Classification of Malaria Parasitized and Uninfected Images Using Machine Learning Approach

Human health is an important concern in the current scenario. Different diseases have adverse effect on human society. Malaria parasite is one of them. So, it is very much essential for the classification of malaria parasitized and uninfected cases at the earliest so that preventive measures can be taken accordingly. Machine Learning (ML) plays an important role for the identification, classification as well as analysis of different medical images which can help in accelerating the diagnosis process. In this work, an attempt has been made for the classification of malaria parasitized and uninfected cases from the analysis of different images using ML based methods. In this paper, the ML based methods such as k-Nearest Neighbor (k-NN), Neural Network (NN), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), Logistic Regression (LR), AdaBoost (AB) and Naive Bayes (NB) are used for such classification. The methods are evaluated using Classification Accuracy (CA) performance parameter. This work is carried out using Orange 3.26.0.