Implementation of Combined Machine Learning with the Big Data Model in IoMT Systems for the Prediction of Network Resource Consumption and Improving the Data Delivery

In recent years, health applications based on the internet of medical things have exploded in popularity in smart cities (IoMT). Many real-time systems help both patients and professionals by allowing remote data access and appropriate responses. The major research problems include making timely medical judgments and efficiently managing massive data utilising IoT-based resources. Furthermore, in many proposed solutions, the dispersed nature of data processing openly raises the risk of information leakage and compromises network integrity. Medical sensors are burdened by such solutions, which reduce the stability of real-time transmission systems. As a result, this study provides a machine-learning approach with SDN-enabled security to forecast network resource usage and enhance sensor data delivery. With a low administration cost, the software define network (SDN) design allows the network to resist dangers among installed sensors. It provides an unsupervised machine learning approach that reduces IoT network communication overheads and uses dynamic measurements to anticipate link status and refines its tactics utilising SDN architecture. Finally, the SDN controller employs a security mechanism to efficiently regulate the consumption of IoT nodes while also protecting them against unidentified events. When the number of nodes and data production rate varies, the suggested approach enhances network speed. As a result, to organise the nodes in a cluster, the suggested model uses an iterative centroid technique. By balancing network demand via durable connections, the multihop transmission technique for routing IoT data improves speed while simultaneously lowering the energy hole problem.