Performance Analysis of Color Cascading Framework on Two Different Classifiers in Malaria Detection

Abstract

Malaria, as a dangerous disease globally, can be reduced its number of victims by finding a method of infection detection that is fast and reliable. Computer-based detection methods make it easier to identify the presence of plasmodium in blood smear images. This kind of methods is suitable for use in locations far from the availability of health experts. This study explores the use of two methods of machine learning on Cascading Color Framework, ie Backpropagation Neural Network and Support Vector Machine. Both methods were used as classifier in detecting malaria infection. From the experimental results it was found that Cascading Color Framework improved the classifier performance for both in Support Vector Machine and Backpropagation Neural Network.