SIMULATION OF DIFFERENT SPEED CONTROL TECHNIQUES OF DC MOTOR (SHUNT, SERIES, AND COMPOUND) USING MATLAB

Abstract

Current healthcare models find it difficult to handle the volume and complexity of data from wearables and IoT devices, despite advancements in AI and cloud computing. Proactive treatment is limited by the fact that traditional prediction models frequently lack the robustness required for precise, real-time illness forecasting. Furthermore, there is currently a lack of development in the use of optimisation approaches to improve model performance in healthcare AI applications. By fusing cloud-based infrastructure with optimization-driven neural networks, the investigation fills a major gap in the field and enables more efficient, rapid
illness monitoring and prediction. Effective illness prediction models that can handle massive amounts of real-time data are
lacking in modern healthcare systems. The accuracy of disease forecasting is impacted by current AI systems in healthcare, that do not fully utilise optimisation techniques. A cloud- based architecture is required in order to provide ongoing observation and the extraction of predictive insights from patient data. Timely disease intervention and real-time patient care are hampered by the incomplete incorporation of IoT-generated data into predictive models