Resumen de Classification Of Malaria Parasite Species Based On Thin Blood Smears Using Multilayer Perceptron Network

Noorhidayati Abu Seman, Nor Ashidi Mat Isa, Lim-Chia Li, Zeehaida Mohamed, Umi Kalthum Ngah, Kamal Zuhairi Zamli

• This paper discusses the application of the MLP network to classify the malaria parasite into three species, namely Plasmodium falciparum, Plasmodium vivax and Plasmodium malariae. Six features (i.e. size of RBC infected per size of normal RBC, shape of parasite, number of chromatin, number of parasite per RBC, texture of RBC and location chromatin of parasite) from thin blood smear were used as input data. In order to determine the applicability of the MLP network, three different training algorithms were employed to train the MLP networks. In this study, the MLP network trained using back propagation algorithm produced the best performance with 89.80% accuracy as compared to LevenbergMarquardt and Bayesian Rule algorithms. The result significantly demonstrates the suitability of the MLP network for classifying the malaria parasite.