An Improved Ensemble Classifier Model to Combat the Escalating Threat of Viral Infections

Résumé fourni par la source

The effect of contagious viral infections spread has led health authorities and organizations to identify dynamic practices to perceive infected people at threat. Recent AI approaches using scientific modeling are enlightening virus investigation and diagnosis. The artificial intelligence system is useful for discovering viruses affecting patients by efficient techniques using vital signs and symptoms. Respiration rate, C-reactive protein, heart parameters, and temperature parameters were used to productively identify persons at acute risk for the virus using neural networks, deep learning, and fuzzy clustering methods. AI-based algorithms determine the ability to improve effective approaches for identifying and classifying infected populations at mild, moderate, and acute risk. This triage is essential and part of the procedure, even in the instance of up-and-coming viral infectious diseases, where efforts must be highlighted. Artificial intelligence-driven approaches provide better monitoring and management of viral infection. Our research proposes an efficient and improved ensemble classifier model to combat the wide threat of viral infections. The outcome of the proposed model for analyzing and classifying the dengue viral infections is better than prevailing approaches Decision Tree Model (DTM), Density base Spatial clustering model (HDPM), etc.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.