Optimised Internet of Things framework-based hybrid meta-heuristic algorithms for E-healthcare monitoring


Everything can be connected in the Internet of Things (IoTs) technology that enables efficient communication between connected objects. IoTs industry-based meta-heuristic and mining algorithms, which are considered an important field of Artificial Intelligence will be used to construct a healthcare application in this study for lowering costs, increasing efficiency, accurate analysis of data and better care for patient. Meta-heuristic algorithms are now effective modelling and optimisation tools. The proposed framework offers hybrid meta-heuristic and mining algorithms to solve the optimisation and analysis issues. Grey Wolf Optimisation (GWO) applies a spiral-shaped path to assure diversity and convergence. To encourage convergence, the Genetic Algorithm (GA) is introduced. Also, we applied a support vector machine and Naïve Bayes for extracting and analysing important information for heart collected from sensors. The goals are to build Electronic Healthcare (E-Health), which includes establishing a link between patients and health providers to monitor, diagnose and save useful information. It is the foundation for accomplishing efficient and robust monitoring. The results offer that the IoTs framework is optimised and enhanced using the hybrid algorithm, which outperforms the GWO and GA, and the mining algorithms are more accurate with a hybrid algorithm than used mining with only GWO or GA.

Authors: Firas H. Almukhtar

Journal Name: IET Journal

Date of Publication: 15 September 2022

URL: https://ietresearch.onlinelibrary.wiley.com/doi/full/10.1049/ntw2.12057

DOI: https://doi.org/10.1049/ntw2.12057