Using Knowledge Discovery to Enhance Classification Techniques for Detect Malaria-Infected Red Blood Cells

Malaria is one of the three most serious diseases worldwide, affecting millions each year, mainly in the tropics where the most serious illnesses are caused by Plasmodium falciparum. The aim of this research paper is to enhance the main machine-learning classification algorithms that used for malaria-infected red blood cells (MRBCs) and evaluation the classification model accuracy. This study uses knowledge discovery technique to analyses the blood smear images. The system that determines the computerized methods of image analysis generally involves three main phases. Firstly, data collection, pre-processing and feature extraction are conducted based on the characteristics of normal and MRBCs. Secondly, application knowledge discovery process to extracts high quality information of normal and MRBCs. Thirdly, using prediction model of classification machine learning algorithms to classify 1000 RBCs sample. After that, use ten-fold cross-validation to evaluation overfitting model and the confusion matrix to evaluate the performance of a classification model. The results indicate that the algorithms achieve high accuracy more than 92.3%. Also, obtain high prediction 90.8%, reliability 92% and ability to distinguish positive and negative classification model 93%. In addition, the reduction in time build the model was very clearly, 13.6 second and 5.8 times faster respectively.