Modified Binary Dragonfly Algorithm for Feature Selection in Human Papillomavirus-Mediated Disease Treatment

Abstract

Diseased caused through the rapid mediation of Human Papillomavirus (HPV) have surged in the recent decades. While there are a large amount of treatment methods, medical data is often voluminous, high dimensional and often has redundancy which make selection of a particular method difficult. Wrapper feature selection methods aim to extract a subset of features to improve computability as well as classification accuracy. To address this, we propose a modification to a relatively new evolutionary computation technique, the Binary Dragonfly algorithm (BDFA), by incorporating a penalty function for optimal feature selection. This wrapper based method using BDFA and Random forest classifier is employed on two treatment methods, Immunotherapy and Cryotherapy, showing an increase in both classification accuracy as well as feature reduction as compared to fuzzy rule based systems, genetic algorithms and random forest classifiers