An Experimental Analysis of Machine Learning Classification Algorithms on Biomedical Data

Abstract

Enormous growth of data in biomedical engineering domain has posed a big challenge for data analysis and processing. This massive volume of biomedical data leverage leads to a great challenge. To address this issue, this paper compares the performance measures of various classification algorithms of machine learning on biomedical data. The various classification algorithms such as Decision Tree (DT), K-Nearest Neighbors (KNN), Naive Bayes (NB), Linear Support Vector Machine (L-SVM), Radial Basis Function Support Vector Machine (RBF-SVM), Polynomial Support Vector Machine (P-SVM), Random Forest (RF), and Adaboost are used for classification process to measure the classification accuracy with 14 number of biomedical datasets. It is observed that the nature of dataset has very strong impact on the performance of the classifiers. The performance of all the aforesaid classification algorithms are analyzed on 14 biomedical datasets and observed that the Adaboost classifier outperforms than rest of the classifiers.