MALARIA DIAGNOSIS USING DOUBLE HIDDEN LAYER EXTREME LEARNING MACHINE ALGORITHM WITH CNN FEATURE EXTRACTION AND PARASITE INFLATOR

Abstract

Millions experience the ill effects of malaria, which kills many thousands yearly. Viable illness treatment and control need ideal and exact finding. Antigen and microscopy testing are wrong, tedious, and costly, particularly in asset obliged regions. Because of these issues, this exploration presents a clever intestinal sickness expectation technique utilizing the Extreme Learning Machine (ELM)
calculation. Red Blood Cell (RBC) pictures are utilized to analyze rapidly and precisely utilizing CNN, ELM, and DELM classifiers. The
recommended approach tends to the critical requirement for solid and speedy early malaria anticipation framework. This work benefits malaria inclined individuals, particularly those in developing nations with deficient medical services access. This exploration further develops medical care, mortality, and general wellbeing in malaria endemic regions by conveying a quick, accurate, and reasonable demonstrative strategy.