Efficient Feature Selection and ML Algorithm for Accurate Diagnostics

Abstract

Machine learning algorithms have been deployed in numerous optimization, prediction and classification problems. This has endeared them for application in fields such as computer networks and medical diagnosis. Although these machine learning algorithms achieve convincing results in these fields, they face numerous challenges when deployed on imbalanced dataset. Consequently, these algorithms are often biased towards majority class, hence unable to generalize the learning process. In addition, they are unable to effectively deal with high-dimensional datasets. Moreover, the utilization of conventional feature selection techniques from a dataset based on attribute significance render them ineffective for majority of the diagnosis applications. In this paper, feature selection is executed using the more effective Neighbour Components Analysis (NCA). During the classification process, an ensemble classifier comprising of K-Nearest Neighbours (KNN), Naive Bayes (NB), Decision Tree (DT) and Support Vector Machine (SVM) is built, trained and tested. Finally, cross validation is carried out to evaluate the developed ensemble model. The results shows that the proposed classifier has the best performance in terms of precision, recall, F-measure and classification accuracy.