Design of inception ResNet V2 for detecting malarial infection using the cell image captured from microscopic slide

Abstract

ABSTRACT Over the past decades, malarial infection is considered a dreadful disease which ruins the lives of millions of people all over the globe. Several research works were developed based on machine learning algorithms to categorize the malarial infected person. However effective prediction with precise results is not attained in conventional approaches. For accurate prediction of malarial transmission deep learning technology is designed in this proposed model. This proposed design utilized inception ResNet V2 for the prediction of malarial-infected individuals. Before disease prediction, certain pre-processing techniques such as noise removal, contrast enhancement and segmentation are used to minimize the error rate during the classification process. The function of the proposed model is evaluated using metrics such as accuracy, recall, precision, etc. The simulation analysis shows that the proposed method obtains 0.98% accuracy, 0.02% error, precision is 0.92%, specificity is 0.94% so on. Thus the designed model predicted the malarial disease effectively.