Search for collections on Undip Repository

Identification of Plasmodium Falciparum Development Phase in Malaria Infected Red Blood Cells using Adaptive Color Segmentation and Decision Tree based Classification

Kusworo, Adi (2015) Identification of Plasmodium Falciparum Development Phase in Malaria Infected Red Blood Cells using Adaptive Color Segmentation and Decision Tree based Classification. International Journal of Applied Engineering Research, 10 (2). pp. 4043-4055. ISSN 0973-4562

[img] PDF
2015-Identification of Plasmodium Falciparum Development Phase in Malaria Infected Red Blood Cells using Adaptive Color Segmentation and Decision Tree based Classification.pdf - Published Version

Download (429kB)

Abstract

Malaria is a medical emergency that must be treated immediately at this time because it has been infecting millions of people in 90 countries every year. Malaria is caused by a parasite that infects red blood cells transmitted through the bite of Anopheles. One species of plasmodium causing malaria is plasmodium falciparum. This type of plasmodium can lead to malaria tertian which is a malignant malaria type and threatening the life of its sufferer. This study aims to design a system capable of identifying the development phase of plasmodium falciparum in red blood cells with adaptive color segmentation and decision tree based classification. Color segmentation process in this study is done by converting the original image color space based on the color components of RGB (Red, Green, Blue) to HSV color space (Hue, Saturation, Value) then thresholding against Saturation component. The used morphological parameters to distinguish the type of plasmodium falciparum development phase are the area ratio and eccentricity. While the classification process is performed using decision tree algorithm results in 87.67% of accuracy.

Item Type: Article
Subjects: Undip Formal Documents
Depositing User: fsm fsm fsm
Date Deposited: 31 Jan 2020 03:40
Last Modified: 31 Jan 2020 03:40
URI: https://eprints2.undip.ac.id/id/eprint/381

Actions (login required)

View Item View Item