Abstract

Dengue is that the most widespread vector-borne illness worldwide. Timely identification and treatment of dengue fever is that the main objective of medical professionals to decrease mortality rates. During this paper, we have a tendency to propose AN autonomous cycle that integrates information analysis tasks to support decision-making within the clinical management of dengue fever. Notably, the autonomous cycle supports dengue fever identification and treatment. The projected system was designed exploitation machine learning techniques for classification tasks (artificial neural networks and support vector machines) and biological process techniques (a genetic algorithm) for prescription tasks (treatment). The system was quantitatively evaluated exploitation dengue-patient datasets rumored by health care establishments. Our system was compared with previous works exploitation qualitative criteria. The projected system has the flexibility to classify a patient's clinical image and advocate the simplest treatment possibility specifically, the classification of dengue fever was finished ninety eight accuracy and a genetic algorithmic rule recommends treatment choices for specific patients. Finally, our system is versatile and simply adjustable, which can enable the addition of latest tasks for dengue fever analysis.