Detection Of Malaria Using Convolutional Neural Network With Visual Geomentry Group--16

Abstract

Through the bites of female Anopheles mosquitoes that have been infected, people are exposed to the dangerous and potentially fatal disease known as malaria. Tropical and subtropical areas, notably in sub-Saharan Africa, are where the disease is most common. Malaria usually manifests as a fever, chills, and flu-like symptoms, but in more serious cases, it can cause organ failure, anaemia, and even death. In order to avoid severe malaria cases, early detection and fast treatment are essential. overview of several malaria detection techniques, including microscopy, rapid diagnostic tests (RDTs), and molecular techniques like PCR and loop-mediated isothermal amplification (LAMP). In the end, a quick and correct diagnosis of malaria is crucial to lessening its impact and enhancing global health results. detection of malaria,In the importance of malaria as a significant global health problem and the potential for deep learning algorithms to increase diagnostic precision will certainly be highlighted by the use of deep learning. The study would explain how a sizable collection of blood smear images from patients with and without malaria, divided into training, validation, and testing sets, was used. On the training set and the testing set, a deep learning model—such as a convolutional neural network (CNN) or a recurrent neural network (RNN)—was trained. A convolutional neural network (CNN) with VGG16 architecture would be used to identify malaria, which would likely draw attention to the disease's importance as a widespread and fatal condition as well as the possibility of artificial intelligence (AI) to help with its identification.