A Novel Data Augmentation Convolutional Neural Network for Detecting Malaria Parasite in Blood Smear Images

Malaria fever is a potentially fatal disease caused by the Plasmodium parasite. Identifying parasites in blood smear images can help diagnose malaria rapidly and precisely. According to World Health Organization (WHO), there were 241 million cases 627 000 deaths worldwide 2020, while 95% of 96% occurred Africa. Also Africa, children that are less than five years old accounted for an estimated 80% all deaths. To address menace malaria, this paper proposes novel deep learning model, called data augmentation convolutional neural network (DACNN), trained reinforcement tackle problem. The performance proposed DACNN model compared with CNN directed acyclic graph (DAGCNN) models. Results show outperforms previous studies processing classification images. It achieved 94.79% accuracy sample balanced class dataset obtained from Kaggle dataset. serve as effective tool detection