Transfer Learning Method for Malaria Identification
Cecilia Audrey Herli, Daniel Zerge Wijaya, Hansen, Michelle Angela, Zakaria Berlam Pragusma, Ajeng Wulandari, Maria Susan Anggreainy · 2023
Malaria is a severe disease caused by parasites of the genus Plasmodium, which are transmitted to humans through the bite of an infected female Anopheles mosquito. Symptoms of malaria begin to appear at least within 10 to 15 days. If malaria is not treated immediately, it is feared that it will cause respiratory problems, shortness of breath, and death. To avoid the occurrence of these events, the idea arose to create an AI (Artificial Intelligence) project that can recognize the presence of malaria parasites in blood cells. Thus, the main objective of this project is to find out how to create a Machine Learning model that can efficiently identify malaria parasites in the human body. The AI project uses CNN (Convolutional Neural network) as an algorithm to recognize the presence or absence of parasites in blood cell images that will be inputted by the user. Process of implementing CNN, using VGG19 which is an advanced CNN that has pre-trained layers and a good understanding of describing an image, both the shape, color, and structure of the image. After implementing the Transfer Learning algorithm on the dataset, the result is a Transfer Learning algorithm that can detect the presence of Malaria parasites in blood cells with an accuracy rate of 92 percent a specificity of 95 percent, and a sensitivity of 89 percent. The accuracy can still increase depending on the diversity of the data provided. The more often we train and input test data as train data, the accuracy of AI will also increase.