A Ghulam Assessment of Performance of Machine Learning Classification Techniques for Monkey Pox Disease Detection

Monkey Pox Disease Detection

Abstract

The World Health Organization designated monkeypox as a disease of public health importance. The United States and the rest of the world are experiencing an outbreak of monkeypox. The damage brought on by this pandemic can be reduced if instances can be predicted in advance and precautions that are required can be taken right away.  Seven distinct classification algorithms are employed for the categorization of monkey pox disease such as LR, DTC, KNN, RF, NB, XGB, QDA classification classifiers. Four evaluation measures were employed to compute the classification accuracy in this study. The four criteria used to evaluate the seven classification algorithms are F-Score, Accuracy, Precision, and Recall. The analysis was based on experimental study demonstrates that the Extreme Gradient Boosting algorithm (XGBoost) outperforms other classification algorithms and achieved a superior accuracy rate of 71%. In order to train eight different models for precise prediction, this paper took a variety of physiological factors and used machine learning algorithms like LR, DT, K-N, RF, NB, XGB, SGD and QDA Classification. The algorithm with the highest accuracy for this task was XGBoost, which had a result of about 70%.