Human Malaria Detection using Random Forest Tree

EasyChair Preprint 3173

Abstract

Malaria is a mosquito-borne infection brought about by parasites of the genus Plasmodium. Due to the difficulty of identifying low-abundance parasites from blood serum, early diagnosis of malaria is daunting. Malaria treatment is tested by a microscope of patient's stressed bloodstain. The blood sample to be examined is put in a transparent glass slide under a microscope to count the number of RBC contaminated concentrations. To view the slide with extreme visual focus, an intended microscopist is required. This entire process is time-consuming, exhausted and less accurate. Under the roof of this paper, we build a fully automatic detection system to count the plasmodium parasites in blood Smear. This system is based on an algorithm for machine learning against traditional thin-blood smear analysis, which has more sensitivity and specificity. This automated system is simple, making it ideal even with low levels of parasites for ultra-fast and accurate detection. The suggested technique utilizes collected photographs of patients to assess the malaria disease without staining the blood or specialist required.

Keyphrases: Plasmodium, RBC, blood smear, microscopy

@booklet{EasyChair:3173,
  author    = {Chandan Kumar and Satyam Saha and Atishay Jain},
  title     = {Human Malaria Detection using Random Forest Tree},
  howpublished = {EasyChair Preprint 3173},
  year      = {EasyChair, 2020}}