Classification System of Malaria Disease with Hu Moment Invariant and Support Vector Machines

Abstract

Malaria is an infectious disease caused by a plasmodium parasite transmitted by the female Anopheles mosquito. According to the World Health Organization (WHO) in 2020 there are an estimated 241 million cases of malaria worldwide with an estimated global death stood at 627. 000. The standard method of malaria diagnosis is by conducting microscopic examination or laboratory test and Rapid Diagnostic Test (RDT). Laboratory tests have a high risk of human error whereas RDT has weaknesses in temperature sensitivity, genetic variation, and antigen resistance in the bloodstream. This research offers a classification system of malaria disease by applying the Hu moment invariant and Support vector Machine (SVM) method with 3 types of malaria parasitic objects, namely falciparum, Malaria and vivax. The classification system uses 3 SVM models, namely linear SVM, polynomial SVM and Gaussian SVM with the Falciparum class as a positive data and malaria and vivax as negative data. The best classification outcome is on the Gaussian SVM model with 96.67% sensitivity and 90% specificity. The mean accuracy of the Gaussian SVM model with a 5-fold cross Validation 90 image sample which is divided into 3 classes is 86.66%.