Identification and Classification for Diagnosis of Malaria Disease using Blood Cell Images

Abstract

Machine Learning is a subfield of artificial intelligence that focuses on developing intelligent algorithms capable of learning from available data without requiring constant programming, enabling them to adapt to different environments based on current scenarios. These algorithms are crucial in making intelligent decisions and conducting thorough analyses to uncover intricate patterns concealed within the data. This study used multiple machine-learning classification algorithms to analyze patients' data based explicitly on input images containing parasite-infected and uninfected Malaria samples. AI techniques were utilised to measure the presence of parasites in the images. The image classification system was designed to accurately identify malaria parasites in blood images by generating image features related to color, texture, and cell and parasite geometry. A classifier based on SVM (Support Vector Machine) provided by Weka was employed to differentiate between parasite-infected and non-infected blood images. Through extensive experimentation, it was determined that SVM strategies exhibited significant relevance, achieving a cross-validation accuracy of 99.4% in the basic diagnosis of malaria fever. This finding holds great potential in assisting clinicians with accurate infection diagnoses.