1 Department of Computer science, Nasarawa State University Keffi, Nigeria.
2 Department of Computer Science, Federal University of Technology, Owerri, Nigeria.
Review Article
World Journal of Advanced Research and Reviews, 2022, 16(03), 205-218
Article DOI: 10.30574/wjarr.2022.16.3.1304
Received on 17 October 2022; revised on 29 November 2022; accepted on 02 December 2022
Traditionally to diagnose malaria and compute the parasitemia, a microscope is being used, which involves the use of thick and thin blood smears. However, the efficiency in examining the blood smear depends on the expertise of the laboratory technician in classifying the blood smear using the natural eye, through observation on the microscope as this may produce inaccurate reports due to human errors and offer less classification accuracy for novice laboratory technicians with less experience. In order to carry out a highly, accurate diagnosis of malaria. This paper presents a mobile malaria disease detection system based on Convolutional Neural Network (CNN), a class of Deep Learning (DL) algorithm with end-to-end feature extraction and classification. It is highly scalable and offers superior results in image classification problems, this would be used in training a classification model and deploying the model in a Mobile App. The Mobile App would then be used to diagnose malaria by using the device camera to take photo of patient blood smears for the model to classify, and give result output. Structured System Analysis and Design Methodology (SSADM) was adopted in the design of the research. The Malaria diagnosis system was developed using the JAVA Mobile Edition (ME) programming language and Python programming language to train the model and deployed in the developed software. The developed software meets the objectives of the system.
Malaria Disease Detection; Convolutional Neural Network; Machine Learning; Deep Learning
Preview Article PDF
Osuji Collins Ifeanyi, Binyamin A. Ajayi and Muhammad Umar Abdullahi. Malaria disease detection system based on convolutional neural network (CNN). World Journal of Advanced Research and Reviews, 2022, 16(3), 205-218. Article DOI: https://doi.org/10.30574/wjarr.2022.16.3.1304