Using data monitoring algorithms to physiological indicators in motion based on Internet of Things in smart city

Abstract

This article discusses the monitoring of physiological indicators during exercise, combined with the data fusion algorithm of the smart city Internet of Things health. We use the hash value of the tuple key to the corresponding data block of the node, use the data block record to obtain the response of the target node, and output the data tuple. It is used as a measure of the load balance of health data streams to determine whether load migration is needed and to determine the way and amount of migration tasks to make migration decisions. The simulation experiments show that the method has good computational performance and dynamic load balancing. A series of mean arterial pressure and heart rate of patients and non-stationary health data, and a series of blood pressure and heart rate of health individuals in different postures are selected to perform experiments to analyze the transfer function and power spectra in the model, validating that the model can be used to reveal the changes associated with severe systemic response syndrome (SIRS), providing a hypothesis for the decomposition of autoregulation of physiological control under health and disease conditions.