Gaussian relevance vector MapReduce based annealed Glowworm optimization for big medical data scheduling

Abstract

Various big-data analytics tools and techniques have been developed for handling massive amounts of data in the healthcare sector. However, scheduling is a significant problem to be solved in smart healthcare applications to provide better quality healthcare services and improve the efficiency of related processes when considering large medical files. For this purpose, a new hybrid model called Gaussian Relevance Vector MapReduce-based Annealed Glowworm Optimization Scheduling (GRVM-AGS) was designed to improve the balancing of large medical data files between different physicians with higher scheduling efficiency and minimal time. First, a GRVM model was developed for the predictive analysis of input medical data. This model reduces the storage complexity of large medical data analysis by means of eliminating unwanted patient information and predicts the disease class with help of a Gaussian kernel function. Afterwards, GRVM performs AGS to schedule the efficient workloads among multiple datacenters based on the luciferin value in the smart healthcare environment with reduced scheduling time. Through computational experiments, we demonstrate that GRVM-AGS increases the scheduling efficiency and reduces the scheduling time of large medical data analysis compared to state-of-the-art approaches.