An efficient cloud-based healthcare services paradigm for chronic kidney disease prediction application using boosted support vector machine

Cloud computing is the on-demand access to computer resources such as applications, servers, data storage, development tools, networking capabilities, and other resources that are held in a remote data center maintained by a cloud services provider(CSP) and accessible over the internet. The limited resources and higher time consumption are the major issues faced by cloud users. The appropriate selection of virtual machines (VMs) is used to maximize cloud resource usage and reduce task execution time for the clients (patients, physicians, etc.). In this article, we have introduced an efficient cloud-based healthcare services paradigm (HCS). The opposition-based Laplacian equilibrium optimizer (O-LEO) algorithm is used to select optimal VMs in which the maximization of resource utilization and minimization of task execution time is performed. Additionally, the boosted support vector machine (SVM) effectively predicts chronic kidney disease (CKD) thereby ensuring better prediction results. The CloudSim platform is used as the implementation platform of the proposed method. The overall time taken by the O-LEO-based CloudSim is less than the standard Cloud Sim model to create three cloudlets which improve the system efficiency by 6%. When compared with the existing techniques, both the O-LEO and boosted SVM classifier outperforms superior performances.

Automated summary

Cloud computing provides on-demand access to computer resources held in remote data centers. Selecting appropriate virtual machines can maximize resource usage and reduce task execution time. The O-LEO algorithm is used to optimize VM selection for efficient cloud-based healthcare services, with boosted SVM improving prediction results for chronic kidney disease.