Design of a Malaria Parasite Detection Model in Microscopic Images of Blood Cells using the Convolutional Neural Network Method

Nurhaeni, Nurhaeni and Ahmad, Hidayat and Septyan, Eka Prastya and Fadhiyah, Noor Anisa (2024) Design of a Malaria Parasite Detection Model in Microscopic Images of Blood Cells using the Convolutional Neural Network Method. [Karya Dosen UNISM]

Text nurhaeni-2024-ijca-924165.pdf Download (350kB)

Abstract

The malaria examination technique through a microscope is the most commonly used examination in health facilities. However, microscopic examination techniques require special skills and take quite a long time. This research aims to develop a malaria parasite detection system model in blood cell images using deep learning technology to increase the accuracy and speed of detection with the Convolutional Neural Network (CNN) algorithm. This research was carried out in several stages consisting of data collection, image preprocessing, dividing training data and validation data, creating a model using CNN, and evaluating the model. A CNN model was created to classify blood cell images into two classes, namely infected and uninfected. The dataset used as a reference in forming a detection system model uses blood cell images from the open-source Kaggle, totaling 11,312 images. The CNN model evaluation results obtained an accuracy value of 97.17% in detecting blood cell images. These results show that the CNN model created can be used to detect malaria parasites using blood cell images.

Actions (login required)

View Item