MALARIA DISEASE DETECTION SYSTEM USING CONVOLUTIONAL NEURAL NETWORK
Abstract
Malaria remains a major global health burden, particularly in tropical and subtropical regions, with traditional microscopic diagnosis being time-consuming, labor-intensive, and prone to human error. This study proposes a Malaria Disease Detection System based on Convolutional Neural Networks (CNN) for automated classification of parasitized and uninfected red blood cells from thin blood smear images. Using the publicly available NIH Malaria Cell Images Dataset (27,558 images), the model was trained and evaluated, achieving high performance metrics (e.g., accuracy exceeding 95-99% in line with state-of-the-art benchmarks). The system includes data preprocessing, CNN architecture design, and evaluation using metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. Results demonstrate the potential of deep learning for scalable, accurate malaria diagnostics, with discussions on limitations, real-world deployment, and future enhancements like species-specific detection or mobile integration.
Full-Text Access Notice
In accordance with the NERD Policy on promoting peer-reviewed publication, public access to the full text of a project, thesis or dissertation is restricted for three years, allowing the author and supervisors sufficient time to pursue peer-reviewed publication.
During this period, researchers with legitimate academic or research purposes may request authorisation directly from the author to enable NERD to release the indexed full texts of the work using the form below.