Enhanced deep convolutional neural network for malarial parasite classification

The standard method for examining malarial disease is performed through the examination of blood smears under the microscope for parasite-infected red blood cells and this is done by qualified technicians. The inadequacy of this traditional method is enhanced using advanced computer vision and deep learning methods to automatically classify the malarial parasite from the microscope’s blood smear image as infected or uninfected. The primary challenge lies in the classification of malarial parasitizes from blood smear data which decide the overall accuracy. The proposed work uses a deep convolutional neural network (DCNN) to detect the malarial parasitizes from smear blood cell images. The primary focus of the work is to (i) compare the validation loss and accuracy by tuning the hyper-parameters in order to classify the images and (ii) compute the Kappa Coefficient and Matthew’s correlation coefficient. The efficiency of the proposed model is analyzed by comparing the optimizers (Adam and Adagrad) at various epochs. The overall accuracy of the proposed DCNN model reached 98.9% compared to the existing state-of-the-art models by focusing on hyper-parameter tuning.