). https://digitalrepository.unm.edu/nss_journal/vol79/iss1/39
