| Popis: |
With the rapid development of IoT technology, medical IoT is one of the current research focuses and hotspots. In the practical application of medical IoT, achieving accurate localization and effective data fusion is conducive to improving the operational efficiency of medical IoT and reducing the power consumption of the network. Therefore, this paper uses SVM and KNN algorithms to improve the localization accuracy, and proposes an event-driven cluster-tree data fusion algorithm DFC based on the special characteristics of data in medical IoT.The DFC algorithm uses a combined cluster-tree topology to dynamically partition clusters and decide the decision range of the corresponding cluster based on the severity of the event, and then constructs the data fusion within the cluster from the current cluster head The data propagation along the fusion tree can improve the accuracy of the data and extend the lifetime of the network. In this paper, we analyze the fusion delay problem in the network and propose a minimum fusion delay method by calculating the fusion waiting time of nodes. Experiments demonstrate that the DFC algorithm has better accuracy and fusion through machine learning, an improvement of the medical IoT. This is of great importance in real-life applications |
